A depth information aided real-time instance segmentation method for space task scenarios under CPU platform. (March 2023)

• Record Type: Journal Article
• Authors: Li, Qianlong; Zhu, Zhanxia; Liang, Junwu; Zhang, Hongwen; Xu, Yanwen; Zhang, Zhihao
• Is Part Of: Acta astronautica. Volume 204(2023)
• Page Start: 666
• Page End: 678
• Publication Date: 2023-03
• Subjects: Instance segmentation -- Intelligence -- Real-time performance -- CPU -- Depth information -- Complex scenes; Astronautics -- Periodicals; Outer space -- Exploration -- Periodicals; Astronautics; Periodicals; 629.405
• DOI: 10.1016/j.actaastro.2023.01.007
• Languages: English
• ISSNs: 0094-5765

Abstract

Abstract: Visual instance segmentation ability is one of the effective means to promote the autonomy and intelligence of space agents. However, due to the limited airborne computing capacity, current methods are difficult to deploy on space agents, because these methods are developed based on GPU. To this end, this paper proposes a novel framework of instance segmentation by introducing depth information and combining traditional computer vision techniques with an object detection method. This framework provides a new idea for the implementation of instance segmentation. The experiment results show that the proposed method achieves a real-time performance under a common laptop CPU platform. In addition, thanks to the introduction of depth information, the proposed method can obtain better segmentation results compared to Mask R–CNN and SOLOv2 in complex scenes (poor illumination and occlusion). Finally, because the semantic information is obtained by the object detection method in this paper, the model training adopts a weakly supervised manner from bounding-box annotations, which can reduce various costs of data labeling to a certain extent. Highlights: A depth-aided instance segmentation fuses mask extraction and object detection. Real-time performance on consumer grade laptop CPU; friendly to airborne platforms. Better segmentation results in complex scenes compared with Mask-RCNN and SOLOv2. Training process adopts a weakly supervised manner from bounding-box annotations.