Fast algorithm for real-time ground extraction from unorganized stereo point clouds
| Autor: | Victor Terra Ferro, Gelson da Cruz Junior, Gilberto Marcon dos Santos, Cassio Vinhal |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
0209 industrial biotechnology
Computer science business.industry 010401 analytical chemistry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Point cloud 02 engineering and technology 01 natural sciences 0104 chemical sciences Image (mathematics) Range (mathematics) 020901 industrial engineering & automation Artificial Intelligence Computer Science::Computer Vision and Pattern Recognition Multilayer perceptron Signal Processing Point (geometry) Segmentation Extraction (military) Computer vision Computer Vision and Pattern Recognition Artificial intelligence business Software |
| Zdroj: | Pattern Recognition Letters. 84:192-198 |
| ISSN: | 0167-8655 |
| DOI: | 10.1016/j.patrec.2016.10.002 |
| Popis: | Fast segmentation algorithm for stereo point clouds.Provides certainty estimation.Accuracy is quantitatively assessed and error cases are presented graphically.3D sensing solution for low budget and small size robotics projects. This paper presents a fast, robust algorithm for ground extraction from unstructured point clouds obtained from stereo reconstruction. Unlike most point cloud segmentation approaches, our algorithm does not rely on 2.5D range image structures nor on any sensor information. All processes involved consider geometry only and do not depend on any reflectivity or color information. We propose applying a top-down 4-ary segmentation followed by a segment-wise classification. This adaptive approach allows accurate differentiation between ground and obstacles in noisy point clouds of cluttered scenes. Real-time performance is achieved on a low cost embedded platform. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect