- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
New approach to enhancing the performance of cloud-based vision system of mobile robots
摘要： Mobile robots require real-time performance, high computation power, and a shared computing environment. Although cloud computing offers computation power, it may adversely affect real-time performance owing to network lag. The main objective of this study is to allow a mobile robot vision system to reliably achieve real-time constraints using cloud computing. A human cloud mobile robot architecture is proposed as well as a data flow mechanism organized on both the mobile robot and the cloud server sides. Two algorithms are proposed: (i) A real-time image clustering algorithm, applied on the mobile robot side, and (ii) A modified growing neural gas algorithm, applied on the cloud server side. The experimental results demonstrate that there is a 25% to 45% enhancement in the total response time, depending on the communication bandwidth and image resolution. Moreover, better performance in terms of data size, path planning time, and accuracy is demonstrated over other state-of-the-art techniques.
关键词： Computation offloading,Computer vision,3D point cloud,Mobile robot,Stereo vision,Real-time networking,Cloud computing,Cloud robotics
更新于2025-09-23 15:23:52
-
Mapping Forest Structure Using UAS inside Flight Capabilities
摘要： We evaluated two unmanned aerial systems (UASs), namely the DJI Phantom 4 Pro and DJI Mavic Pro, for 3D forest structure mapping of the forest stand interior with the use of close-range photogrammetry techniques. Assisted flights were performed within two research plots established in mature pure Norway spruce (Picea abies (L.) H. Karst.) and European beech (Fagus sylvatica L.) forest stands. Geotagged images were used to produce georeferenced 3D point clouds representing tree stem surfaces. With a flight height of 8 m above the ground, the stems were precisely modeled up to a height of 10 m, which represents a considerably larger portion of the stem when compared with terrestrial close-range photogrammetry. Accuracy of the point clouds was evaluated by comparing field-measured tree diameters at breast height (DBH) with diameter estimates derived from the point cloud using four different fitting methods, including the bounding circle, convex hull, least squares circle, and least squares ellipse methods. The accuracy of DBH estimation varied with the UAS model and the diameter fitting method utilized. With the Phantom 4 Pro and the least squares ellipse method to estimate diameter, the mean error of diameter estimates was ?1.17 cm (?3.14%) and 0.27 cm (0.69%) for spruce and beech stands, respectively.
关键词： point cloud,diameter at breast height (DBH),photogrammetry,obstacle sensing,forestry,unmanned aerial system (UAS),vision positioning system
更新于2025-09-23 15:23:52
-
Optical measurements based on practical methods for detecting time-wise morphing structures
摘要： Nowadays non-contact measurement methods have become widely used systems in several fields especially robotics, aerospace, architecture, and cultural heritage. Practical devices, taken from mass markets, are increasingly being used in scientific and engineering research fields thanks to their ability to combine good accuracy with to the low-cost and ready-to-use experimental setup. In the present paper, digital image analysis (based on digital camera devices) and three-dimensional scanning technique (based on Kinect I and Kinect II sensors) are compared to evaluate their performance in detecting a time-wise shape modification. Digital camera and Kinect sensors are used to the non-contact detection of a morphing blade able to modify its geometry according to airflow temperature variation. The comparison showed the capability of the digital image technique to provide quantitative information when a proper alignment is adopted, while the three-dimensional scanning process allows the continuous blade detection useful to quantify the shape modification. Two-dimensional and three-dimensional blade shape reconstruction processes are also discussed.
