Classification of pixel-level fused hyperspectral and lidar data using deep convolutional neural networks

With the increasing number of remote sensing (RS) data sources, the joint utilization of multimodal data in Earth observation tasks has become a crucial research topic. As a typical representative of RS data, hyperspectral images (HSIs) provide accurate spectral information, while rich elevation information can be obtained from light detection and ranging (LiDAR) data. However, due to the significant differences in multimodal heterogeneous features, how to efficiently fuse HSI and LiDAR data remains one of the challenges faced by existing research. In addition, the edge contour information of images is not fully considered by existing methods, which can easily lead to performance bottlenecks. Thus, a joint classification network of HSI and LiDAR data based on Mamba (HLMamba) is proposed. Specifically, a gradient joint algorithm (GJA) is first performed on LiDAR data to obtain the edge contour data of the land distribution. Subsequently, a multimodal feature extraction module (MFEM) was proposed to capture the semantic features of HSI, LiDAR, and edge contour data. Then, to efficiently fuse multimodal features, a novel deep learning (DL) framework called Mamba, was introduced, and a multimodal Mamba fusion module (MMFM) was constructed. By efficiently modeling the long-distance dependencies of multimodal sequences, the MMFM can better explore the internal features of multimodal data and the interrelationships between modalities, thereby enhancing fusion performance. Finally, to validate the effectiveness of HLMamba, a series of experiments were conducted on three common HSI and LiDAR datasets. The results indicate that HLMamba has superior classification performance compared to other state-of-the-art DL methods. The source code of the proposed method will be available publicly at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/Dilingliao/HLMamba</uri>.

Topographical technology by Airborne LIDAR (Light Detection and Ranging) generates a precise points cloud with a density of several points per square meter, LIDAR data processing is a crucial step to be used. Extraction of 3D information in automatic way and especially in urban areas from LIDAR data is one of the most difficult problems in computer vision; it is also a necessary step for implementation of several applications that require a high level interpretation of LASER data. Therefore, there is recently an increased interest in this research field and a vast literature. The problematic discussed in this article lies in the differentiation between the sets of points that represent a specified layer of information (construction, vegetation, roads, lines, etc.). This step is called segmentation. The aim of this study is to provide a set of automatic segmentation techniques tailored to different types of 3D data and proposes a methodology to classify LIDAR data with a maximum degree of automaticity using only point cloud data.

Civil engineering includes a wide range of applications that require three-dimensional (3D) information. With the advent of LiDAR (Light Detection And Ranging) technology, obtaining 3D terrain information accurately in a cost and time effective manner became more popular. In this paper, three case studies demonstrate the roles and applications of airborne LiDAR data including highway, transmission line and hydropower dam development projects. In first case study, the highway alignment was considerably changed after the initial design stage. LiDAR data was able to do the re-alignment survey quickly, allowing for prompt changes in design. In the next case study, a comparison is made between conventional transmission route alignment design and the design using PLS-CADD with LiDAR data. Utilizing the LiDAR data in PLSCADD allows transmission line engineers to model the construction costs of several alignments options effectively and efficiently compared to the conventional method. The last case study uses LiDAR for obtaining the necessary information for proposed dam. Using LiDAR data maximizes topological accuracy and volume measurements while minimizing survey time and costs. Furthermore, utilizing the multi-temporal LiDAR data can reveal valuable information such as topography changes. LiDAR survey technology has proven that it is the best method to capture accurate data from the earth surface which provides maximum density of topographical &amp; digital imagery information for various applications.

Airborne Light Detection and Ranging (LiDAR) topographic data provide highly accurate digital terrain information, which is used widely in applications like creating flood insurance rate maps, forest and tree studies, coastal change mapping, soil and landscape classification, 3D urban modeling, river bank management, agricultural crop studies, etc. In this paper, we focus mainly on the use of LiDAR data in terrain modeling/Digital Elevation Model (DEM) generation. Technological advancements in building LiDAR sensors have enabled highly accurate and highly dense LiDAR point clouds, which have made possible high resolution modeling of terrain surfaces. However, high density data result in massive data volumes, which pose computing issues. Computational time required for dissemination, processing and storage of these data is directly proportional to the volume of the data. We describe a novel technique based on the slope map of the terrain, which addresses the challenging problem in the area of spatial data analysis, of reducing this dense LiDAR data without sacrificing its accuracy. To the best of our knowledge, this is the first ever landscape-driven data reduction algorithm. We also perform an empirical study, which shows that there is no significant loss in accuracy for the DEM generated from a 52% reduced LiDAR dataset generated by our algorithm, compared to the DEM generated from an original, complete LiDAR dataset. For the accuracy of our statistical analysis, we perform Root Mean Square Error (RMSE) comparing all of the grid points of the original DEM to the DEM generated by reduced data, instead of comparing a few random control points. Besides, our multi-core data reduction algorithm is highly scalable. We also describe a modified parallel Inverse Distance Weighted (IDW) spatial interpolation method and show that the DEMs it generates are time-efficient and have better accuracy than the one’s generated by the traditional IDW method.

Foresters are increasingly interested in remote sensing data because they provide an overview of landscape conditions, which is impractical with field sample data alone. Light Detection and Ranging (LiDAR) provides exceptional spatial detail of forest structure, but difficulties in processing LiDAR data have limited their application beyond the research community. Another obstacle to operational use of LiDAR data has been the high cost of data collection. Our objectives in this study were to summarize, at the stand level, both LiDAR- and Landsat (satellite)-based predictions of some common structural and volume attributes and to compare the cost of obtaining such summaries with those obtained through traditional stand exams. We found that the accuracy and cost of a LiDAR-based inventory summarized at the stand level was comparable to traditional stand exams for structural attributes. However, the LiDAR data were able to provide information across a much larger area than the stand exams alone.

A high percentage of forest fires take place around roads. These infrastructures provide an escape route for the population in case of fire. Optimization of forest management in the surroundings of roads is a necessary task in terms of wildfires prevention and mitigation of their effects. Therefore, it is essential to avoid the horizontal continuity of vegetation across roads. A methodology for the measurement of canopy area over roads is developed and based on mobile LiDAR (Light Detection and Ranging) point clouds. The acquisition of LiDAR data is done by Lynx Mobile Mapper System from the University of Vigo. The methodology is automated using LiDAR data processing (M-estimator Sample Consensus and near neighbour algorithms) and image processing techniques (rasterization and binarization). The developed algorithms are tested on a study area, the DP-3606 road (Spain). Results are compared with ground truth data of the canopy projected on the road. The best obtained results present a mean geometric error of 2.82% for 0.25 m resolution and 104.02% for 2 m resolution. Furthermore, the higher the pixel size, the greater the error was obtained with a linear correlation value of 0.99.

High-resolution Light Detection and Ranging (LiDAR) scanners provide detailed information on terrain surfaces, thus enabling the detection of the topographic signatures of historical anthropogenic landforms overgrown by trees or covered by the soil surface. This study aimed to examine the potential of incoming nationwide LiDAR data for detecting the cultural landscape features in Slovakia. We derived a detailed digital elevation model from LiDAR points and adopted upgraded visualisation techniques based on the combination of local relief models, sky view factor, slope steepness, and colour blending. We visually identified examples of different anthropogenic landforms and confirmed our findings with existing literature. In addition, we provide examples of previously unknown historical anthropogenic landforms discovered from LiDAR images. Finally, we discuss the potential and limits of LiDAR data in exploring and protecting different groups of historic anthropogenic landforms as remnants of past cultural landscapes in Slovakia.

In this study, we develop a novel deep hierarchical vision transformer (DHViT) architecture for hyperspectral and light detection and ranging (LiDAR) data joint classification. Current classification methods have limitations in heterogeneous feature representation and information fusion of multi-modality remote sensing data (e.g., hyperspectral and LiDAR data), these shortcomings restrict the collaborative classification accuracy of remote sensing data. The proposed deep hierarchical vision transformer architecture utilizes both the powerful modeling capability of long-range dependencies and strong generalization ability across different domains of the transformer network, which is based exclusively on the self-attention mechanism. Specifically, the spectral sequence transformer is exploited to handle the long-range dependencies along the spectral dimension from hyperspectral images, because all diagnostic spectral bands contribute to the land cover classification. Thereafter, we utilize the spatial hierarchical transformer structure to extract hierarchical spatial features from hyperspectral and LiDAR data, which are also crucial for classification. Furthermore, the cross attention (CA) feature fusion pattern could adaptively and dynamically fuse heterogeneous features from multi-modality data, and this contextual aware fusion mode further improves the collaborative classification performance. Comparative experiments and ablation studies are conducted on three benchmark hyperspectral and LiDAR datasets, and the DHViT model could yield an average overall classification accuracy of 99.58%, 99.55%, and 96.40% on three datasets, respectively, which sufficiently certify the effectiveness and superior performance of the proposed method.

Geometric integration of high-resolution satellite imagery and airborne LiDAR data for improved geopositioning accuracy in metropolitan areas

Improving classification accuracy of airborne LiDAR intensity data by geometric calibration and radiometric correction

The detailed representation of the topography is an important aspect when dealing with any flood simulation model. A Digital Surface Model (DSM) with fine spatial resolution can capture topographic object boundaries with a high level of detail. Light detection and ranging (LiDAR) is a technology that can rapidly collect elevation data of a relatively large topographic area with fine spatial resolution (< 0.5m ∼1m). Information about physical objects on the DSM is critical for storm water management as the propagation of flood water is influenced by both the terrain and the objects on the terrain. The processing of LiDAR data is an important task for generating an accurate DSM suitable to running a flood simulation model. Filtering is the first step in processing LiDAR data. In the LiDAR community, the term “filtering” means the task of separating LiDAR data into ground (bare earth) and non-ground points (buildings and trees). However, the choice of appropriate filtering algorithm is crucial in order to detect micro objects such as boundary walls, fences, and thin embankments that have significant impact on the surface flow pattern. This study offers an innovative approach for developing a LiDAR filtering algorithm that is flexible in nature and able to detect not only buildings and trees but also the micro objects. The filtering algorithm is applied to two study areas, and the output suggests close correspondence to reality.

ABSTRACTLandslides are a pervasive natural disaster, resulting in severe social, environmental and economic impacts worldwide. The tropical, mountainous landscape in South-West Mexico is predisposed to landslides because of frequent hurricanes and earthquakes. The main goal of this study is to compare landslide susceptibility maps in Guerrero derived using high-resolution LIDAR (light detection and ranging) data from both a manual landslide event inventory and an automated landslide inventorying algorithm. The paper also highlights the importance of applying LIDAR data in landslide inventorying and susceptibility mapping.We mapped landslides based on two approaches: (1) manual mapping using satellite images and (2) automatic identification of landslide morphology employing the Contour Connection Method (CCM). We produced a landslide susceptibility map by computing the probability of landslide occurrence from statistical relationships of inventoried landslides detected with LIDAR digital terrain models (DTMs) and derived landslide-causing factors using the logistic regression method.Our results suggest that the automated inventory derived through the CCM algorithm with LIDAR DTMs effectively minimizes the time-consuming and subjective manual inventorying process. The high overall prediction accuracy (up to 0.83) from logistic regression demonstrates the validity and applicability deriving reliable landslide susceptibility maps from an automated inventory; however, LIDAR data are required.

Automatic building extraction is an important topic for many applications such as urban planning, disaster management, 3D building modeling and updating GIS databases. Its approaches mainly depend on two data sources: light detection and ranging (LiDAR) point cloud and aerial imagery both of which have advantages and disadvantages of their own. In this study, in order to benefit from the advantages of each data sources, LiDAR and image data combined together. And then, the building boundaries were extracted with the automated active contour algorithm implemented in MATLAB. Active contour algorithm uses initial contour positions to segment an object in the image. Initial contour positions were detected without user interaction by a series of image enhancements, band ratio and morphological operations. Four test areas with varying building and background levels of detail were selected from ISPRS’s benchmark Vaihingen and Istanbul datasets. Vegetation and shadows were removed from all the datasets by band ratio to improve segmentation quality. Subsequently, LiDAR point cloud data was converted to raster format and added to the aerial imagery as an extra band. Resulting merged image and initial contour positions were given to the active contour algorithm to extract building boundaries. In order to compare the contribution of LiDAR to the proposed method, the boundaries of the buildings were extracted from the input image before and after adding LiDAR data to the image as a layer. Finally extracted building boundaries were smoothed by the Awrangjeb (Int J Remote Sen 37(3): 551–579. https://doi.org/10.1080/01431161.2015.1131868 , 2016) boundary regularization algorithm. Correctness (Corr), completeness (Comp) and accuracy (Q) metrics were used to assess accuracy of segmented building boundaries by comparing extracted building boundaries with manually digitized building boundaries. Proposed approach shows the promising results with over 93% correctness, 92% completeness and 89% quality.

Airborne light detection and ranging (LIDAR) system uses in many field such as military, agriculture, geology and transportation. LIDAR data acquisition consumes several gigabytes from the storage capacity of the system. So, it's necessary to reduce the on board storage capacity as well as its transmission rate. Compression of LIDAR data means reducing the amount of data required to represent the digital data acquired by LIDAR system. This is done by removing data redundancies to achieve compression. In this paper we explain LIDAR system theory and component, compare between lossy and lossless compression techniques then we discuss LIDAR data compression techniques in order to choose a suitable one for LIDAR system that gives high compression ratio with suitable processing time. In most LIDAR data compression techniques classification of LIDAR data is an important issue as a preprocessing step to simplify the data. Using more than one compression algorithms increase the compression ratio but increase the processing time as well.

Currently, the worsening impacts of urbanizations have been impelled to the importance of monitoring and management of existing urban trees, securing sustainable use of the available green spaces. Urban tree species identification and evaluation of their roles in atmospheric Carbon Stock (CS) are still among the prime concerns for city planners regarding initiating a convenient and easily adaptive urban green planning and management system. A detailed methodology on the urban tree carbon stock calibration and mapping was conducted in the urban area of Brussels, Belgium. A comparative analysis of the mapping outcomes was assessed to define the convenience and efficiency of two different remote sensing data sources, Light Detection and Ranging (LiDAR) and WorldView-3 (WV-3), in a unique urban area. The mapping results were validated against field estimated carbon stocks. At the initial stage, dominant tree species were identified and classified using the high-resolution WorldView3 image, leading to the final carbon stock mapping based on the dominant species. An object-based image analysis approach was employed to attain an overall accuracy (OA) of 71% during the classification of the dominant species. The field estimations of carbon stock for each plot were done utilizing an allometric model based on the field tree dendrometric data. Later based on the correlation among the field data and the variables (i.e., Normalized Difference Vegetation Index, NDVI and Crown Height Model, CHM) extracted from the available remote sensing data, the carbon stock mapping and validation had been done in a GIS environment. The calibrated NDVI and CHM had been used to compute possible carbon stock in either case of the WV-3 image and LiDAR data, respectively. A comparative discussion has been introduced to bring out the issues, especially for the developing countries, where WV-3 data could be a better solution over the hardly available LiDAR data. This study could assist city planners in understanding and deciding the applicability of remote sensing data sources based on their availability and the level of expediency, ensuring a sustainable urban green management system.