re-OBJ:Jointly learning the foreground and background for object instance re-identification

James, Stuart

Abstract

Conventional approaches to object instance re-identification rely on matching appearances of the target objects among a set of frames. However, learning appearances of the objects alone might fail when there are multiple objects with similar appearance or multiple instances of same object class present in the scene. This paper proposes that partial observations of the background can be utilized to aid in the object re-identification task for a rigid scene, especially a rigid environment with a lot of reoccurring identical models of objects. Using an extension to the Mask R-CNN architecture, we learn to encode the important and distinct information in the background jointly with the foreground relevant to rigid real-world scenarios such as an indoor environment where objects are static and the camera moves around the scene. We demonstrate the effectiveness of our joint visual feature in the re-identification of objects in the ScanNet dataset and show a relative improvement of around 28.25% in the rank-1 accuracy over the deepSort method.

Citation

James, S. (2019, September). re-OBJ:Jointly learning the foreground and background for object instance re-identification. Presented at Image Analysis and Processing – ICIAP 2019, Trento, Italy

• Presentation Conference Type: Conference Paper (published)
• Conference Name: Image Analysis and Processing – ICIAP 2019
• Start Date: Sep 9, 2019
• End Date: Sep 13, 2019
• Online Publication Date: Oct 2, 2019
• Publication Date: 2019
• Deposit Date: Aug 29, 2024
• Peer Reviewed: Peer Reviewed
• Book Title: International Conference on Image Analysis and Processing
• Keywords: own,conference
• Public URL: https://durham-repository.worktribe.com/output/2024592