关键词： Reverse Engineering,Non-contact measurement,Point cloud,Kinect sensor,Optical method,Digital image analysis
更新于2025-09-23 15:23:52
-
Methods for LiDAR-based estimation of extensive grassland biomass
摘要： Biomass estimation derived from Terrestrial Laser Scanning (TLS) is already an established technique in forestry, whereas TLS measurements are less well investigated for use in grassland ecosystems. Detailed information provided by survey systems can enhance management strategies and support timely measures. Field measurements were made in the “UNESCO biosphere reserve Rh?n” in Central Germany with a TLS station (Leica P30). Four methods for estimating biomass from 3d point clouds have been applied to the data, which were Canopy Surface Height (CSH), Sum of Voxel, Mean of 3d-grid Heights, and Convex-Hull. The optimum set of model specific parameters to increase model stability and performance was identified. The methods were compared in terms of model performance and calculation speed. For each method the effect of the number of scans used for each point cloud was assessed. The best fit for fresh biomass determination was achieved with a mean CSH value derived from the top 5% of all CSH values (adj. R2 0.72). In all cases, models for dry biomass estimation had less explanatory power than those for fresh biomass. CSH models based on point clouds, which were merged from two opposite scans, achieved the highest average accuracy both for fresh and dry biomass (adj. R2 0.73 and 0.58 respectively).
关键词： Biomass,TLS,Point cloud,Grassland,LiDAR
更新于2025-09-23 15:23:52
-
Practical optimal registration of terrestrial LiDAR scan pairs
摘要： Point cloud registration is a fundamental problem in 3D scanning. In this paper, we address the frequent special case of registering terrestrial LiDAR scans (or, more generally, levelled point clouds). Many current solutions still rely on the Iterative Closest Point (ICP) method or other heuristic procedures, which require good initializations to succeed and/or provide no guarantees of success. On the other hand, exact or optimal registration algorithms can compute the best possible solution without requiring initializations; however, they are currently too slow to be practical in realistic applications. Existing optimal approaches ignore the fact that in routine use the relative rotations between scans are constrained to the azimuth, via the built-in level compensation in LiDAR scanners. We propose a novel, optimal and computationally efficient registration method for this 4DOF scenario. Our approach operates on candidate 3D keypoint correspondences, and contains two main steps: (1) a deterministic selection scheme that significantly reduces the candidate correspondence set in a way that is guaranteed to preserve the optimal solution; and (2) a fast branch-and-bound (BnB) algorithm with a novel polynomial-time subroutine for 1D rotation search, that quickly finds the optimal alignment for the reduced set. We demonstrate the practicality of our method on realistic point clouds from multiple LiDAR surveys.
关键词： Branch-and-bound,Exact optimization,Point cloud registration
更新于2025-09-23 15:23:52
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - 3D Data Acquisition Using Stereo Camera
摘要： Computer vision systems allow digital reconstruction of targets by capturing information through remote sensors such as video cameras and scanners. In this context, the objective of this work was to evaluate the capacity and quality of three-dimensional reconstruction of static targets using the ZED stereoscopic camera. For this goal, we took images of several environments and objects with different surfaces, textures, lighting, distances and acquisition speeds. The results were compared with high-density and high precision point clouds obtained from the targets using a Leica Viva TS15 total station. The data were processed in the CloudCompare software to calculate the displacement between the models generated by the camera and the total station. Under certain circumstances, this technology is able to reconstruct three-dimensional objects and environments with an error of a few centimeters.
关键词： Machine Vision,Mesh,Point Cloud,ZED Camera,SLAM
更新于2025-09-23 15:23:52
-
[IEEE 2018 24th International Conference on Pattern Recognition (ICPR) - Beijing, China (2018.8.20-2018.8.24)] 2018 24th International Conference on Pattern Recognition (ICPR) - Accurate 3-D Reconstruction with RGB-D Cameras using Depth Map Fusion and Pose Refinement
摘要： Depth map fusion is an essential part in both stereo and RGB-D based 3-D reconstruction pipelines. Whether produced with a passive stereo reconstruction or using an active depth sensor, such as Microsoft Kinect, the depth maps have noise and may have poor initial registration. In this paper, we introduce a method which is capable of handling outliers, and especially, even significant registration errors. The proposed method first fuses a sequence of depth maps into a single non-redundant point cloud so that the redundant points are merged together by giving more weight to more certain measurements. Then, the original depth maps are re-registered to the fused point cloud to refine the original camera extrinsic parameters. The fusion is then performed again with the refined extrinsic parameters. This procedure is repeated until the result is satisfying or no significant changes happen between iterations. The method is robust to outliers and erroneous depth measurements as well as even significant depth map registration errors due to inaccurate initial camera poses.
