Object detection from satellite images has been a challenging problem for many years. With the development of effective deep learning algorithms and advancement in hardware systems, higher accuracies have been achieved in the detection of various objects from very high-resolution (VHR) satellite images. This article provides a comparative evaluation of the state-of-the-art convolutional neural network (CNN)-based object detection models, which are Faster R-CNN, Single Shot Multi-box Detector (SSD), and You Look Only Once-v3 (YOLO-v3), to cope with the limited number of labeled data and to automatically detect airplanes in VHR satellite images. Data augmentation with rotation, rescaling, and cropping was applied on the test images to artificially increase the number of training data from satellite images. Moreover, a non-maximum suppression algorithm (NMS) was introduced at the end of the SSD and YOLO-v3 flows to get rid of the multiple detection occurrences near each detected object in the overlapping areas. The trained networks were applied to five independent VHR test images that cover airports and their surroundings to evaluate their performance objectively. Accuracy assessment results of the test regions proved that Faster R-CNN architecture provided the highest accuracy according to the F1 scores, average precision (AP) metrics, and visual inspection of the results. The YOLO-v3 ranked as second, with a slightly lower performance but providing a balanced trade-off between accuracy and speed. The SSD provided the lowest detection performance, but it was better in object localization. The results were also evaluated in terms of the object size and detection accuracy manner, which proved that large- and medium-sized airplanes were detected with higher accuracy.

In this research work, a multi-index-based support vector machine (SVM) classification approach has been proposed to determine the complex and morphologically heterogeneous land cover/use (LCU) patterns of cities, with a special focus on separating bare lands and built-up regions, using Istanbul, Turkey as the main study region, and Ankara and Konya (in Turkey) as the independent test regions. The multi-index approach was constructed using three-band combinations of spectral indices, where each index represents one of the three major land cover categories, green areas, water bodies, and built-up regions. Additionally, a shortwave infrared-based index, the Normalized Difference Tillage Index (NDTI), was proposed as an alternative to existing built-up indices. All possible index combinations and the original ten-band Sentinel-2A image were classified with the SVM algorithm, to map seven LCU classes, and an accuracy assessment was performed to determine the multi-index combination that provided the highest performance. The SVM classification results revealed that the multi-index combination of the normalized difference tillage index (NDTI), the red-edge-based normalized vegetation index (NDVIre), and the modified normalized difference water index (MNDWI) improved the mapping accuracy of the heterogeneous urban areas and provided an effective separation of bare land from built-up areas. This combination showed an outstanding overall performance with a 93% accuracy and a 0.91 kappa value for all LCU classes. The results of the test regions provided similar findings and the same index combination clearly outperformed the other approaches, with 92% accuracy and a 0.90 kappa value for Ankara, and an 84% accuracy and a 0.79 kappa value for Konya. The multi-index combination of the normalized difference built-up index (NDBI), the NDVIre, and the MNDWI, ranked second in the assessment, with similar accuracies to that of the ten-band image classification.

Digital elevation models (DEMs), which can occur in the form of digital surface models (DSMs) or digital terrain models (DTMs), are widely used as important geospatial information sources for various remote sensing applications, including the precise orthorectification of high-resolution satellite images, 3D spatial analyses, multi-criteria decision support systems, and deformation monitoring. The accuracy of DEMs has direct impacts on specific calculations and process chains; therefore, it is important to select the most appropriate DEM by considering the aim, accuracy requirement, and scale of each study. In this research, DSMs obtained from a variety of satellite sensors were compared to analyze their accuracy and performance. For this purpose, freely available Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) 30 m, Shuttle Radar Topography Mission (SRTM) 30 m, and Advanced Land Observing Satellite (ALOS) 30 m resolution DSM data were obtained. Additionally, 3 m and 1 m resolution DSMs were produced from tri-stereo images from the SPOT 6 and Pleiades high-resolution (PHR) 1A satellites, respectively. Elevation reference data provided by the General Command of Mapping, the national mapping agency of Turkey—produced from 30 cm spatial resolution stereo aerial photos, with a 5 m grid spacing and ±3 m or better overall vertical accuracy at the 90% confidence interval (CI)—were used to perform accuracy assessments. Gross errors and water surfaces were removed from the reference DSM. The relative accuracies of the different DSMs were tested using a different number of checkpoints determined by different methods. In the first method, 25 checkpoints were selected from bare lands to evaluate the accuracies of the DSMs on terrain surfaces. In the second method, 1000 randomly selected checkpoints were used to evaluate the methods’ accuracies for the whole study area. In addition to the control point approach, vertical cross-sections were extracted from the DSMs to evaluate the accuracies related to land cover. The PHR and SPOT DSMs had the highest accuracies of all of the testing methods, followed by the ALOS DSM, which had very promising results. Comparatively, the SRTM and ASTER DSMs had the worst accuracies. Additionally, the PHR and SPOT DSMs captured man-made objects and above-terrain structures, which indicated the need for post-processing to attain better representations.

Convolutional neural network (CNN)-based approaches have shown promising results in the pansharpening of the satellite images in recent years. However, they still exhibit limitations in producing high-quality pansharpening outputs. To that end, we propose a new self-supervised learning framework, where we treat pansharpening as a colorization problem, which brings an entirely novel perspective and solution to the problem compared with the existing methods that base their solution solely on producing a super-resolution version of the multispectral image. Whereas the CNN-based methods provide a reduced-resolution panchromatic image as the input to their model along with the reduced-resolution multispectral images and, hence, learn to increase their resolution together, we instead provide the grayscale transformed multispectral image as the input and train our model to learn the colorization of the grayscale input. We further address the fixed downscale ratio assumption during training, which does not generalize well to the full-resolution scenario. We introduce a noise injection into the training by randomly varying the downsampling ratios. Those two critical changes, along with the addition of adversarial training in the proposed PanColorization generative adversarial network (PanColorGAN) framework, help overcome the spatial-detail loss and blur problems that are observed in CNN-based pansharpening. The proposed approach outperforms the previous CNN-based and traditional methods, as demonstrated in our experiments.

Accurate and timely information about land use and land cover (LULC) and its changes in urban areas are crucial for urban land management decision-making, ecosystem monitoring and urban planning. Also, monitoring and representation of urban sprawl and its effects on the LULC patterns and hydrological processes of an urbanized watershed is an essential part of water resource planning and management. This paper presents an image analysis study using multi temporal digital satellite imagery of LULC and changes in the Kucukcekmece Watershed (Metropolitan Istanbul, Turkey) from 1992 to 2006. The Kucukcekmece Basin includes portions of the Kucukcekmece District within the municipality of Istanbul so it faces a dramatic urbanization. An urban monitoring analysis approach was first used to implement a land cover classification. A change detection method controlled with ground truth information was then used to determine changes in land cover. During the study period, the variability and magnitude of hydrological components based on land-use patterns were cumulatively influenced by urban sprawl in the watershed. The proposed approach, which uses a combination of Remote Sensing (RS) and Geographical Information System (GIS) techniques, is an effective tool that enhances land-use monitoring, planning, and management of urbanized watersheds.