Search

Airborne laser bathymetry (ALB) is employed to measure shallow depth water by using a high sampling rate and point density. Thus, the problems of using traditional detection methods in inaccessible areas can be avoided. This study focuses on practical solutions for receiving echo signals, identifying target echoes, and integrating land and underwater terrain point cloud data in coastal environments. Optimization of the system design and its data processing scheme is undertaken to improve the performance of the receiving system based on a single-band ALB system developed by the authors at Shenzhen University. A flight experiment over eastern Hainan Island was conducted, during which the effectiveness of the proposed strategy was verified. Finally, the technical characteristics of the self-developed system are summarized to provide a reliable reference source for the subsequent industrialization and production of related marine light detection and ranging (LiDAR) laser systems. [ABSTRACT FROM AUTHOR]

Three-dimensional (3D) mapping is important to achieve early warning for construction safety and support the long-term safety maintenance of tunnels. However, generating 3D point cloud maps of excavation tunnels that tend to be deficient in features, have rough lining structures, and suffer from dynamic construction interference, can be a challenging task. In this paper, we propose a novel legged robot-aided 3D tunnel mapping method to address the influence of point clouds in the mapping phase. First, a method of kinematic model construction that integrates information from both the robot's motors and the inertial measurement unit (IMU) is proposed to correct the motion distortion of point clouds. Then, a residual compensation model for unreliable regions (abbreviated as the URC model) is proposed to eliminate the inherent alignment errors in the 3D structures. The structural regions of a tunnel are divided into different reliabilities using the K-means method, and an inherent alignment metric is compensated based on region residual estimation. The compensated alignment metric is then incorporated into a rotation-guided anomaly consistency detection (RAD) model. An isolation forest-based anomaly consistency indicator is designed to remove anomalous light detection and ranging (LiDAR) points and reduce sensor noise caused by ultralong distances. To verify the proposed method, we conduct numerous experiments in three tunnels, namely, a drilling and blasting tunnel, a TBM tunnel, and an underground pedestrian tunnel. According to the experimental results, the proposed method achieves 0.84 ‰, 0.40 ‰, and 0.31 ‰ closure errors (CEs) for the three tunnels, respectively, and the absolute map error (AME) and relative map error (RME) are approximately 1.45 cm and 0.57 %, respectively. The trajectory estimation and mapping errors of our method are smaller than those of existing methods, such as FAST-LIO2, Faster-LIO and LiLi-OM. In addition, ablation tests are conducted to further reveal the roles of the different models used in our method for legged robot-aided 3D mapping in tunnels. [ABSTRACT FROM AUTHOR]

Due to the low-cost and lightweight units, single-wavelength LiDAR bathymetric systems are an ideal option for shallow-water (<12 m) bathymetry. However, one disadvantage of such systems is the lack of near-infrared and Raman channels, which results in difficulties in extracting the water surface. Therefore, the choice of a suitable waveform processing method is extremely important to guarantee the accuracy of the bathymetric retrieval. In this paper, we test six algorithms for single-wavelength bathymetric waveform processing, i.e. peak detection (PD), the average square difference function (ASDF), Gaussian decomposition (GD), quadrilateral fitting (QF), Richardson–Lucy deconvolution (RLD), and Wiener filter deconvolution (WD). To date, most of these algorithms have previously only been applied in topographic LiDAR waveforms captured over land. A simulated dataset and an Optech Aquarius dataset were used to assess the algorithms, with the focus being on their capability of extracting the depth and the bottom response. The influences of a number of water and equipment parameters were also investigated by the use of a Monte Carlo method. The results showed that the RLD method had a superior performance in terms of a high detection rate and low errors in the retrieved depth and magnitude. The attenuation coefficient, noise level, water depth, and bottom reflectance had significant influences on the measurement error of the retrieved depth, while the effects of scan angle and water surface roughness were not so obvious. [ABSTRACT FROM AUTHOR]

Abstract: The complexity of building models directly affects the application efficiencies of 3D urban maps. To address the challenges of building models with various structures, we propose a structural simplification method in this paper. The geometric structures of building models are classified into three categories: embedded structures, compositional structures, and connecting structures, which can be extracted separately through convex/concave analysis. Some specific rules are proposed for the simplification of geometric structures, and the building models are suggested to be simplified progressively. The robustness and efficiency of the method are demonstrated by experiments, and the applications of the Levels of detail of the building models are illustrated. [Copyright &y& Elsevier]

