Towards better exploiting convolutional neural networks for remote sensing scene classification

In recent years, deep learning (DL), a rebranding of neural networks (NNs), has risen to the top in numerous areas, namely computer vision (CV), speech recognition, and natural language processing. Whereas remote sensing (RS) possesses a number of unique challenges, primarily related to sensors and applications, inevitably RS draws from many of the same theories as CV, e.g., statistics, fusion, and machine learning, to name a few. This means that the RS community should not only be aware of advancements such as DL, but also be leading researchers in this area. Herein, we provide the most comprehensive survey of state-of-the-art RS DL research. We also review recent new developments in the DL field that can be used in DL for RS. Namely, we focus on theories, tools, and challenges for the RS community. Specifically, we focus on unsolved challenges and opportunities as they relate to (i) inadequate data sets, (ii) human-understandable solutions for modeling physical phenomena, (iii) big data, (iv) nontraditional heterogeneous data sources, (v) DL architectures and learning algorithms for spectral, spatial, and temporal data, (vi) transfer learning, (vii) an improved theoretical understanding of DL systems, (viii) high barriers to entry, and (ix) training and optimizing the DL.

Comprehensive survey of deep learning in remote sensing: theories, tools, and challenges for the community

To secure uninterrupted distribution of electricity, effective monitoring and maintenance of power lines are needed This literature review article aims to give a wide overview of the possibilities provided by modern remote sensing sensors in power line corridor surveys and to discuss the potential and limitations of different approaches Monitoring of both power line components and vegetation around them is included Remotely sensed data sources discussed in the review include synthetic aperture radar (SAR) images, optical satellite and aerial images, thermal images, airborne laser scanner (ALS) data, land-based mobile mapping data, and unmanned aerial vehicle (UAV) data The review shows that most previous studies have concentrated on the mapping and analysis of network components In particular, automated extraction of power line conductors has achieved much attention, and promising results have been reported For example, accuracy levels above 90% have been presented for the extraction of conductors from ALS data or aerial images However, in many studies datasets have been small and numerical quality analyses have been omitted Mapping of vegetation near power lines has been a less common research topic than mapping of the components, but several studies have also been carried out in this field, especially using optical aerial and satellite images Based on the review we conclude that in future research more attention should be given to an integrated use of various data sources to benefit from the various techniques in an optimal way Knowledge in related fields, such as vegetation monitoring from ALS, SAR and optical image data should be better exploited to develop useful monitoring approaches Special attention should be given to rapidly developing remote sensing techniques such as UAVs and laser scanning from airborne and land-based platforms To demonstrate and verify the capabilities of automated monitoring approaches, large tests in various environments and practical monitoring conditions are needed These should include careful quality analyses and comparisons between different data sources, methods and individual algorithms

https://cyberleninka.org/article/n/613852.pdf

Remote sensing methods for power line corridor surveys

In recent years, deep learning (DL), a re-branding of neural networks (NNs), has risen to the top in numerous areas, namely computer vision (CV), speech recognition, natural language processing, etc. Whereas remote sensing (RS) possesses a number of unique challenges, primarily related to sensors and applications, inevitably RS draws from many of the same theories as CV; e.g., statistics, fusion, and machine learning, to name a few. This means that the RS community should be aware of, if not at the leading edge of, of advancements like DL. Herein, we provide the most comprehensive survey of state-of-the-art RS DL research. We also review recent new developments in the DL field that can be used in DL for RS. Namely, we focus on theories, tools and challenges for the RS community. Specifically, we focus on unsolved challenges and opportunities as it relates to (i) inadequate data sets, (ii) human-understandable solutions for modelling physical phenomena, (iii) Big Data, (iv) non-traditional heterogeneous data sources, (v) DL architectures and learning algorithms for spectral, spatial and temporal data, (vi) transfer learning, (vii) an improved theoretical understanding of DL systems, (viii) high barriers to entry, and (ix) training and optimizing the DL.

A Comprehensive Survey of Deep Learning in Remote Sensing: Theories, Tools and Challenges for the Community

Mobile Laser Scanning (MLS) is a versatile remote sensing technology based on Light Detection and Ranging (lidar) technology that has been utilized for a wide range of applications. Several previous reviews focused on applications or characteristics of these systems exist in the literature, however, reviews of the many innovative data processing strategies described in the literature have not been conducted in sufficient depth. To this end, we review and summarize the state of the art for MLS data processing approaches, including feature extraction, segmentation, object recognition, and classification. In this review, we first discuss the impact of the scene type to the development of an MLS data processing method. Then, where appropriate, we describe relevant generalized algorithms for feature extraction and segmentation that are applicable to and implemented in many processing approaches. The methods for object recognition and point cloud classification are further reviewed including both the general concepts as well as technical details. In addition, available benchmark datasets for object recognition and classification are summarized. Further, the current limitations and challenges that a significant portion of point cloud processing techniques face are discussed. This review concludes with our future outlook of the trends and opportunities of MLS data processing algorithms and applications.

Object Recognition, Segmentation, and Classification of Mobile Laser Scanning Point Clouds: A State of the Art Review.

Our work addresses the problem of extracting and classifying tree species from mobile LiDAR data. The work includes tree preprocessing and tree classification. In tree preprocessing, voxel-based upward-growing filtering is proposed to remove ground points from the mobile LiDAR data, followed by a tree segmentation that extracts individual trees via Euclidean distance clustering and voxel-based normalized cut segmentation. In tree classification, first, a waveform representation is developed to model geometric structures of trees. Then, deep learning techniques are used to generate high-level feature abstractions of the trees’ waveform representations. Quantitative analysis shows that our algorithm achieves an overall accuracy of 86.1% and a kappa coefficient of 0.8 in classifying urban tree species using mobile LiDAR data. Comparative experiments demonstrate that the uses of waveform representation and deep Boltzmann machines contribute to the improvement of classification accuracies of tree species.

Deep learning-based tree classification using mobile LiDAR data

This paper presents a step-wise method for extracting power-transmission lines and towers from vehicle-borne light detection and ranging lidar data. First, this method estimates road ranges with regard to incidence angles and separates off-road points from road-surface points by applying elevation-difference and slope criteria to the road ranges scan-line by scan-line. Then, three filters, in terms of height, spatial density, and a combination of size and shape, are proposed to extract power-transmission line/power tower points from the identified off-road points, followed by the extraction of individual power-transmission lines via Hough transform and Euclidean distance clustering. Finally, a three-dimensional 3D power-transmission line is modelled as a horizontal line in the x–y plane and a vertical catenary curve defined by a hyperbolic cosine function in the x–z plane. We evaluated the method using two data sets acquired by the RIEGL VMX-450 system. The average completeness, correctness, and quality of the extracted power-lines on two data sets are 0.92, 0.99, and 0.91, respectively, and the positional accuracies including root mean square error and maximum error averaged 0.07 and 0.05 m, respectively. The results show that the proposed method extracts power-transmission lines from large-scale, vehicle-borne lidar data with good thematic and positional accuracy.

Qi Zhang

Papers

Deep learning-based tree classification using mobile LiDAR data

Extraction of power-transmission lines from vehicle-borne lidar data