This page has only limited features, please log in for full access.

Prof. Dr. Stefan Hinz
Karlsruhe Institute of Technology (KIT), Institute of Photogrammetry and Remote Sensing (IPF), Englerstr. 7, D-76131 Karlsruhe, Germany

Basic Info

Basic Info is private.

Research Keywords & Expertise

0 Semantic and statistical scene understanding and monitoring
0 Image-based automatic navigation and 3D reconstruction
0 Physical parameter retrieval from multi- and hyperspectral remote sensing
0 Radar- and SAR processing for object motion analysis
0 GI-methods in Augmented Reality

Honors and Awards

The user has no records in this section


Career Timeline

The user has no records in this section.


Short Biography

The user biography is not available.
Following
Followers
Co Authors
The list of users this user is following is empty.
Following: 0 users

Feed

Journal article
Published: 07 June 2021 in Sensors
Reads 0
Downloads 0

With the emergence of low-cost robotic systems, such as unmanned aerial vehicle, the importance of embedded high-performance image processing has increased. For a long time, FPGAs were the only processing hardware that were capable of high-performance computing, while at the same time preserving a low power consumption, essential for embedded systems. However, the recently increasing availability of embedded GPU-based systems, such as the NVIDIA Jetson series, comprised of an ARM CPU and a NVIDIA Tegra GPU, allows for massively parallel embedded computing on graphics hardware. With this in mind, we propose an approach for real-time embedded stereo processing on ARM and CUDA-enabled devices, which is based on the popular and widely used Semi-Global Matching algorithm. In this, we propose an optimization of the algorithm for embedded CUDA GPUs, by using massively parallel computing, as well as using the NEON intrinsics to optimize the algorithm for vectorized SIMD processing on embedded ARM CPUs. We have evaluated our approach with different configurations on two public stereo benchmark datasets to demonstrate that they can reach an error rate as low as 3.3%. Furthermore, our experiments show that the fastest configuration of our approach reaches up to 46 FPS on VGA image resolution. Finally, in a use-case specific qualitative evaluation, we have evaluated the power consumption of our approach and deployed it on the DJI Manifold 2-G attached to a DJI Matrix 210v2 RTK unmanned aerial vehicle (UAV), demonstrating its suitability for real-time stereo processing onboard a UAV.

ACS Style

Boitumelo Ruf; Jonas Mohrs; Martin Weinmann; Stefan Hinz; Jürgen Beyerer. ReS2tAC—UAV-Borne Real-Time SGM Stereo Optimized for Embedded ARM and CUDA Devices. Sensors 2021, 21, 3938 .

AMA Style

Boitumelo Ruf, Jonas Mohrs, Martin Weinmann, Stefan Hinz, Jürgen Beyerer. ReS2tAC—UAV-Borne Real-Time SGM Stereo Optimized for Embedded ARM and CUDA Devices. Sensors. 2021; 21 (11):3938.

Chicago/Turabian Style

Boitumelo Ruf; Jonas Mohrs; Martin Weinmann; Stefan Hinz; Jürgen Beyerer. 2021. "ReS2tAC—UAV-Borne Real-Time SGM Stereo Optimized for Embedded ARM and CUDA Devices." Sensors 21, no. 11: 3938.

Journal article
Published: 21 April 2021 in Water
Reads 0
Downloads 0

This study aims at evaluating the geographical influences of rice-based protection dykes on floodwater regimes along the main rivers, namely the Mekong and the Bassac, in the Vietnamese Mekong Delta (VMD). Specifically, numerous low dykes and high dykes have been constructed particularly in the upper delta’s floodplains to protect the double and triple rice cropping against the annual flooding. For the whole deltaic domain, a 1D-quasi-2D hydrodynamic model setup was used to simulate seventy-two (72) scenarios of dyke construction development in the context of low, medium, and high floods that occurred in the VMD to examine the effects of different flood magnitudes on a certain dyke construction area. Based on the model simulation results, we established an evaluation indicator, the so-called Geographical Impact Factor (GIF), to evaluate the impacts of zone-based dyke compartments on the floodwater regimes along the main rivers for different kinds of floods. Our findings revealed different rates of influences on the floodwater levels along the Mekong and Bassac Rivers under different scenarios of zone-based high-dyke developments. GIF is a useful index for scientists and decision-makers in land use planning, especially in rice intensification, in conjunction with flood management for the VMD and for similar deltas worldwide.

ACS Style

Hoang Vu; Van Trinh; Dung Tran; Peter Oberle; Stefan Hinz; Franz Nestmann. Evaluating the Impacts of Rice-Based Protection Dykes on Floodwater Dynamics in the Vietnamese Mekong Delta Using Geographical Impact Factor (GIF). Water 2021, 13, 1144 .

AMA Style

Hoang Vu, Van Trinh, Dung Tran, Peter Oberle, Stefan Hinz, Franz Nestmann. Evaluating the Impacts of Rice-Based Protection Dykes on Floodwater Dynamics in the Vietnamese Mekong Delta Using Geographical Impact Factor (GIF). Water. 2021; 13 (9):1144.

