FlowTrack: Point-level Flow Network for 3D Single Object Tracking

3D single object tracking (SOT) is a crucial task in fields of mobile robotics and autonomous driving. Traditional motion-based approaches achieve target tracking by estimating the relative movement of target between two consecutive frames. However, they usually overlook local motion information of the target and fail to exploit historical frame information effectively. To overcome the above limitations, we propose a point-level flow method with multi-frame information for 3D SOT task, called FlowTrack. Specifically, by estimating the flow for each point in the target, our method could capture the local motion details of target, thereby improving the tracking performance. Meanwhile, to handle scenes with sparse points, we present a learnable target feature as the bridge to efficiently integrate target information from past frames. Moreover, we design a Instance Flow Head to transform dense point-level flow into instance-level motion, effectively aggregating local motion information to obtain global target motion. Finally, our method achieves competitive performance with improvements of 5. 9% on the KITTI and 2. 9% on the NuScenes, compared to the next best method.

Authors

• Shuo Li
• Yubo Cui
• Zhiheng Li 0003
• Zheng Fang 0001

Keywords

• Bridges
• Target tracking
• Three-dimensional displays
• Aggregates
• Transforms
• Object tracking
• Intelligent robots
• Autonomous vehicles
• Single Tracking
• Single Object Tracking
• Historical Information
• Target Features
• Tracking Performance
• Consecutive Frames
• Target Information
• Local Details
• Relative Movement
• Motion Information
• Local Motion
• Sparse Point
• Historical Framing
• Convolutional Network
• Convolutional Layers
• Feature Maps
• Pedestrian
• Point Cloud
• Template Feature
• KITTI Dataset
• Current Frame
• Optical Flow Estimation
• Bounding Box
• Motion Estimation
• Multiple Frames
• Motion Prediction
• Rigid Body Transformation
• Prediction Head