re-OBJ: Jointly Learning the Foreground and Background for Object Instance Re-identification

TL;DR

This paper introduces re-OBJ, a method that jointly learns foreground and background features using an extended Mask R-CNN to improve object re-identification in rigid scenes, especially with similar objects.

Contribution

It proposes a novel joint learning approach for foreground and background features to enhance object re-identification in static, rigid environments.

Findings

Achieves a 28.25% relative improvement in rank-1 accuracy over DeepSort.

Effectively utilizes background information to distinguish similar objects.

Demonstrates success on the ScanNet dataset.

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.