Chicago/Turabian Style

Hoang Vu; Van Trinh; Dung Tran; Peter Oberle; Stefan Hinz; Franz Nestmann. 2021. "Evaluating the Impacts of Rice-Based Protection Dykes on Floodwater Dynamics in the Vietnamese Mekong Delta Using Geographical Impact Factor (GIF)." Water 13, no. 9: 1144.

Journal article
Published: 16 February 2021 in Remote Sensing
Reads 0
Downloads 0

Information about the chlorophyll a concentration of inland water bodies is essential for water monitoring. This study focuses on estimating chlorophyll a with remote sensing data, and machine learning (ML) approaches on the real-world SpecWa dataset. We adapt and apply a one-dimensional convolutional neural network (1D CNN) as a deep learning architecture for the first time to address this estimation. Since such a DL approach requires a large amount of data for its training, we rely on simulation data generated by the Water Color Simulator (WASI). This simulation is prepared accordingly and includes a knowledge-based water composition with two origins of the chlorophyll a concentration. Therefore, the training data is independent of the real-world SpecWa dataset, which is challenging for any ML approach. We define two spectral downsampling approaches as a pre-processing step, representing the hyperspectral EnMAP satellite mission (SR-EnMAP) and the multispectral Sentinel-2 mission (SR-Sentinel). Subsequently, we train a Random Forest, an artificial neural network, a band-ratio approach, and the 1D CNN on the WASI-generated simulation training dataset. Finally, all ML models are evaluated on the real SpecWa dataset. For both downsampled data, the 1D CNN outperforms the other ML models. On the finer resolved SR-EnMAP data it achieves an R 2 = 81.9 % , R M S E = 12.4 μg L−1, and M A E = 6.7 μg L−1. Besides, the 1D CNN’s performance decreases on the SR-Sentinel data to R 2 = 62.4 % . When focusing on the individual water bodies of the SpecWa dataset, the most significant differences exist between natural and artificial water bodies. We discover that the applied models estimate the chlorophyll a concentration of most natural water bodies satisfyingly. In sum, the newly DL approach can estimate the chlorophyll a values of unknown inland water bodies successfully, although it is trained on an entire simulation dataset.

ACS Style

Philipp Maier; Sina Keller; Stefan Hinz. Deep Learning with WASI Simulation Data for Estimating Chlorophyll a Concentration of Inland Water Bodies. Remote Sensing 2021, 13, 718 .

AMA Style

Philipp Maier, Sina Keller, Stefan Hinz. Deep Learning with WASI Simulation Data for Estimating Chlorophyll a Concentration of Inland Water Bodies. Remote Sensing. 2021; 13 (4):718.

Chicago/Turabian Style

Philipp Maier; Sina Keller; Stefan Hinz. 2021. "Deep Learning with WASI Simulation Data for Estimating Chlorophyll a Concentration of Inland Water Bodies." Remote Sensing 13, no. 4: 718.

Journal article
Published: 01 September 2020 in Journal of Urban Planning and Development
Reads 0
Downloads 0

The purpose of this study is to provide a rapid monitoring of the recent patterns and trends of urban growth in the north of Jordan as a result of increasing refugee fluxes from nearby countries due to the Syrian political conflict. A time series of medium spatial resolution optical satellite images have been used to describe change events in the study area. These satellite images, obtained from different sensors and which were acquired for the years 2010 and 2015, cover four governorates in the north of Jordan. Supervised classification and change analysis are used to detect if there is any expansion of urban areas in the region. The results indicate that most of the extensions and developments are in the urban fringe where the agricultural lands, range lands, bare soil, and rural settlements are converted to urban. A postclassification comparison reveals an increase in urban areas by 7.8% during the study period. The used control area in this study is recommended for future continued monitoring as the final destination of future refugees is not clear and cannot be specified from the beginning.

ACS Style

Nawras Shatnawi; Uwe Weidner; Stefan Hinz. Monitoring Urban Expansion as a Result of Refugee Fluxes in North Jordan Using Remote Sensing Techniques. Journal of Urban Planning and Development 2020, 146, 04020026 .

AMA Style

Nawras Shatnawi, Uwe Weidner, Stefan Hinz. Monitoring Urban Expansion as a Result of Refugee Fluxes in North Jordan Using Remote Sensing Techniques. Journal of Urban Planning and Development. 2020; 146 (3):04020026.

Chicago/Turabian Style

Nawras Shatnawi; Uwe Weidner; Stefan Hinz. 2020. "Monitoring Urban Expansion as a Result of Refugee Fluxes in North Jordan Using Remote Sensing Techniques." Journal of Urban Planning and Development 146, no. 3: 04020026.

