Efficient Bird Eye View Proposals for 3D Siamese Tracking

Abstract

Tracking vehicles in LIDAR point clouds is a challenging task due to the sparsity of the data and the dense search space. The lack of structure in point clouds impedes the use of convolution filters usually employed in 2D object tracking. In addition, structuring point clouds is cumbersome and implies losing fine-grained information. As a result, generating proposals in 3D space is expensive and inefficient. In this paper, we leverage the dense and structured Bird Eye View (BEV) representation of LIDAR point clouds to efficiently search for objects of interest. We use an efficient Region Proposal Network and generate a small number of object proposals in 3D. Successively, we refine our selection of 3D object candidates by exploiting the similarity capability of a 3D Siamese network. We regularize the latter 3D Siamese network for shape completion to enhance its discrimination capability. Our method attempts to solve both for an efficient search space in the BEV space and a meaningful selection using 3D LIDAR point cloud. We show that the Region Proposal in the BEV outperforms Bayesian methods such as Kalman and Particle Filters in providing proposal by a significant margin and that such candidates are suitable for the 3D Siamese network. By training our method end-to-end, we outperform the previous baseline in vehicle tracking by 12% / 18% in Success and Precision when using only 16 candidates.

References in corpus (8)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• A Novel Performance Evaluation Methodology for Single-Target Trackers
• Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net
• VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
• SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks
• Distractor-aware Siamese Networks for Visual Object Tracking
• TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild
• Particle Filter Networks with Application to Visual Localization

Cited by in corpus (8)

• 3D-SiamRPN: An End-to-End Learning Method for Real-Time 3D Single Object Tracking Using Raw Point Cloud
• Deep Learning for 3D Point Clouds: A Survey
• OST: Efficient One-stream Network for 3D Single Object Tracking in Point Clouds
• Online Adaptation for Implicit Object Tracking and Shape Reconstruction in the Wild
• F-Siamese Tracker: A Frustum-based Double Siamese Network for 3D Single Object Tracking
• FusionMapping: Learning Depth Prediction with Monocular Images and 2D Laser Scans
• Uncertainty-aware Self-supervised 3D Data Association
• Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds