Unsupervised Subcategory Domain Adaptive Network for 3D Object Detection in LiDAR

Abstract

Three-dimensional object detection based on the LiDAR point cloud plays an important role in autonomous driving. The point cloud distribution of the object varies greatly at different distances, observation angles, and occlusion levels. Besides, different types of LiDARs have different settings of projection angles, thus producing an entirely different point cloud distribution. Pre-trained models on the dataset with annotations may degrade on other datasets. In this paper, we propose a method for object detection using an unsupervised adaptive network, which does not require additional annotation data of the target domain. Our object detection adaptive network consists of a general object detection network, a global feature adaptation network, and a special subcategory instance adaptation network. We divide the source domain data into different subcategories and use a multi-label discriminator to assign labels dynamically to the target domain data. We evaluated our approach on the KITTI object benchmark and proved that the proposed unsupervised adaptive method could achieve a remarkable improvement in the adaptation capabilities.

Dynamic Vehicle Pose Estimation with Heuristic L-Shape Fitting and Grid-Based Particle Filter

“…Besides, the threshold value of the symmetrical segment number N sym is in the range of [5,20]. The value of δ is in the range of [1,60] degrees.…”

“…The field of autonomous driving has gained significant attention worldwide, leading to extensive research efforts in recent years [1,2]. The autonomous driving system consists of several components, including environmental perception, decision-making and planning, and control execution [3].…”