This paper primarily presents a parallel incremental Structure from Motion (ISfM) solution for large-scale images captured by unmanned aerial vehicles (UAVs). The core ideas are a local connection-constrained edge weighting strategy for match graph construction and an anchor-free parallel merging algorithm for the merged model generation. First, an effective algorithm is employed to retrieve spatially overlapped match pairs, utilizing the global descriptor for image representation and the graph indexing for nearest neighbor searching. Second, match pairs are used to create an undirected weighted match graph that is weighted by the local connection strength of the image. This match graph is then used to achieve parallel ISfM through graph clustering. Third, an anchor-free cluster merging algorithm, called AFP-Merging, is then designed by taking advantage of the independent connection between clusters, which increases the merging efficiency and stability. For robust estimation, AFP-Merging is implemented via a bidirectional mean square reprojection error. Finally, extensive evaluation and analysis have been carried out to verify its validation using large-scale UAV datasets captured from classical oblique photogrammetry and recent optimized views photogrammetry. Experiment results show that the proposed solution can generate more compact scene clusters and achieve a speedup ratio greater than 9.0 in cluster merging; compared with recent parallel ISfM, its orientation accuracy is higher in both relative bundle adjustment (BA) without GCPs (Ground Control Points) and absolute BA with GCPs. For the orientation of very large-scale UAV images, it has been successfully applied to a dataset containing ninety thousand images over an area of 50.0 km 2. The proposed method provides a more efficient and reliable parallel SfM solution. The executable tool is made publicly available 1 1 https://github.com/json87/ParallelSfM.. [ABSTRACT FROM AUTHOR]

Indoor map is a fundamental element of indoor location-based services (ILBS). However, traditional indoor mapping techniques are labor-intensive and time-consuming. The advancement of smartphones offers great opportunities for crowdsourcing-based indoor mapping, which is one of the most promising applications due to its low cost and flexibility. Over the last decade, many crowdsourcing-based indoor mapping solutions using smartphones have been proposed. This article provides a systematic review of these works. Different from former surveys, we classify the indoor mapping process by the stage of map construction. In particular, we highlight the two key steps, geospatial-element acquisition, and indoor-map construction, and provide state-of-the-art techniques on these topics. Then, we systematically review the crowdsourcing-based indoor mapping solutions under grid-based, landmark-based, and semantic maps. In addition to covering the principles, benefits, and challenges, these systems are compared in terms of sensors, participation, output, experimental environment, and reported accuracy. Besides these existing performance criteria, we extract quantitative performance criteria that are suitable to evaluate crowdsourcing-based indoor mapping solutions. Finally, we present open issues and future research directions. [ABSTRACT FROM AUTHOR]

Accurate atmospheric correction is decisive for ocean color remote sensing applications. Near infrared (NIR)-based algorithm performs well for clear waters; while shortwave infrared (SWIR)-based algorithm can obtain good results for turbid waters, however, it tends to produce noisy patterns for clear waters. A practical strategy is to apply NIR- and SWIR-based algorithm for clear and turbid waters, respectively, which is called NIR-SWIR combined atmospheric correction algorithm. However, the currently applied switching scheme for the NIR-SWIR algorithm undermines the atmospheric correction performance. This study aimed to find an applicable switching scheme for NIR-SWIR algorithm. Four MODIS land bands were used to switch the NIR- and SWIR-based algorithms. A simulated dataset was used to evaluate atmospheric performance of NIR- and SWIR-based algorithm. The switching threshold for each MODIS land band was determined as an R rs value at which SWIR-based algorithm performed better than NIR-based algorithm. The switching scheme was evaluated using matchups of simultaneous MODIS Aqua images and AERONET-OC data, and then tested with a MODIS Aqua image over the western Pacific Ocean. Results showed that the switching threshold for R rs (469), R rs (555), R rs (645) and R rs (859) were 0.009, 0.016, 0.009 and 0.0006 sr−1, respectively; R rs (645) with a threshold of 0.009 sr−1 and R rs (555) with a threshold of 0.016 sr−1 worked well for NIR-SWIR algorithm, while R rs (469) and R rs (859) produced worse performance. Therefore, R rs (555) > 0.016 sr−1 or R rs (645) > 0.009 sr−1 was recommended as the switching scheme for NIR-SWIR algorithm. Considering contrasted estuarine, coastal and some inland waters, combining NIR- and SWIR-based atmospheric correction algorithm with the proposed switching scheme should be useful for remote sensing monitoring over these waters. [ABSTRACT FROM AUTHOR]

Camera-based indoor localization is a fundamental aspect of indoor navigation, virtual reality, and location-based services. Deep learning methods have exhibited remarkable performance with low storage requirements and high efficiency. However, existing methods mainly derive features implicitly for pose regression without considering explicit structure information from images. This paper proposes that incorporating such information can improve the localization performance of learning-based approaches. We extract structure information from RGB images in the form of depth maps and edge maps and design two modules for depth-weighted and edge-weighted feature fusion. These modules are integrated into the pose regression network to enhance pose prediction. Furthermore, we employ a self-attention module for high-level feature extraction to augment the network capacity. Extensive experiments are conducted on the publicly available 7Scenes and 12Scenes datasets, and the results demonstrate that the proposed method achieves high localization performance, with an average positional error of 0. 19 m and 0. 16 m , respectively. The code for this work is available at https://github.com/lqing900205/structureLoc. [ABSTRACT FROM AUTHOR]

Image-based indoor localization provides fundamental support for applications such as indoor navigation, virtual reality, and location-based services. Most research focuses on developing methods in good lighting conditions via RGB images; while for low lighting situations, especially at night, RGB-based methods cannot perform well. Depth images are promising alternative in such conditions as they record geometrical information instead of texture information, making it possible to work in low lighting scenarios. Current depth image-based methods, either retrieval-based methods or 3D registration-based methods, are inefficient due to its high computation overhead, preventing the wide applications. To address this issue, we propose a fast coarse-to-fine localization framework for dark environment via deep learning and keypoint-based geometry alignment. In the coarse localization phase, we jointly perform the depth completion and pose regression to relieve the occlusion caused appearance variance in depth images. In the refinement phase, keypoints are used instead of whole depth image points under the ICP alignment framework to increase the localization efficiency. The keypoints are detected on depth feature maps weakly supervised with pose regression. The experiments on the open available 7Scenes dataset show that the proposed method obtain positional accuracy of 0.143 m and orientational accuracy of 5.275°in average and only cost 0.8s for a single depth image. The code for the proposed work is available at https://github.com/lqing900205/KeyPointDepthLocalization [ABSTRACT FROM AUTHOR]

The spatial information has been widely utilized in Spectral Mixture Analysis (SMA) studies over the years. However, the spatial autocorrelation, as a prerequisite of these studies, was seldomly examined. In the complex urban systems, it remains largely unknown whether and how land cover spectra at different locations are spatially autocorrelated and to which extent spatial autocorrelation can explain the great spectral variability. This study proposed an SMA method with Spatial Endmember Modeling (SEMSMA) to improve the fraction estimation of major urban land cover types. SEMSMA used the Incremental Spatial Autocorrelation (ISA) analysis to quantify spatial autocorrelation patterns in broadband reflectance. With the patterns, SEMSMA predicted endmember signatures that incorporated both spatial (location-oriented) and non-spatial spectral variability via the Restricted Maximum Likelihood-Empirical Best Linear Unbiased Predictor (REML-EBLUP) and Monte Carlo sampling. The spectral variabilities were then addressed in pixel unmixing by an iterative mixture analysis method. Results of ISA demonstrated diverse spatial autocorrelation patterns in reflectance of urban land covers. These patterns can be related to the pathways that spatial processes acted on land cover properties. The predicted endmember signatures explained most of the spectral variability for all land cover types. Subpixel fraction estimates showed that SEMSMA outperformed multiple endmember SMA (MESMA) and spatially adaptive SMA (SASMA), based on the root mean square error (0.04–0.15), the mean absolute error (0.01–0.09), and the Systematic Error (SE) (−80.00–0.01). The low SE of SEMSMA revealed unbiased estimation of land cover fractions. Results of this study underscored the necessity of spatial autocorrelation examination and the advantage of rigorous spatial endmember modeling when incorporating spatial information into SMA. [ABSTRACT FROM AUTHOR]

In aerial photogrammetry, data products are commonly needed in national coordinates, and, in practice, the georeferencing is often performed in the required national map projection frame directly. However, as a map projection frame is not Cartesian, some additional corrections are necessary in the georeferencing process to take account of various map projection distortions. This paper presents a new map projection correction method for the direct georeferencing of aerial images in national coordinates, which comprises of three consecutive steps: (1) a rough intersection to predict ground point coordinates in the Cartesian space; (2) calculating map projection corrections; and (3) a fine intersection. Benefiting from the explicit estimation of ground positions in the Cartesian space, our new method can directly adopt the accurate map projection distortion model that was previously developed for the direct georeferencing of airborne LiDAR data in national coordinates. Simulations show that the correction residuals of our new method are smaller by one order of magnitude than those of the previous best approach while their computational costs are at the same level, and even in an extreme scenario of 8000 m flight height above ground, the maximum error of our method is only several centimeters, which can be safely neglected in practical applications. [ABSTRACT FROM AUTHOR]

