Multi-granularity environment perception based on octree occupancy grid
- PDF / 3,573,978 Bytes
- 21 Pages / 439.642 x 666.49 pts Page_size
- 18 Downloads / 213 Views
Multi-granularity environment perception based on octree occupancy grid Ge Zhang1 · Bin Wu1 · Yu-Long Xu2 · Yang-Dong Ye1 Received: 28 October 2019 / Revised: 30 June 2020 / Accepted: 6 July 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract With the development of RGB-D cameras, dense point cloud model gains great attention for its information richness and obstacle avoidance features. It can be overlapped to occupancy grid for path planning and navigation applications. But there are redundant information since point cloud models tend to perceive every details in the environment and the computation complexity of traversal increases significantly with scene expansion. A possible solution is the combination of measurements of different granularities from various sensors to construct the environment models in uniform representation. Based on octree occupancy grid and our previous work, we propose a multi-granularity environment perception algorithm, which uniformly represents environment models from various sensors. A probabilistic octree representation is constructed to uniformly express the point cloud models. This representation uniformly fuses the sparse, semi-dense and dense models dynamically through an incremental algorithm along with the camera trajectory. Multiple resolutions of the same model can be obtained at any time by limiting the depth of a query. Experiments demonstrate the effectiveness of our method in minimizing trajectory error on several public available benchmarks and reducing the space complexity of environment models. Keywords SLAM · Probablistic octree · Occupancy grid · Multi-granularity Yang-Dong Ye
[email protected] Ge Zhang [email protected] Bin Wu [email protected] Yu-Long Xu [email protected] 1
100 Science Avenue, School of Information Engineering, Zhengzhou University, Zhengzhou, China
2
156 Jinshui East Road, School of Information and Technology, Henan University of Traditional Chinese Medicine, Zhengzhou, China
Multimedia Tools and Applications
1 Introduction Environment perception and modeling are the foundation of navigation oriented simultaneous localization and mapping (SLAM) system [3]. It is widely implemented in various platforms, such as drones and autonomous guided vehicle (AGV) with onboard sensors [7]. The map in SLAM system is described by observation function of the observed vector field [32], which is essential in tracking and localization. Several kinds of representations are available in SLAM systems, such as metric map, topological map, point cloud map and occupancy map. The accuracy of planned path is largely determined by the quality of constructed maps. With the extensive use of SLAM system, the environment perception is facing more challenging scenarios, e.g., embedded devices with limited computation capabilities when running in complicated dynamic scenes. The construction and storage of environment models are very important in environment perception of SLAM, which determines the effectiveness and efficiency of
Data Loading...
