Understanding Sensor Fusion and Tracking, Part 5: How to Track Multiple Objects at Once

Check out the other videos in the series: Part 1 - What Is Sensor Fusion? Part 2 - Fusing an Accel, Mag, and Gyro to Estimation Orientation Part 3 - Fusing a GPS and IMU to Estimate Pose Part 4 - Tracking a Single Object with an IMM Filter This video describes two common problems that arise when tracking multiple objects: data association and track maintenance. We cover a few ways to solve these issues and provide a general way to approach all multi-object tracking problems. We cover data association algorithms like global nearest neighbor (GNN) and joint probabilistic data association (JPDA) and look at the criteria for deleting and creating tracks. We talk about gating observations so that we don’t waste computational resources. At the end of the video, we show an example of GNN and JPDA algorithms operating on two objects in close proximity. Check out these other references! Multi-Object Trackers: https://bit.ly/2qrpzB1

Previous Lectures:
1. Understanding Sensor Fusion and Tracking, Part 1: What Is Sensor Fusion?
2. Understanding Sensor Fusion and Tracking, Part 2: Fusing a Mag, Accel, & Gyro Estimate
3. Understanding Sensor Fusion and Tracking, Part 3: Fusing a GPS and IMU to Estimate Pose
4. Understanding Sensor Fusion and Tracking, Part 4: Tracking a Single Object With an IMM Filter