Measurement-wise Occlusion in Multi-object Tracking
This work addresses occlusion handling in multi-object tracking, which is a fundamental problem for practical applications like autonomous driving or surveillance, though it appears incremental as it builds on existing probabilistic tracking frameworks.
The paper tackles the challenge of object occlusion in multi-object tracking by formalizing two abstractions: object-wise occlusion and a novel measurement-wise occlusion, where all objects may generate measurements but some are occluded. It demonstrates the value of measurement-wise occlusion by showing it naturally derives a popular lidar tracking approximation and applies to visual tracking in image space.
Handling object interaction is a fundamental challenge in practical multi-object tracking, even for simple interactive effects such as one object temporarily occluding another. We formalize the problem of occlusion in tracking with two different abstractions. In object-wise occlusion, objects that are occluded by other objects do not generate measurements. In measurement-wise occlusion, a previously unstudied approach, all objects may generate measurements but some measurements may be occluded by others. While the relative validity of each abstraction depends on the situation and sensor, measurement-wise occlusion fits into probabilistic multi-object tracking algorithms with much looser assumptions on object interaction. Its value is demonstrated by showing that it naturally derives a popular approximation for lidar tracking, and by an example of visual tracking in image space.