Journal article
Published: 14 March 2020 in Remote Sensing
Reads 0
Downloads 0

This article spanned a new, consistent framework for production, archiving, and provision of analysis ready data (ARD) from multi-source and multi-temporal satellite acquisitions and an subsequent image fusion. The core of the image fusion was an orthogonal transform of the reflectance channels from optical sensors on hypercomplex bases delivered in Kennaugh-like elements, which are well-known from polarimetric radar. In this way, SAR and Optics could be fused to one image data set sharing the characteristics of both: the sharpness of Optics and the texture of SAR. The special properties of Kennaugh elements regarding their scaling—linear, logarithmic, normalized—applied likewise to the new elements and guaranteed their robustness towards noise, radiometric sub-sampling, and therewith data compression. This study combined Sentinel-1 and Sentinel-2 on an Octonion basis as well as Sentinel-2 and ALOS-PALSAR-2 on a Sedenion basis. The validation using signatures of typical land cover classes showed that the efficient archiving in 4 bit images still guaranteed an accuracy over 90% in the class assignment. Due to the stability of the resulting class signatures, the fuzziness to be caught by Machine Learning Algorithms was minimized at the same time. Thus, this methodology was predestined to act as new standard for ARD remote sensing data with an subsequent image fusion processed in so-called data cubes.

ACS Style

Andreas Schmitt; Anna Wendleder; Rüdiger Kleynmans; Maximilian Hell; Achim Roth; Stefan Hinz. Multi-Source and Multi-Temporal Image Fusion on Hypercomplex Bases. Remote Sensing 2020, 12, 943 .

AMA Style

Andreas Schmitt, Anna Wendleder, Rüdiger Kleynmans, Maximilian Hell, Achim Roth, Stefan Hinz. Multi-Source and Multi-Temporal Image Fusion on Hypercomplex Bases. Remote Sensing. 2020; 12 (6):943.

Chicago/Turabian Style

Andreas Schmitt; Anna Wendleder; Rüdiger Kleynmans; Maximilian Hell; Achim Roth; Stefan Hinz. 2020. "Multi-Source and Multi-Temporal Image Fusion on Hypercomplex Bases." Remote Sensing 12, no. 6: 943.

Regular paper
Published: 06 February 2020 in Annales Geophysicae
Reads 0
Downloads 0

In this work, the effect of the observing geometry on the tomographic reconstruction quality of both a regularized least squares (LSQ) approach and a compressive sensing (CS) approach for water vapor tomography is compared based on synthetic Global Navigation Satellite System (GNSS) slant wet delay (SWD) estimates. In this context, the term “observing geometry” mainly refers to the number of GNSS sites situated within a specific study area subdivided into a certain number of volumetric pixels (voxels) and to the number of signal directions available at each GNSS site. The novelties of this research are (1) the comparison of the observing geometry's effects on the tomographic reconstruction accuracy when using LSQ or CS for the solution of the tomographic system and (2) the investigation of the effect of the signal directions' variability on the tomographic reconstruction. The tomographic reconstruction is performed based on synthetic SWD data sets generated, for many samples of various observing geometry settings, based on wet refractivity information from the Weather Research and Forecasting (WRF) model. The validation of the achieved results focuses on a comparison of the refractivity estimates with the input WRF refractivities. The results show that the recommendation of Champollion et al. (2004) to discretize the analyzed study area into voxels with horizontal sizes comparable to the mean GNSS intersite distance represents a good rule of thumb for both LSQ- and CS-based tomography solutions. In addition, this research shows that CS needs a variety of at least 15 signal directions per site in order to estimate the refractivity field more accurately and more precisely than LSQ. Therefore, the use of CS is particularly recommended for water vapor tomography applications for which a high number of multi-GNSS SWD estimates are available.

ACS Style

Marion Heublein; Patrick Erik Bradley; Stefan Hinz. Observing geometry effects on a Global Navigation Satellite System (GNSS)-based water vapor tomography solved by least squares and by compressive sensing. Annales Geophysicae 2020, 38, 179 -189.

AMA Style

Marion Heublein, Patrick Erik Bradley, Stefan Hinz. Observing geometry effects on a Global Navigation Satellite System (GNSS)-based water vapor tomography solved by least squares and by compressive sensing. Annales Geophysicae. 2020; 38 (1):179-189.

Chicago/Turabian Style

Marion Heublein; Patrick Erik Bradley; Stefan Hinz. 2020. "Observing geometry effects on a Global Navigation Satellite System (GNSS)-based water vapor tomography solved by least squares and by compressive sensing." Annales Geophysicae 38, no. 1: 179-189.

Journal article
Published: 18 December 2019 in Remote Sensing
Reads 0
Downloads 0

Machine learning approaches are valuable methods in hyperspectral remote sensing, especially for the classification of land cover or for the regression of physical parameters. While the recording of hyperspectral data has become affordable with innovative technologies, the acquisition of reference data (ground truth) has remained expensive and time-consuming. There is a need for methodological approaches that can handle datasets with significantly more hyperspectral input data than reference data. We introduce the Supervised Self-organizing Maps (SuSi) framework, which can perform unsupervised, supervised and semi-supervised classification as well as regression on high-dimensional data. The methodology of the SuSi framework is presented and compared to other frameworks. Its different parts are evaluated on two hyperspectral datasets. The results of the evaluations can be summarized in four major findings: (1) The supervised and semi-Supervised Self-organizing Maps (SOM) outperform random forest in the regression of soil moisture. (2) In the classification of land cover, the supervised and semi-supervised SOM reveal great potential. (3) The unsupervised SOM is a valuable tool to understand the data. (4) The SuSi framework is versatile, flexible, and easy to use. The SuSi framework is provided as an open-source Python package on GitHub.

