Object Preserving Siamese Network for Single Object Tracking on Point Clouds
This work addresses a specific bottleneck in 3D object tracking for autonomous driving applications, offering an incremental improvement over existing methods.
The paper tackles the problem of inaccurate bounding box predictions in 3D single object tracking due to random point dropping in Siamese-based trackers, proposing OPSNet to preserve object points and achieve state-of-the-art performance with 9.4% and 2.5% success gains on KITTI and Waymo datasets.
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).