Deep learning has already been proved as a powerful state-of-the-art technique for many image understanding tasks in computer vision and other applications including remote sensing (RS) image analysis. Unmanned aircraft systems (UASs) offer a viable and economical alternative to a conventional sensor and platform for acquiring high spatial and high temporal resolution data with high operational flexibility. Coastal wetlands are among some of the most challenging and complex ecosystems for land cover prediction and mapping tasks because land cover targets often show high intra-class and low inter-class variances. In recent years, several deep convolutional neural network (CNN) architectures have been proposed for pixel-wise image labeling, commonly called semantic image segmentation. In this paper, some of the more recent deep CNN architectures proposed for semantic image segmentation are reviewed, and each model’s training efficiency and classification performance are evaluated by training it on a limited labeled image set. Training samples are provided using the hyper-spatial resolution UAS imagery over a wetland area and the required ground truth images are prepared by manual image labeling. Experimental results demonstrate that deep CNNs have a great potential for accurate land cover prediction task using UAS hyper-spatial resolution images. Some simple deep learning architectures perform comparable or even better than complex and very deep architectures with remarkably fewer training epochs. This performance is especially valuable when limited training samples are available, which is a common case in most RS applications.

Small unmanned aircraft systems (sUASs) have emerged as promising platforms for the purpose of crash scene reconstruction through structure-from-motion (SfM) photogrammetry. However, auto crashes tend to occur under adverse weather conditions that usually pose increased risks of sUAS operation in the sky. Wind is a typical environmental factor that can cause adverse weather, and sUAS responses to various wind conditions have been understudied in the past. To bridge this gap, commercial and open source sUAS flight simulation software is employed in this study to analyze the impacts of wind speed, direction, and turbulence on the ability of sUAS to track the pre-planned path and endurance of the flight mission. This simulation uses typical flight capabilities of quadcopter sUAS platforms that have been increasingly used for traffic incident management. Incremental increases in wind speed, direction, and turbulence are conducted. Average 3D error, standard deviation, battery use, and flight time are used as statistical metrics to characterize the wind impacts on flight stability and endurance. Both statistical and visual analytics are performed. Simulation results suggest operating the simulated quadcopter type when wind speed is less than 11 m/s under light to moderate turbulence levels for optimal flight performance in crash scene reconstruction missions, measured in terms of positional accuracy, required flight time, and battery use. Major lessons learned for real-world quadcopter sUAS flight design in windy conditions for crash scene mapping are also documented.

The deep convolutional neural network (DCNN) has recently been applied to the highly challenging and ill-posed problem of single image super-resolution (SISR), which aims to predict high-resolution (HR) images from their corresponding low-resolution (LR) images. In many remote sensing (RS) applications, spatial resolution of the aerial or satellite imagery has a great impact on the accuracy and reliability of information extracted from the images. In this study, the potential of a DCNN-based SISR model, called enhanced super-resolution generative adversarial network (ESRGAN), to predict the spatial information degraded or lost in a hyper-spatial resolution unmanned aircraft system (UAS) RGB image set is investigated. ESRGAN model is trained over a limited number of original HR (50 out of 450 total images) and virtually-generated LR UAS images by downsampling the original HR images using a bicubic kernel with a factor $\times 4$ . Quantitative and qualitative assessments of super-resolved images using standard image quality measures (IQMs) confirm that the DCNN-based SISR approach can be successfully applied on LR UAS imagery for spatial resolution enhancement. The performance of DCNN-based SISR approach for the UAS image set closely approximates performances reported on standard SISR image sets with mean peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) index values of around 28 dB and 0.85 dB, respectively. Furthermore, by exploiting the rigorous Structure-from-Motion (SfM) photogrammetry procedure, an accurate task-based IQM for evaluating the quality of the super-resolved images is carried out. Results verify that the interior and exterior imaging geometry, which are extremely important for extracting highly accurate spatial information from UAS imagery in photogrammetric applications, can be accurately retrieved from a super-resolved image set. The number of corresponding keypoints and dense points generated from the SfM photogrammetry process are about 6 and 17 times more than those extracted from the corresponding LR image set, respectively.

In urban planning and transportation management, the centrality characteristics of urban streets are vital measures to consider. Centrality can help in understanding the structural properties of dense traffic networks that affect both human life and activity in cities. Many cities classify urban streets to provide stakeholders with a group of street guidelines for possible new rehabilitation such as sidewalks, curbs, and setbacks. Transportation research always considers street networks as a connection between different urban areas. The street functionality classification defines the role of each element of the urban street network (USN). Some potential factors such as land use mix, accessible service, design goal, and administrators’ policies can affect the movement pattern of urban travelers. In this study, nine centrality measures are used to classify the urban roads in four cities evaluating the structural importance of street segments. In our work, a Stacked Denoising Autoencoder (SDAE) predicts a street’s functionality, then logistic regression is used as a classifier. Our proposed classifier can differentiate between four different classes adopted from the U.S. Department of Transportation (USDT): principal arterial road, minor arterial road, collector road, and local road. The SDAE-based model showed that regular grid configurations with repeated patterns are more influential in forming the functionality of road networks compared to those with less regularity in their spatial structure.

In this study, the potential of raw samples of digitized echo waveforms collected by full-waveform (FW) terrestrial laser scanning (TLS) for point cloud classification is investigated. Two different TLS systems are employed, both equipped with a waveform digitizer for access to the raw waveform and online waveform processing which assigns calibrated waveform attributes to each point measurement. Point cloud classification based on samples of the raw single-peak echo waveform is compared with point cloud classification based on the calibrated online waveform attributes. A deep convolutional neural network (DCNN) is designed for the supervised classification. Random forest classifier is used as a benchmark to evaluate the performance of the proposed DCNN model. In addition, feature importance and temporal stability of the raw waveform samples versus the calibrated waveform attributes for point cloud classification are reported. Classification results are evaluated at two study sites, a built environment on a university campus and a coastal wetland environment. Results show that direct classification of the raw waveform samples outperforms classification based on the set of waveform attributes at both study sites. Results also show that the contribution of the range, as the only geometric attribute in the raw waveform feature vector, significantly increases the classification performance. Finally, the performance of the DCNN for filtering ground points to generate a digital terrain model (DTM) based on classification of the raw waveform samples is assessed and compared to a DTM generated from a progressive morphological filter and to real-time kinematic (RTK) GNSS survey data.

Information derived from full-waveform (FW) data collected by FW laser scanning systems has already been shown to be relevant for point cloud analysis tasks. Relevant waveform attributes to populate the corresponding point’s feature vector are typically provided through a post-processing FW analysis (FWA) technique based on fitting the echo waveform with a parametric function describing the shape and location of the echo pulse in the waveform. Samples of the digitized echo are the primary source for any waveform analysis using parametric functions. On the other hand, for some FW laser scanning systems, describing the complex system response model using a simple parametric function seems challenging or impractical. Earlier studies have shown the potential of waveform’s digital samples as relevant waveform attributes, for point cloud classification. The main goal of this study is to extend earlier experiments on direct exploitation of returned waveform signals collected by a FW terrestrial laser scanning (TLS) system in a built environment for point cloud classification, to multi-return waveform signals. Furthermore, the classification performance on feature vectors containing calibrated waveform attributes, derived from a waveform processing approach performed in real-time by the FW TLS system, is evaluated on multiple-echo waveforms and compared with the classification performance derived from the proposed FW data classification technique. Classification performance derived through the proposed technique demonstrates high information content of raw digitized waveform samples. Results show that feature vectors containing samples of digitized echoes carry more information about physical properties of the target than those containing calibrated waveform attributes.