ACS Style

Felix M. Riese; Sina Keller; Stefan Hinz. Supervised and Semi-Supervised Self-Organizing Maps for Regression and Classification Focusing on Hyperspectral Data. Remote Sensing 2019, 12, 7 .

AMA Style

Felix M. Riese, Sina Keller, Stefan Hinz. Supervised and Semi-Supervised Self-Organizing Maps for Regression and Classification Focusing on Hyperspectral Data. Remote Sensing. 2019; 12 (1):7.

Chicago/Turabian Style

Felix M. Riese; Sina Keller; Stefan Hinz. 2019. "Supervised and Semi-Supervised Self-Organizing Maps for Regression and Classification Focusing on Hyperspectral Data." Remote Sensing 12, no. 1: 7.

Journal article
Published: 15 September 2019 in Remote Sensing
Reads 0
Downloads 0

Knowledge about the existing materials in urban areas has, in recent times, increased in importance. With the use of imaging spectroscopy and hyperspectral remote sensing techniques, it is possible to measure and collect the spectra of urban materials. Most spectral libraries consist of either spectra acquired indoors in a controlled lab environment or of spectra from afar using airborne systems accompanied with in situ measurements. Furthermore, most publicly available spectral libraries have, so far, not focused on facade materials but on roofing materials, roads, and pavements. In this study, we present an urban spectral library consisting of collected in situ material spectra with imaging spectroscopy techniques in the visible and near-infrared (VNIR) and short-wave infrared (SWIR) spectral range, with particular focus on facade materials and material variation. The spectral library consists of building materials, such as facade and roofing materials, in addition to surrounding ground material, but with a focus on facades. This novelty is beneficial to the community as there is a shift to oblique-viewed Unmanned Aerial Vehicle (UAV)-based remote sensing and thus, there is a need for new types of spectral libraries. The post-processing consists partly of an intra-set solar irradiance correction and recalculation of reference spectra caused by signal clipping. Furthermore, the clustering of the acquired spectra was performed and evaluated using spectral measures, including Spectral Angle and a modified Spectral Gradient Angle. To confirm and compare the material classes, we used samples from publicly available spectral libraries. The final material classification scheme is based on a hierarchy with subclasses, which enables a spectral library with a larger material variation and offers the possibility to perform a more refined material analysis. The analysis reveals that the color and the surface structure, texture or coating of a material plays a significantly larger role than what has been presented so far. The samples and their corresponding detailed metadata can be found in the Karlsruhe Library of Urban Materials (KLUM) archive.

ACS Style

Rebecca Ilehag; Andreas Schenk; Yilin Huang; Stefan Hinz. KLUM: An Urban VNIR and SWIR Spectral Library Consisting of Building Materials. Remote Sensing 2019, 11, 2149 .

AMA Style

Rebecca Ilehag, Andreas Schenk, Yilin Huang, Stefan Hinz. KLUM: An Urban VNIR and SWIR Spectral Library Consisting of Building Materials. Remote Sensing. 2019; 11 (18):2149.

Chicago/Turabian Style

Rebecca Ilehag; Andreas Schenk; Yilin Huang; Stefan Hinz. 2019. "KLUM: An Urban VNIR and SWIR Spectral Library Consisting of Building Materials." Remote Sensing 11, no. 18: 2149.

Journal article
Published: 01 July 2019 in Journal of Applied Remote Sensing
Reads 0
Downloads 0

In general, when speaking about change detection using remote sensing imagery, passive and active sensor systems can be mentioned for data acquisition. Especially for change detection and monitoring issues, where a regularly sampled data basis is necessary to produce meaningful analysis results, active sensors have some significant benefits. For example, current synthetic aperture radar (SAR) satellite sensors, such as the German TerraSAR-X (TSX; operating since 2007) and TanDEM-X (TDX; since 2010) missions,1 illuminate the Earth using microwave radiation at a wavelength of about 3 cm. Due to their active transmission of microwave radiation, SAR systems can operate during day and night and independently of clouds, fog, and dust, providing 24/7 monitoring capabilities.2,3 Focusing on the TSX and TDX mission, the high-resolution Spotlight mode HS300 enables the acquisition of images with a geometric resolution of less than 1 m,4 which allows detailed analysis of urban areas.

ACS Style

Markus Boldt; Antje Thiele; Karsten Schulz; Franz J. Meyer; Stefan Hinz. Practical approach for synthetic aperture radar change analysis in urban environments. Journal of Applied Remote Sensing 2019, 13, 034528 .

AMA Style

Markus Boldt, Antje Thiele, Karsten Schulz, Franz J. Meyer, Stefan Hinz. Practical approach for synthetic aperture radar change analysis in urban environments. Journal of Applied Remote Sensing. 2019; 13 (3):034528.

Chicago/Turabian Style

Markus Boldt; Antje Thiele; Karsten Schulz; Franz J. Meyer; Stefan Hinz. 2019. "Practical approach for synthetic aperture radar change analysis in urban environments." Journal of Applied Remote Sensing 13, no. 3: 034528.

Journal article
Published: 26 September 2018 in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Reads 0
Downloads 0
ACS Style

B. Jutzi; M. Weinmann; Stefan Hinz. PREFACE. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2018, IV-1, 1 -3.

AMA Style

B. Jutzi, M. Weinmann, Stefan Hinz. PREFACE. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2018; IV-1 ():1-3.

Chicago/Turabian Style

B. Jutzi; M. Weinmann; Stefan Hinz. 2018. "PREFACE." ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences IV-1, no. : 1-3.

Journal article
Published: 26 September 2018 in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Reads 0
Downloads 0

Change detection represents a broad field of research being on demand for different applications (e.g. disaster management and land use / land cover monitoring). Since the detection itself only delivers information about location and date of the change event, it is limited against approaches dealing with the category, type, or class of the change objects. In contrast to classification, categorization denotes a feature-based clustering of entities (here: change objects) without using any class catalogue information. Therefore, the extraction of suitable features has to be performed leading to a clear distinction of the resulting clusters.In previous work, a change analysis workflow has been accomplished, which comprises both the detection, the categorization, and the classification of so-called high activity change objects extracted from a TerraSAR-X time series dataset. With focus on the features used in this study, the morphological differential attribute profiles (DAPs) turned out to be very promising. It was shown, that the DAP were essential for the construction of the principal components.In this paper, this circumstance is considered. Moreover, a change categorization based only on different and complementary DAP features is performed. An assessment concerning the best suitable features is given.

ACS Style

M. Boldt; A. Thiele; K. Schulz; Stefan Hinz. ON THE CATEGORIZATION OF HIGH ACTIVITY OBJECTS USING DIFFERENTIAL ATTRIBUTE PROFILES. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2018, XLII-1, 59 -64.

AMA Style

M. Boldt, A. Thiele, K. Schulz, Stefan Hinz. ON THE CATEGORIZATION OF HIGH ACTIVITY OBJECTS USING DIFFERENTIAL ATTRIBUTE PROFILES. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2018; XLII-1 ():59-64.

Chicago/Turabian Style

M. Boldt; A. Thiele; K. Schulz; Stefan Hinz. 2018. "ON THE CATEGORIZATION OF HIGH ACTIVITY OBJECTS USING DIFFERENTIAL ATTRIBUTE PROFILES." The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLII-1, no. : 59-64.

Journal article
Published: 26 September 2018 in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Reads 0
Downloads 0

In this paper, we describe and evaluate the process of estimating reflectance corrected temperatures based on infrared measurements in the scope of an industrial cement production plant. We overview the underlying cement production phases, as well as the resulting challenges for infrared-based monitoring in such an industrial environment. Our studies are focused particularly on the use of infrared sensors in the clinker cooling process. Using a highly specialized infrared camera (10.6 μm), a dataset is obtained capturing the radiation emissions of cement clinker during the clinker cooling process at a cement plant. We briefly turn on the necessity of image preprocessing and then focus on calculating reflectance corrected thermal images for temperature estimation without the use of reference markers or additional instrumentation. This study represents the first usage of infrared camera-based measurements in the clinker cooling process. The main contributions, a recorded dataset and two proposed estimation models including a linear model and a machine learning model with their respective temperature estimations, will provide the basis for the extraction of further process characteristics. Therefore, our contributions will enable scientists as well as process operators to gain new insights about the cement clinker cooling process and to optimize the cement cooling and production process automatically.

ACS Style

R. Gabriel; S. Keller; J. Matthes; P. Waibel; H. B. Keller; Stefan Hinz. INFRARED MEASUREMENTS AND ESTIMATION OF TEMPERATURE IN THE RESTRICTIVE SCOPE OF AN INDUSTRIAL CEMENT PLANT. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2018, IV-1, 53 -60.

AMA Style

R. Gabriel, S. Keller, J. Matthes, P. Waibel, H. B. Keller, Stefan Hinz. INFRARED MEASUREMENTS AND ESTIMATION OF TEMPERATURE IN THE RESTRICTIVE SCOPE OF AN INDUSTRIAL CEMENT PLANT. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2018; IV-1 ():53-60.

Chicago/Turabian Style

R. Gabriel; S. Keller; J. Matthes; P. Waibel; H. B. Keller; Stefan Hinz. 2018. "INFRARED MEASUREMENTS AND ESTIMATION OF TEMPERATURE IN THE RESTRICTIVE SCOPE OF AN INDUSTRIAL CEMENT PLANT." ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences IV-1, no. : 53-60.

Journal article
Published: 26 September 2018 in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Reads 0
Downloads 0

In this paper, we investigate the potential of estimating the soil-moisture content based on VNIR hyperspectral data combined with LWIR data. Measurements from a multi-sensor field campaign represent the benchmark dataset which contains measured hyperspectral, LWIR, and soil-moisture data conducted on grassland site. We introduce a regression framework with three steps consisting of feature selection, preprocessing, and well-chosen regression models. The latter are mainly supervised machine learning models. An exception are the self-organizing maps which combine unsupervised and supervised learning. We analyze the impact of the distinct preprocessing methods on the regression results. Of all regression models, the extremely randomized trees model without preprocessing provides the best estimation performance. Our results reveal the potential of the respective regression framework combined with the VNIR hyperspectral data to estimate soil moisture measured under real-world conditions. In conclusion, the results of this paper provide a basis for further improvements in different research directions.

