Object Preserving Siamese Network for Single Object Tracking on Point Clouds

TL;DR

The paper introduces OPSNet, a novel 3D single object tracking method that preserves object points and features, significantly improving accuracy over previous Siamese-based trackers on KITTI and Waymo datasets.

Contribution

Proposes OPSNet, which enhances object feature preservation and sampling strategies to improve 3D object tracking accuracy.

Findings

Outperforms state-of-the-art on KITTI with 9.4% success gain.

Achieves 2.5% success improvement on Waymo dataset.

Effectively maintains object integrity during tracking.

Abstract

Obviously, the object is the key factor of the 3D single object tracking (SOT) task. However, previous Siamese-based trackers overlook the negative effects brought by randomly dropped object points during backbone sampling, which hinder trackers to predict accurate bounding boxes (BBoxes). Exploring an approach that seeks to maximize the preservation of object points and their object-aware features is of particular significance. Motivated by this, we propose an Object Preserving Siamese Network (OPSNet), which can significantly maintain object integrity and boost tracking performance. Firstly, the object highlighting module enhances the object-aware features and extracts discriminative features from template and search area. Then, the object-preserved sampling selects object candidates to obtain object-preserved search area seeds and drop the background points that contribute less to tracking. Finally, the object localization network precisely locates 3D BBoxes based on the object-preserved search area seeds. Extensive experiments demonstrate our method outperforms the state-of-the-art performance (9.4% and 2.5% success gain on KITTI and Waymo Open Dataset respectively).