3-D Single Object Tracking With Temporal-Aware and Attention Mechanism

The 3-D single object tracking (SOT) in point clouds is a computer vision task that involves localizing the target object in subsequent frames given the initial state. Most 3-D SOT methods have only employed the current feature fusion map while overlooking the significance of temporal knowledge. However, it is crucial to incorporate temporal knowledge of the previous target cues into the current feature fusion map, especially in situations involving occlusion, significant appearance variations, and sparse point cloud representations of the target object. In addition, the performance of object tracking is highly dependent on a discriminative feature fusion map. To address these issues, we propose a 3-D SOT by exploiting temporal knowledge and attention mechanisms. First, we design a cascading attention-based feature fusion (CAFF) module to integrate the target cues into the search area, taking into account the intrafeature dependence within each feature and the interfeature dependence between the template and search area features. Second, we present a temporal relation modeling (TRM) module to refine the current feature fusion map by propagating temporal target cues from the previous feature fusion map. To further enhance the performance of the tracker, we present a template update submodule to address the challenges posed by low-quality templates and appearance variations. The experimental results obtained from the KITTI, nuScenes, and Waymo Open Dataset (WOD) datasets demonstrate that the proposed approach achieves competitive performance compared to the state-of-the-art (SOTA) methods. Our method runs at 67.57 frames/s on a single RTX 2080 GPU.