Journal of the Japan Society for Precision Engineering
Online ISSN : 1882-675X
Print ISSN : 0912-0289
ISSN-L : 0912-0289
Paper
Study of Occlusion-Robust Object Detection with Soft-NMS and Contextual Feature Extraction
Tadafumi NISHIMURATrong Huy PHANKazuma YAMAMOTOMakoto MASUDA
Author information
JOURNAL FREE ACCESS

2021 Volume 87 Issue 1 Pages 71-77

Details
Abstract

Visual object detection (cars, pedestrians, etc.) from vehicle mounted camera faces great difficulty when the target objects are mutually occluded or partially hidden behind background objects. In this paper, in order to realize a occlusion-robust object detector, we propose to use 1) MDCN1), a SSD2)-based detector which utilizes contextual information surrounding the target objects, together with 2) Soft-NMS3), a bounding box unification technique catering to close-by objects. Experiments with the publicly available KITTI4) data acquired from vehicle mounted camera proved the effectiveness of the proposed method.

Information related to the author
© 2021 The Japan Society for Precision Engineering
Previous article Next article
feedback
Top