Search results for "Point Cloud"
showing 10 items of 81 documents
CNN-based People Detection in Voxel Space using Intensity Measurements and Point Cluster Flattening
2021
In this paper real-time people detection is demonstrated in a relatively large indoor industrial robot cell as well as in an outdoor environment. Six depth sensors mounted at the ceiling are used to generate a merged point cloud of the cell. The merged point cloud is segmented into clusters and flattened into gray-scale 2D images in the xy and xz planes. These images are then used as input to a classifier based on convolutional neural networks (CNNs). The final output is the 3D position (x,y,z) and bounding box representing the human. The system is able to detect and track multiple humans in real-time, both indoors and outdoors. The positional accuracy of the proposed method has been verifi…
Replication Data for: Automatic Calibration of an Industrial RGB-D Camera Network using Retroreflective Fiducial Markers.
2019
Replication Data in the form of a Robot Operating System (ROS) recording (ROS-bag) to replicate the results of the paper "Automatic Calibration of an Industrial RGB-D Camera Network using Retroreflective Fiducial Markers." The contents of the dataset are timestamped images and point clouds recorded from six different sensor nodes.
Novel algorithms for 3D surface point cloud boundary detection and edge reconstruction
2019
Abstract Tessellated surfaces generated from point clouds typically show inaccurate and jagged boundaries. This can lead to tolerance errors and problems such as machine judder if the model is used for ongoing manufacturing applications. This paper introduces a novel boundary point detection algorithm and spatial FFT-based filtering approach, which together allow for direct generation of low noise tessellated surfaces from point cloud data, which are not based on pre-defined threshold values. Existing detection techniques are optimized to detect points belonging to sharp edges and creases. The new algorithm is targeted at the detection of boundary points and it is able to do this better tha…
Assessment of Classifiers and Remote Sensing Features of Hyperspectral Imagery and Stereo-Photogrammetric Point Clouds for Recognition of Tree Specie…
2018
Recognition of tree species and geospatial information on tree species composition is essential for forest management. In this study, tree species recognition was examined using hyperspectral imagery from visible to near-infrared (VNIR) and short-wave infrared (SWIR) camera sensors in combination with a 3D photogrammetric canopy surface model based on RGB camera stereo-imagery. An arboretum with a diverse selection of 26 tree species from 14 genera was used as a test area. Aerial hyperspectral imagery and high spatial resolution photogrammetric color imagery were acquired from the test area using unmanned aerial vehicle (UAV) borne sensors. Hyperspectral imagery was processed to calibrated …
3D Reconstruction of Dynamic Vehicles using Sparse 3D-Laser-Scanner and 2D Image Fusion
2016
International audience; Map building becomes one of the most interesting research topic in computer vision field nowadays. To acquire accurate large 3D scene reconstructions, 3D laser scanners are recently developed and widely used. They produce accurate but sparse 3D point clouds of the environments. However, 3D reconstruction of rigidly moving objects along side with the large-scale 3D scene reconstruction is still lack of interest in many researches. To achieve a detailed object-level 3D reconstruction, a single scan of point cloud is insufficient due to their sparsity. For example, traditional Iterative Closest Point (ICP) registration technique or its variances are not accurate and rob…
Process parameters influence in additive manufacturing
2016
Additive manufacturing is a rapidly expanding technology. It allows the creation of very complex 3D objects by adding layers of material, in spite of the traditional production systems based on the removal of material. The development of additive technology has produced initially a generation of additive manufacturing techniques restricted to industrial applications, but their extraordinary degree of innovation has allowed the spreading of household systems. Nowadays, the most common domestic systems produce 3D parts through a fused deposition modeling process. Such systems have low productivity and make, usually, objects with no high accuracy and with unreliable mechanical properties. Thes…
Computer vision-based approach for rite decryption in old societies
2015
International audience; This paper presents an approach to determine the spatial arrangement of bones of horses in an excavation site and perform the 3D reconstruction of the scene. The relative 3D positioning of the bones was computed exploiting the information in images acquired at different levels, and used to relocate provided 3D models of the bones. A novel semi-supervised approach was proposed to generate dense point clouds of the bones from sparse features. The point clouds were later matched with the given models using Iterative Closest Point (ICP).
Relationship between resolution and accuracy of four intraoral scanners in complete-arch impressions
2018
Background The scanner does not measure the dental surface continually. Instead, it generates a point cloud, and these points are then joined to form the scanned object. This approximation will depend on the number of points generated (resolution), which can lead to low accuracy (trueness and precision) when fewer points are obtained. The purpose of this study is to determine the resolution of four intraoral digital imaging systems and to demonstrate the relationship between accuracy and resolution of the intraoral scanner in impressions of a complete dental arch. Material and methods A master cast of the complete maxillary arch was prepared with different dental preparations. Using four di…
3D Reconstruction of rough terrain for USARSim using a height-map method
2008
In this paper, a process for a simplified reconstruction of rough terrains from point clouds acquired using laser scanners is presented. The main idea of this work is to build height-maps which are level gray-scale images representing the ground elevation. These height-maps are generated from step-fields which can be represented by a set of side-by-side pillars. Although height-maps are a practical means for rough terrain reconstruction, it is not possible to represent two different elevations for a given location with one height-map. This is an important drawback as terrain point clouds can show different zones representing surfaces above other surfaces.In this paper, a methodology to crea…
Detection and Isolation of Switches in Point Clouds of the German Railway Network
2015
In order to obtain an automated system of railway management, it is necessary to automatically detect, isolate and identify all switches in a point cloud which represents the railway. To realize this automated system of detection, a set of pre-processing steps is applied. The system begins by detecting and isolating tracks through application of a mask on each section of the point cloud. Then, it does a denoising through mathematical morphology and a compression in replacing a group of points by their centroid. Finally, it closes tracks holes through extrapolation. After that, the system does a low-level processing to search for all intersections between tracks, and records information on t…