Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Deep Supervised Descent Method With Multiple Seeds Generation for 3-D Tracking in Point Cloud
AU - Tian, Shengjing
AU - Liu, Bin
AU - Tan, Hongchen
AU - Liu, Jun
AU - Liu, Meng
AU - Liu, Xiuping
PY - 2022/8/31
Y1 - 2022/8/31
N2 - Three-dimensional (3-D) tracking in point cloud is a core competence of autonomous robots to perceive and forecast the environment. How to initialize bounding box seeds and optimize their position and orientation are very crucial for 3-D object tracking in point clouds. Nevertheless, existing methods mainly resort to developing a powerful classifier based on the initial bounding box seeds. In this article, we propose an end-to-end deep supervised descent method (SDM), which seamlessly integrates multiple seeds generation for the initialization of seeds and sequential updates for the estimation of accurate result. Specifically, we start with transforming the SDM iterative process into a trainable recurrent module. It explicitly learns a series of descent directions in the parameter space, to gradually optimize the initial seeds. Moreover, to alleviate drifting of this process, we initialize multiple seeds based on aggregated point sets generated by the deep Hough voting. Besides, a discrimination module is introduced to determine the bounding box with the highest score as the final result. Importantly, a specific multitask loss is proposed to train our model in an end-to-end way. Experiments on KITTI, PandaSet, and Waymo datasets show that our method could achieve significant improvements (up to 11.2% in success ratio) as compared to state-of-the-art trackers.
AB - Three-dimensional (3-D) tracking in point cloud is a core competence of autonomous robots to perceive and forecast the environment. How to initialize bounding box seeds and optimize their position and orientation are very crucial for 3-D object tracking in point clouds. Nevertheless, existing methods mainly resort to developing a powerful classifier based on the initial bounding box seeds. In this article, we propose an end-to-end deep supervised descent method (SDM), which seamlessly integrates multiple seeds generation for the initialization of seeds and sequential updates for the estimation of accurate result. Specifically, we start with transforming the SDM iterative process into a trainable recurrent module. It explicitly learns a series of descent directions in the parameter space, to gradually optimize the initial seeds. Moreover, to alleviate drifting of this process, we initialize multiple seeds based on aggregated point sets generated by the deep Hough voting. Besides, a discrimination module is introduced to determine the bounding box with the highest score as the final result. Importantly, a specific multitask loss is proposed to train our model in an end-to-end way. Experiments on KITTI, PandaSet, and Waymo datasets show that our method could achieve significant improvements (up to 11.2% in success ratio) as compared to state-of-the-art trackers.
U2 - 10.1109/TII.2021.3126391
DO - 10.1109/TII.2021.3126391
M3 - Journal article
VL - 18
SP - 5077
EP - 5086
JO - IEEE Transactions on Industrial Informatics
JF - IEEE Transactions on Industrial Informatics
SN - 1551-3203
IS - 8
ER -