关键词： point cloud,3-D reconstruction,RGB-D cameras,pose refinement,depth map fusion,registration errors
更新于2025-09-23 15:23:52
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Gaussian Decomposition of LiDAR Waveform Data Simulated by Dart
摘要： Light Detection And Ranging (LiDAR) techniques have been extensively applied in spaceborne, airborne and ground-based platforms. Understanding LiDAR data requires modeling approaches that can precisely account for the physical interactions between the emitted laser pulse and reflecting targets. Diverse LiDAR data types arise from different systems, platforms, and applications. However, most existing physical models consider only single pulse configurations to simulate large footprint LiDAR waveforms, which do not correspond to standard data formats. Hence, in many cases, model outputs are not well adapted to research conducted with actual LiDAR systems, especially for Aerial and Terrestrial Laser Scanning (ALS and TLS) systems. The Discrete Anisotropic Radiation Transfer (DART) model provides accurate and efficient simulations of multiple LiDAR pulses from all platform types. This paper presents the latest development of the DART LiDAR module: Gaussian decomposition of the simulated ALS and TLS waveforms followed by the provision of LiDAR point cloud and waveforms in text and standard ASPRS LAS formats.
关键词： point cloud,DART,waveform,LiDAR,ALS,Gaussian decomposition,TLS
更新于2025-09-23 15:23:52
-
Using multi-scale and hierarchical deep convolutional features for 3D semantic classification of TLS point clouds
摘要： Point cloud classification, which provides meaningful semantic labels to the points in a point cloud, is essential for generating three-dimensional (3D) models. Its automation, however, remains challenging due to varying point densities and irregular point distributions. Adapting existing deep-learning approaches for two-dimensional (2D) image classification to point cloud classification is inefficient and results in the loss of information valuable for point cloud classification. In this article, a new approach that classifies point cloud directly in 3D is proposed. The approach uses multi-scale features generated by deep learning. It comprises three steps: (1) extract single-scale deep features using 3D convolutional neural network (CNN); (2) subsample the input point cloud at multiple scales, with the point cloud at each scale being an input to the 3D CNN, and combine deep features at multiple scales to form multi-scale and hierarchical features; and (3) retrieve the probabilities that each point belongs to the intended semantic category using a softmax regression classifier. The proposed approach was tested against two publicly available point cloud datasets to demonstrate its performance and compared to the results produced by other existing approaches. The experiment results achieved 96.89% overall accuracy on the Oakland dataset and 91.89% overall accuracy on the Europe dataset, which are the highest among the considered methods.
关键词： point cloud,multi-scale,classification,3D,Deep learning
更新于2025-09-23 15:23:52
-
Derivation of space-resolved normal joint spacing and in situ block size distribution data from terrestrial LIDAR point clouds in a rugged Alpine relief (Kühtai, Austria)
摘要： Terrestrial laserscan (TLS) surveys allow the geological investigation of rock slopes, which cannot be measured by direct surveys because of inaccessibility, high hazard potential or excessive effort. The normal joint spacing and the in situ block size distribution are relevant properties for rock mass characterisation but are commonly evaluated statistically or at small regions only. This study presents the jointing characterisation of an Alpine rock slope by both scanline data and a new, automated analysis of point cloud data. The slope, located in the L?ngental (Austria), is characterised by a rugged Alpine relief and granodioritic gneisses fractured by non-persistent joints. The scanline data and the TLS surveys were used to investigate joint set orientations, normal joint spacings and in situ block sizes. Area-wide maps of rock slope properties were prepared from the results of the point cloud analysis. The general results derived from the point clouds are in good agreement with the scanline data. The space-resolved maps show larger block sizes in some of the higher ranging sub-regions and small block sizes in tectonically formed gullies, as well as various local variations. These visualisations are much more beneficial for most rock mechanical questions than common statistical data evaluation approaches using pre-defined sub-regions, which are treated as homogenous areas and thus are missing space-resolved information.
关键词： Point cloud analysis,Terrestrial laserscan,Normal joint spacing,Austria,In situ block size distribution,Joint characterisation
更新于2025-09-23 15:23:52