IMM-MOT: A Novel 3D Multi-object Tracking Framework with Interacting Multiple Model Filter

3D Multi-Object Tracking (MOT) provides the trajectories of surrounding objects, assisting robots or vehicles in smarter path planning and obstacle avoidance. Existing 3D MOT methods based on the Tracking-by-Detection framework typically use a single motion model to track an object throughout its entire tracking process. However, objects may change their motion patterns due to variations in the surrounding environment. In this paper, we introduce the Interacting Multiple Model filter in IMM-MOT, which accurately fits the complex motion patterns of individual objects, overcoming the limitation of single-model tracking in existing approaches. In addition, we incorporate a Damping Window mechanism into the trajectory lifecycle management, leveraging the continuous association status of trajectories to control their creation and termination, reducing the occurrence of overlooked low-confidence true targets. Furthermore, we propose the Distance-Based Score Enhancement module, which enhances the differentiation between false positives and true positives by adjusting detection scores, thereby improving the effectiveness of the Score Filter. On the NuScenes Val dataset, IMM-MOT outperforms most other single-modal models using 3D point clouds, achieving an AMOTA of 73. 8%. Our project is available at https://github.com/Ap01lo/IMM-MOT.

Authors

• Xiaohong Liu
• Xulong Zhao
• Gang Liu
• Zili Wu
• Tao Wang
• Lei Meng
• Yuhan Wang

Keywords

• Point cloud compression
• Damping
• Solid modeling
• Three-dimensional displays
• Target tracking
• Predictive models
• Data models
• Trajectory
• Windows
• Tuning
• Interaction Model
• Tracking Framework
• Multi-object Tracking
• Interacting Multiple Model
• 3D Multi-object Tracking
• Multiple Model Filter
• True Positive
• Point Cloud
• Path Planning
• Motion Model
• Motion Patterns
• True Target
• Obstacle Avoidance
• Tracking Process
• Set Of Models
• Bounding Box
• Kalman Filter
• Constant Velocity
• Tracking Performance
• Extended Kalman Filter
• Pre-processing Module
• Filter-based Methods
• Non-maximum Suppression
• True Detection
• Point Cloud Data
• Constant Acceleration
• Prediction Phase
• Target Category
• Management Module
• Track Quality