Although the deep learning-based indoor image localization has made significant improvement in terms of accuracy, efficiency, and storage requirement of large indoor scenes, the need for collecting huge labeled training data severely limits its practical application. Recently, the synthetic images rendered from widely available 3D models have shown promising potential to relieve the data collection problem. However, due to the dramatic differences between the synthetic and real images, the localization accuracy of approaches trained on synthetic images is not comparable to the methods trained on real images. In this paper, we propose a domain adaptation-based approach to address this issue. Specifically, the proposed approach mainly contains a model consisting of a multi-level constrained pose regression network and a feature-level discriminator network. The discriminator network forces the pose regression network to generate domain-invariant features from real and synthetic images by adversarial learning and thus reduces the performance gaps. In addition, the multi-level constraints further enhance the localization accuracy of pose regression. We perform extensive experiments on open-source rendering images in different settings. The results show that the proposed method significantly improves the performance. The code for the proposed work is available at https://github.com/lqing900205/BIM_domainadaptation. [ABSTRACT FROM AUTHOR]

Urban region function recognition is key to rational urban planning and management. Due to the complex socioeconomic nature of functional land use, recognizing urban region function in high-density cities using remote sensing images alone is difficult. The inclusion of social sensing has the potential to improve the function classification performance. However, effectively integrating the multi-source and multi-modal remote and social sensing data remains technically challenging. In this paper, we have proposed a novel end-to-end deep learning-based remote and social sensing data fusion model to address this issue. Two neural network based methods, one based on a 1-dimensional convolutional neural network (CNN) and the other based on a long short-term memory (LSTM) network, have been developed to automatically extract discriminative time-dependent social sensing signature features, which are fused with remote sensing image features extracted via a residual neural network. One of the major difficulties in exploiting social and remote sensing data is that the two data sources are asynchronous. We have developed a deep learning-based strategy to address this missing modality problem by enforcing cross-modal feature consistency (CMFC) and cross-modal triplet (CMT) constraints. We train the model in an end-to-end manner by simultaneously optimizing three costs, including the classification cost, the CMFC cost and the CMT cost. Extensive experiments have been conducted on publicly available datasets to demonstrate the effectiveness of the proposed method in fusing remote and social sensing data for urban region function recognition. The results show that the seemingly unrelated physically sensed image data and social activities sensed signatures can indeed complement each other to help enhance the accuracy of urban region function recognition. [ABSTRACT FROM AUTHOR]

Image localization is an important supplement to GPS-based methods, especially in indoor scenes. Traditional methods depending on image retrieval or structure from motion (SfM) techniques either suffer from low accuracy or even fail to work due to the texture-less or repetitive indoor surfaces. With the development of range sensors, 3D colourless maps are easily constructed in indoor scenes. How to utilize such a 3D colourless map to improve single image localization performance is a timely but unsolved research problem. In this paper, we present a new approach to addressing this problem by inferring the 3D geometry from a single image with an initial 6DOF pose estimated by a neural network based method. In contrast to previous methods that rely multiple overlapping images or videos to generate sparse point clouds, our new approach can produce dense point cloud from only a single image. We achieve this through estimating the depth map of the input image and performing geometry matching in the 3D space. We have developed a novel depth estimation method by utilizing both the 3D map and RGB images where we use the RGB image to estimate a dense depth map and use the 3D map to guide the depth estimation. We will show that our new method significantly outperforms current RGB image based depth estimation methods for both indoor and outdoor datasets. We also show that utilizing the depth map predicted by the new method for single indoor image localization can improve both position and orientation localization accuracy over state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Abstract The outstanding accuracy and spatial resolution of airborne light detection and ranging (LiDAR) systems allow for very detailed urban monitoring. Classification is a crucial step in LiDAR data processing, as many applications, e.g., 3D city modeling, building extraction, and digital elevation model (DEM) generation, rely on classified results. In this study, we present a novel LiDAR classification approach that uses simple pixel comparison features instead of the manually designed features used in many previous studies. The proposed features are generated by the computed height difference between two randomly selected neighboring pixels. In this way, the feature design does not require prior knowledge or human effort. More importantly, the features encode contextual information and are extremely quick to compute. We apply a random forest classifier to these features and a majority analysis postprocessing step to refine the classification results. The experiments undertaken in this study achieved an overall accuracy of 87.2%, which can be considered good given that only height information from the LiDAR data was used. The results were better than those obtained by replacing the proposed features with five widely accepted man-made features. We conducted algorithm parameter setting tests and an importance analysis to explore how the algorithm works. We found that the pixel pairs directing along the object structure and with a distance of the approximate object size can generate more discriminative pixel comparison features. Comparison with other benchmark results shows that this algorithm can approach the performance of state-of-the-art deep learning algorithms and exceed them in computational efficiency. We conclude that the proposed algorithm has high potential for urban LiDAR classification. [ABSTRACT FROM AUTHOR]