ACS Style

S. Keller; Felix Riese; J. Stötzer; P. M. Maier; Stefan Hinz. DEVELOPING A MACHINE LEARNING FRAMEWORK FOR ESTIMATING SOIL MOISTURE WITH VNIR HYPERSPECTRAL DATA. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2018, IV-1, 101 -108.

AMA Style

S. Keller, Felix Riese, J. Stötzer, P. M. Maier, Stefan Hinz. DEVELOPING A MACHINE LEARNING FRAMEWORK FOR ESTIMATING SOIL MOISTURE WITH VNIR HYPERSPECTRAL DATA. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2018; IV-1 ():101-108.

Chicago/Turabian Style

S. Keller; Felix Riese; J. Stötzer; P. M. Maier; Stefan Hinz. 2018. "DEVELOPING A MACHINE LEARNING FRAMEWORK FOR ESTIMATING SOIL MOISTURE WITH VNIR HYPERSPECTRAL DATA." ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences IV-1, no. : 101-108.

Journal article
Published: 26 September 2018 in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Reads 0
Downloads 0

In this paper, we address the semantic segmentation of aerial imagery based on the use of multi-modal data given in the form of true orthophotos and the corresponding Digital Surface Models (DSMs). We present the Deeply-supervised Shuffling Convolutional Neural Network (DSCNN) representing a multi-scale extension of the Shuffling Convolutional Neural Network (SCNN) with deep supervision. Thereby, we take the advantage of the SCNN involving the shuffling operator to effectively upsample feature maps and then fuse multiscale features derived from the intermediate layers of the SCNN, which results in the Multi-scale Shuffling Convolutional Neural Network (MSCNN). Based on the MSCNN, we derive the DSCNN by introducing additional losses into the intermediate layers of the MSCNN. In addition, we investigate the impact of using different sets of hand-crafted radiometric and geometric features derived from the true orthophotos and the DSMs on the semantic segmentation task. For performance evaluation, we use a commonly used benchmark dataset. The achieved results reveal that both multi-scale fusion and deep supervision contribute to an improvement in performance. Furthermore, the use of a diversity of hand-crafted radiometric and geometric features as input for the DSCNN does not provide the best numerical results, but smoother and improved detections for several objects.

ACS Style

K. Chen; M. Weinmann; X. Sun; M. Yan; Stefan Hinz; B. Jutzi. SEMANTIC SEGMENTATION OF AERIAL IMAGERY VIA MULTI-SCALE SHUFFLING CONVOLUTIONAL NEURAL NETWORKS WITH DEEP SUPERVISION. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2018, IV-1, 29 -36.

AMA Style

K. Chen, M. Weinmann, X. Sun, M. Yan, Stefan Hinz, B. Jutzi. SEMANTIC SEGMENTATION OF AERIAL IMAGERY VIA MULTI-SCALE SHUFFLING CONVOLUTIONAL NEURAL NETWORKS WITH DEEP SUPERVISION. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2018; IV-1 ():29-36.

Chicago/Turabian Style

K. Chen; M. Weinmann; X. Sun; M. Yan; Stefan Hinz; B. Jutzi. 2018. "SEMANTIC SEGMENTATION OF AERIAL IMAGERY VIA MULTI-SCALE SHUFFLING CONVOLUTIONAL NEURAL NETWORKS WITH DEEP SUPERVISION." ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences IV-1, no. : 29-36.

Proceedings article
Published: 01 September 2018 in 2018 9th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)
Reads 0
Downloads 0

Small and lightweight hyperspectral cameras mounted on unmanned aerial systems (UAS) are increasingly used as close range remote sensing systems. When they are applied to studies of biophysical parameters in environmental sciences, user have to consider the radiometric response of the imaging sensor and apply necessary corrections to get unbiased parameter estimates. In this paper we discuss the radiometric characteristics of a hyperspectral snapshot camera and a proper vicarious calibration method. We observe that spectral sampling of each pixel of the camera is individually distorted with respect to the nominal values. These errors must be corrected, since they directly affect the parameter retrieval. We provide a simple method to estimate and correct the spectral sampling of each pixel. With correction of the spectral sampling and additional flat fielding, the precision of estimated water quality parameters can be significantly enhanced.

ACS Style

Jens Kern; Andreas Schenk; Stefan Hinz. Radiometric Calibration of a UAV-Mounted Hyperspectral Snapshot Camera with Focus on Uniform Spectral Sampling. 2018 9th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS) 2018, 1 -5.

AMA Style

Jens Kern, Andreas Schenk, Stefan Hinz. Radiometric Calibration of a UAV-Mounted Hyperspectral Snapshot Camera with Focus on Uniform Spectral Sampling. 2018 9th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS). 2018; ():1-5.

Chicago/Turabian Style

Jens Kern; Andreas Schenk; Stefan Hinz. 2018. "Radiometric Calibration of a UAV-Mounted Hyperspectral Snapshot Camera with Focus on Uniform Spectral Sampling." 2018 9th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS) , no. : 1-5.

Journal article
Published: 30 August 2018 in International Journal of Environmental Research and Public Health
Reads 0
Downloads 0

Inland waters are of great importance for scientists as well as authorities since they are essential ecosystems and well known for their biodiversity. When monitoring their respective water quality, in situ measurements of water quality parameters are spatially limited, costly and time-consuming. In this paper, we propose a combination of hyperspectral data and machine learning methods to estimate and therefore to monitor different parameters for water quality. In contrast to commonly-applied techniques such as band ratios, this approach is data-driven and does not rely on any domain knowledge. We focus on CDOM, chlorophyll a and turbidity as well as the concentrations of the two algae types, diatoms and green algae. In order to investigate the potential of our proposal, we rely on measured data, which we sampled with three different sensors on the river Elbe in Germany from 24 June–12 July 2017. The measurement setup with two probe sensors and a hyperspectral sensor is described in detail. To estimate the five mentioned variables, we present an appropriate regression framework involving ten machine learning models and two preprocessing methods. This allows the regression performance of each model and variable to be evaluated. The best performing model for each variable results in a coefficient of determination R 2 in the range of 89.9% to 94.6%. That clearly reveals the potential of the machine learning approaches with hyperspectral data. In further investigations, we focus on the generalization of the regression framework to prepare its application to different types of inland waters.

ACS Style

Sina Keller; Philipp M. Maier; Felix M. Riese; Stefan Norra; Andreas Holbach; Nicolas Börsig; Andre Wilhelms; Christian Moldaenke; André Zaake; Stefan Hinz. Hyperspectral Data and Machine Learning for Estimating CDOM, Chlorophyll a, Diatoms, Green Algae and Turbidity. International Journal of Environmental Research and Public Health 2018, 15, 1881 .

AMA Style

Sina Keller, Philipp M. Maier, Felix M. Riese, Stefan Norra, Andreas Holbach, Nicolas Börsig, Andre Wilhelms, Christian Moldaenke, André Zaake, Stefan Hinz. Hyperspectral Data and Machine Learning for Estimating CDOM, Chlorophyll a, Diatoms, Green Algae and Turbidity. International Journal of Environmental Research and Public Health. 2018; 15 (9):1881.

Chicago/Turabian Style

Sina Keller; Philipp M. Maier; Felix M. Riese; Stefan Norra; Andreas Holbach; Nicolas Börsig; Andre Wilhelms; Christian Moldaenke; André Zaake; Stefan Hinz. 2018. "Hyperspectral Data and Machine Learning for Estimating CDOM, Chlorophyll a, Diatoms, Green Algae and Turbidity." International Journal of Environmental Research and Public Health 15, no. 9: 1881.

Conference paper
Published: 01 July 2018 in IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium
Reads 0
Downloads 0

In this paper, we focus on the use of multi-modal data to achieve a semantic segmentation of aerial imagery. Thereby, the multi-modal data is composed of a true orthophoto, the Digital Surface Model (DSM) and further representations derived from these. Taking data of different modalities separately and in combination as input to a Residual Shuffling Convolutional Neural Network (RSCNN), we analyze their value for the classification task given with a benchmark dataset. The derived results reveal an improvement if different types of geometric features extracted from the DSM are used in addition to the true orthophoto.

ACS Style

Kaiqiang Chen; Kun Fu; Xian Sun; Michael Weinmann; Stefan Hinz; Boris Jutzi; Martin Weinmann. Deep Semantic Segmentation of Aerial Imagery Based on Multi-Modal Data. IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium 2018, 6219 -6222.

AMA Style

Kaiqiang Chen, Kun Fu, Xian Sun, Michael Weinmann, Stefan Hinz, Boris Jutzi, Martin Weinmann. Deep Semantic Segmentation of Aerial Imagery Based on Multi-Modal Data. IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium. 2018; ():6219-6222.

Chicago/Turabian Style

Kaiqiang Chen; Kun Fu; Xian Sun; Michael Weinmann; Stefan Hinz; Boris Jutzi; Martin Weinmann. 2018. "Deep Semantic Segmentation of Aerial Imagery Based on Multi-Modal Data." IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium , no. : 6219-6222.

Original article
Published: 02 June 2018 in Journal of Geodesy
Reads 0
Downloads 0

In this work, the reconstruction quality of an approach for neutrospheric water vapor tomography based on Slant Wet Delays (SWDs) obtained from Global Navigation Satellite Systems (GNSS) and Interferometric Synthetic Aperture Radar (InSAR) is investigated. The novelties of this approach are (1) the use of both absolute GNSS and absolute InSAR SWDs for tomography and (2) the solution of the tomographic system by means of compressive sensing (CS). The tomographic reconstruction is performed based on (i) a synthetic SWD dataset generated using wet refractivity information from the Weather Research and Forecasting (WRF) model and (ii) a real dataset using GNSS and InSAR SWDs. Thus, the validation of the achieved results focuses (i) on a comparison of the refractivity estimates with the input WRF refractivities and (ii) on radiosonde profiles. In case of the synthetic dataset, the results show that the CS approach yields a more accurate and more precise solution than least squares (LSQ). In addition, the benefit of adding synthetic InSAR SWDs into the tomographic system is analyzed. When applying CS, adding synthetic InSAR SWDs into the tomographic system improves the solution both in magnitude and in scattering. When solving the tomographic system by means of LSQ, no clear behavior is observed. In case of the real dataset, the estimated refractivities of both methodologies show a consistent behavior although the LSQ and CS solution strategies differ.

