Deep Person Re-identification for Probabilistic Data Association in Multiple Pedestrian Tracking
This work addresses tracking challenges in vision-based systems for applications like surveillance, but it is incremental as it builds on existing re-ID and data association methods.
The paper tackled the problem of multiple pedestrian tracking by using deep convolutional features for person re-identification to improve data association, resulting in greatly improved tracking robustness to occlusions and path crossings.
We present a data association method for vision-based multiple pedestrian tracking, using deep convolutional features to distinguish between different people based on their appearances. These re-identification (re-ID) features are learned such that they are invariant to transformations such as rotation, translation, and changes in the background, allowing consistent identification of a pedestrian moving through a scene. We incorporate re-ID features into a general data association likelihood model for multiple person tracking, experimentally validate this model by using it to perform tracking in two evaluation video sequences, and examine the performance improvements gained as compared to several baseline approaches. Our results demonstrate that using deep person re-ID for data association greatly improves tracking robustness to challenges such as occlusions and path crossings.