Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking

By Jinlong Peng, Changan Wang, Fangbin Wan, Yang Wu, Yabiao Wang, Ying Tai, Chengjie Wang, Jilin Li, Feiyue Huang, Yanwei Fu. European Conference on Computer Vision, 2020

380 citations recorded by the source corpus.

Existing Multiple-Object Tracking (MOT) methods either follow the tracking-by-detection paradigm to conduct object detection, feature extraction and data association separately, or have two of the three subtasks integrated to form a partially end-to-end solution. Going beyond these sub-optimal frameworks, we propose a simple online model named Chained-Tracker (CTracker), which naturally integrates all the three subtasks into an end-to-end solution (the first as far as we know). It chains paired bounding boxes regression results estimated from overlapping nodes, of which each node covers two adjacent frames. The paired regression is made attentive by object-attention (brought by a detection module) and identity-attention (ensured by an ID verification module). The two major novelties: chained structure and paired attentive regression, make CTracker simple, fast and effective, setting new MOTA records on MOT16 and MOT17 challenge datasets (67.6 and 66.6, respectively), without relying on any extra training data. The source code of CTracker can be found at: this http URL.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/bec1169363ac423033cc05e8058b7a621531b088

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

ByteTrack: Multi-Object Tracking by Associating Every Detection Box (2021, methodology): “4 - 45486 149307 2049 CTracker [49] 66.”
Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation (2020, background): “Other works like [8, 4] resorted to using state-of-the-art instance segmentation or tracking pipeline [12, 13] while attempting to design matching strategies to associate the mask over time.”
FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking (2020, background): “Chained-Tracker (Peng et al. 2020) proposes an end-to-end model using adjacent frame pair as input and generating the box pair representing the same target.”
Quasi-Dense Similarity Learning for Multiple Object Tracking (2020, methodology): “3 735 468 27060 177483 4137 CTrackerV1 [35] 66.”
Track to Detect and Segment: An Online Multi-Object Tracker (2021, methodology): “CTracker [29] constructs tracklets by chaining paired boxes in every two frames.”
Joint Object Detection and Multi-Object Tracking with Graph Neural Networks (2021, background): “[26]–[29] proposed to extend an object detector by adding a re-identification (Re-ID) [32] or ID verification branch which extracts features of objects”
TransTrack: Multiple-Object Tracking with Transformer (2020, methodology): “We introduce track rebirth in the inference procedure of TransTrack in order to enhance robustness to occlusions and short-term disappearing [1, 45, 27].”
StrongSORT: Make DeepSORT Great Again (2022, background): “Recently, several joint trackers [30,32,38,57,59,65,68] have been proposed to train detection and some other components jointly, e.”
BoT-SORT: Robust Associations Multi-Pedestrian Tracking (2022, background): “Recently, several joint trackers [46, 51, 59, 26, 53, 32, 24, 44] have been proposed to train detection and some other components jointly, e.g., motion, embedding, and association models.”
Rethinking the Competition Between Detection and ReID in Multiobject Tracking (2020, methodology): “For instance, CTracker [22] uses adjacent frame pairs as input and generates a pair of bounding boxes for the same target by a chaining structure.”