Simple Online and Realtime Tracking with a Deep Association Metric
This work addresses tracking accuracy in computer vision for applications like surveillance, but it is incremental as it builds on the existing SORT method.
The paper tackled the problem of multiple object tracking by integrating appearance information into the SORT framework to handle occlusions better, resulting in a 45% reduction in identity switches while maintaining high frame rates.
Simple Online and Realtime Tracking (SORT) is a pragmatic approach to multiple object tracking with a focus on simple, effective algorithms. In this paper, we integrate appearance information to improve the performance of SORT. Due to this extension we are able to track objects through longer periods of occlusions, effectively reducing the number of identity switches. In spirit of the original framework we place much of the computational complexity into an offline pre-training stage where we learn a deep association metric on a large-scale person re-identification dataset. During online application, we establish measurement-to-track associations using nearest neighbor queries in visual appearance space. Experimental evaluation shows that our extensions reduce the number of identity switches by 45%, achieving overall competitive performance at high frame rates.