Faster object tracking pipeline for real time tracking

TL;DR

This paper presents a generic, optimized object tracking pipeline that significantly speeds up real-time multi-object tracking by parallelizing tasks and employing computational enhancements, making it suitable for industrial applications.

Contribution

The paper introduces a novel pipeline that accelerates detection-based object tracking by parallelizing localization and association, and optimizing computational processes.

Findings

Achieved a 57.8% speed increase, reaching 30 FPS on FullHD videos.

Speed remains consistent regardless of object density in the scene.

Optimal batch sizes depend on GPU memory, balancing speed and resource use.

Abstract

Multi-object tracking (MOT) is a challenging practical problem for vision based applications. Most recent approaches for MOT use precomputed detections from models such as Faster RCNN, performing fine-tuning of bounding boxes and association in subsequent phases. However, this is not suitable for actual industrial applications due to unavailability of detections upfront. In their recent work, Wang et al. proposed a tracking pipeline that uses a Joint detection and embedding model and performs target localization and association in realtime. Upon investigating the tracking by detection paradigm, we find that the tracking pipeline can be made faster by performing localization and association tasks parallely with model prediction. This, and other computational optimizations such as using mixed precision model and performing batchwise detection result in a speed-up of the tracking pipeline by 57.8\% (19 FPS to 30 FPS) on FullHD resolution. Moreover, the speed is independent of the object density in image sequence. The main contribution of this paper is showcasing a generic pipeline which can be used to speed up detection based object tracking methods. We also reviewed different batch sizes for optimal performance, taking into consideration GPU memory usage and speed.