PMOD-Net: point-cloud-map-based metric scale obstacle detection by using a monocular camera. (3rd April 2023)

• Record Type: Journal Article
• Authors: Shikishima, Junya; Urasaki, Keisuke; Tasaki, Tsuyoshi
• Is Part Of: Advanced robotics. Volume 37:Number 7(2023)
• Page Start: 458
• Page End: 466
• Publication Date: 2023-04-03
• Subjects: Obstacle detection -- 3d reconstruction -- 3d map -- autonomous driving; Robotics -- Periodicals; Robotics -- Japan -- Periodicals; Robotics; Japan; Periodicals; 629.89205
• DOI: 10.1080/01691864.2022.2153080
• Languages: English
• ISSNs: 0169-1864

Abstract

Abstract : Metric scale obstacle detection, which detects obstacles and measures the distances to them with a metric scale, is a key function in autonomous driving. A monocular camera is inexpensive and effective for detecting objects in images. However, it cannot measure the distances to objects with a metric scale because it can estimate only relative distance. 3D point cloud maps can determine the distances of fixed objects in the 3D map; however, they cannot detect non-fixed obstacles that are not in the 3D map. Therefore, we developed a new method for detecting non-fixed obstacles using a monocular camera and 3D point cloud maps. We used a semantic segmentation neural network (NN) for detecting obstacles and an image-guided depth completion NN for densifying a sparse depth map with a metric scale. We proposed a multitask NN that three-dimensionally reconstructed non-fixed obstacles using the shape information obtained by the semantic segmentation NN. The detection accuracy of the proposed multitask NN was 1.3 times higher than that of a single-task method. Moreover, our robot avoided obstacles using the proposed NN. GRAPHICAL ABSTRACT: UF0001