ACS Style

Marion Heublein; Fadwa AlShawaf; Bastian Erdnüß; Xiao Xiang Zhu; Stefan Hinz. Compressive sensing reconstruction of 3D wet refractivity based on GNSS and InSAR observations. Journal of Geodesy 2018, 93, 197 -217.

AMA Style

Marion Heublein, Fadwa AlShawaf, Bastian Erdnüß, Xiao Xiang Zhu, Stefan Hinz. Compressive sensing reconstruction of 3D wet refractivity based on GNSS and InSAR observations. Journal of Geodesy. 2018; 93 (2):197-217.

Chicago/Turabian Style

Marion Heublein; Fadwa AlShawaf; Bastian Erdnüß; Xiao Xiang Zhu; Stefan Hinz. 2018. "Compressive sensing reconstruction of 3D wet refractivity based on GNSS and InSAR observations." Journal of Geodesy 93, no. 2: 197-217.

Journal article
Published: 28 May 2018 in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Reads 0
Downloads 0

In this paper, we address the deep semantic segmentation of aerial imagery based on multi-modal data. Given multi-modal data composed of true orthophotos and the corresponding Digital Surface Models (DSMs), we extract a variety of hand-crafted radiometric and geometric features which are provided separately and in different combinations as input to a modern deep learning framework. The latter is represented by a Residual Shuffling Convolutional Neural Network (RSCNN) combining the characteristics of a Residual Network with the advantages of atrous convolution and a shuffling operator to achieve a dense semantic labeling. Via performance evaluation on a benchmark dataset, we analyze the value of different feature sets for the semantic segmentation task. The derived results reveal that the use of radiometric features yields better classification results than the use of geometric features for the considered dataset. Furthermore, the consideration of data on both modalities leads to an improvement of the classification results. However, the derived results also indicate that the use of all defined features is less favorable than the use of selected features. Consequently, data representations derived via feature extraction and feature selection techniques still provide a gain if used as the basis for deep semantic segmentation.

ACS Style

K. Chen; M. Weinmann; X. Gao; M. Yan; Stefan Hinz; B. Jutzi. RESIDUAL SHUFFLING CONVOLUTIONAL NEURAL NETWORKS FOR DEEP SEMANTIC IMAGE SEGMENTATION USING MULTI-MODAL DATA. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2018, IV-2, 65 -72.

AMA Style

K. Chen, M. Weinmann, X. Gao, M. Yan, Stefan Hinz, B. Jutzi. RESIDUAL SHUFFLING CONVOLUTIONAL NEURAL NETWORKS FOR DEEP SEMANTIC IMAGE SEGMENTATION USING MULTI-MODAL DATA. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2018; IV-2 ():65-72.

Chicago/Turabian Style

K. Chen; M. Weinmann; X. Gao; M. Yan; Stefan Hinz; B. Jutzi. 2018. "RESIDUAL SHUFFLING CONVOLUTIONAL NEURAL NETWORKS FOR DEEP SEMANTIC IMAGE SEGMENTATION USING MULTI-MODAL DATA." ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences IV-2, no. : 65-72.

Preprint
Published: 24 April 2018
Reads 0
Downloads 0

In this paper, we investigate the potential of estimating the soil-moisture content based on VNIR hyperspectral data combined with IR data. Measurements from a multi-sensor field campaign represent the benchmark dataset which contains measured hyperspectral, IR, and soil-moisture data. We introduce a regression framework with three steps consisting of feature selection, preprocessing, and well-chosen regression models. The latter are mainly supervised machine learning models. An exception are the self-organizing maps which are a combination of unsupervised and supervised learning. We analyze the impact of the distinct preprocessing methods on the regression results. Of all regression models, the extremely randomized trees model without preprocessing provides the best estimation performance. Our results reveal the potential of the respective regression framework combined with the VNIR hyperspectral data to estimate soil moisture. In conclusion, the results of this paper provide a basis for further improvements in different research directions.

ACS Style

Sina Keller; Felix M. Riese; Johanna Stötzer; Philipp M. Maier; Stefan Hinz. Is it possible to retrieve soil-moisture content from measured VNIR hyperspectral data? 2018, 1 .

AMA Style

Sina Keller, Felix M. Riese, Johanna Stötzer, Philipp M. Maier, Stefan Hinz. Is it possible to retrieve soil-moisture content from measured VNIR hyperspectral data? . 2018; ():1.

Chicago/Turabian Style

Sina Keller; Felix M. Riese; Johanna Stötzer; Philipp M. Maier; Stefan Hinz. 2018. "Is it possible to retrieve soil-moisture content from measured VNIR hyperspectral data?" , no. : 1.