CropTrack: A Tracking with Re-Identification Framework for Precision Agriculture

TL;DR

CropTrack is a novel multi-object tracking framework for agriculture that combines appearance and motion cues, significantly improving identity preservation and accuracy over traditional methods in challenging agricultural environments.

Contribution

It introduces a new framework integrating reranking-enhanced appearance association and a prototype feature bank for better tracking in agricultural scenarios.

Findings

Outperforms traditional motion-based trackers in agricultural datasets

Achieves higher identification F1 and association accuracy scores

Reduces the number of identity switches

Abstract

Multiple-object tracking (MOT) in agricultural environments presents major challenges due to repetitive patterns, similar object appearances, sudden illumination changes, and frequent occlusions. Contemporary trackers in this domain rely on the motion of objects rather than appearance for association. Nevertheless, they struggle to maintain object identities when targets undergo frequent and strong occlusions. The high similarity of object appearances makes integrating appearance-based association nontrivial for agricultural scenarios. To solve this problem we propose CropTrack, a novel MOT framework based on the combination of appearance and motion information. CropTrack integrates a reranking-enhanced appearance association, a one-to-many association with appearance-based conflict resolution strategy, and an exponential moving average prototype feature bank to improve appearance-based association. Evaluated on publicly available agricultural MOT datasets, CropTrack demonstrates consistent identity preservation, outperforming traditional motion-based tracking methods. Compared to the state of the art, CropTrack achieves significant gains in identification F1 and association accuracy scores with a lower number of identity switches.