Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

FAMNet: Joint Learning of Feature, Affinity and Multi-dimensional Assignment for Online Multiple Object Tracking

About

Data association-based multiple object tracking (MOT) involves multiple separated modules processed or optimized differently, which results in complex method design and requires non-trivial tuning of parameters. In this paper, we present an end-to-end model, named FAMNet, where Feature extraction, Affinity estimation and Multi-dimensional assignment are refined in a single network. All layers in FAMNet are designed differentiable thus can be optimized jointly to learn the discriminative features and higher-order affinity model for robust MOT, which is supervised by the loss directly from the assignment ground truth. We also integrate single object tracking technique and a dedicated target management scheme into the FAMNet-based tracking system to further recover false negatives and inhibit noisy target candidates generated by the external detector. The proposed method is evaluated on a diverse set of benchmarks including MOT2015, MOT2017, KITTI-Car and UA-DETRAC, and achieves promising performance on all of them in comparison with state-of-the-arts.

Peng Chu, Haibin Ling• 2019

Related benchmarks

TaskDatasetResultRank
Multiple Object TrackingMOT17 (test)
MOTA52
921
Multi-Object TrackingMOT17
MOTA52
55
Multi-Object TrackingKITTI (test)--
51
Multi-Object TrackingMOT17 1.0 (test)
MOTA52
48
Multiple Object TrackingMOT 17 (public detections)
MOTA52
15
Multi-Object TrackingKITTI Tracking Car
HOTA52.6
10
Multiple Object TrackingUA-DETRAC v1 (test)
MOTA19.8
8
Multiple Object TrackingUA-DETRAC
MOTA19.8
8
Showing 8 of 8 rows

Other info

Follow for update