Real-Time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification

By Long Chen, Haizhou Ai, Zijie Zhuang, Chong Shang. IEEE International Conference on Multimedia and Expo, 2018

431 citations recorded by the source corpus.

Online multi-object tracking is a fundamental problem in time-critical video analysis applications. A major challenge in the popular tracking-by-detection framework is how to associate unreliable detection results with existing tracks. In this paper, we propose to handle unreliable detection by collecting candidates from outputs of both detection and tracking. The intuition behind generating redundant candidates is that detection and tracks can complement each other in different scenarios. Detection results of high confidence prevent tracking drifts in the long term, and predictions of tracks can handle noisy detection caused by occlusion. In order to apply optimal selection from a considerable amount of candidates in real-time, we present a novel scoring function based on a fully convolutional neural network, that shares most computations on the entire image. Moreover, we adopt a deeply learned appearance representation, which is trained on large-scale person re-identification datasets, to improve the identification ability of our tracker. Extensive experiments show that our tracker achieves real-time and state-of-the-art performance on a widely used people tracking benchmark.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/07f4ba45b771ed123b08261d88acda19406a7987

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

TransTrack: Multiple-Object Tracking with Transformer (2020, background): “Most state-of-the-art multiobject trackers [43, 39, 7, 42, 47, 41, 4] follow the trackingby-detection paradigm.”
Learning a Neural Solver for Multiple Object Tracking (2019, methodology): “As an alternative, for the results in Section 4, we follow a similar detection preprocessing scheme to the one applied by other methods [4, 30, 12].”
Segment as Points for Efficient Online Multi-Object Tracking and Segmentation (2020, neutral): “MOTDT [5]+ MG 47.”
Tracking Objects as Points (2020, background): “Note that refining and rescoring the given bounding boxes is allowed and is commonly used by participants in the challenge [1,19,25].”
Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking (2020, neutral): “7% 7909 89874 532 MOTDT [33] 47.”
StrongSORT: Make DeepSORT Great Again (2022, background): “Seperate trackers [3,4,7,8,15,36,62,69] follow the tracking-by-detection paradigm and localize targets first and then associate them with information on appearance, motion, etc.”
DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion (2021, methodology): “On the other hand, MOTDT [7] uses the tracking result to help detect bounding boxes.”
FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking (2020, methodology): “GradNorm gets the best overall tracking accuracy (highest IDF1 and second highestMOTA), meaning that ensuring different tasks to have similar gradient magnitude is helpful to handle feature conflicts.”
MOTS: Multi-Object Tracking and Segmentation (2019, methodology): “The association head is inspired by the embedding vectors used in person re-identification [17, 5, 31, 55, 62].”
HOTA: A Higher Order Metric for Evaluating Multi-object Tracking (2020, methodology): “We evaluate 37 different trackers [11,76,7,64,51,84,89,33, 16,82,30,47,15,35,42,85,26,29,17,34,46,41,70,25,31,2, 62,63,9,10,3,69,4,22,37,5] on MOT17 [54].”
Tracking Without Bells and Whistles (2019, background): “Compared to the graph-based jCC method, the online MOTDT17 method excels at covering particularly long gaps.”
Deep learning in video multi-object tracking: A survey (2019, methodology): “Above: tracking results for MOTDT [118], online algorithm.”
MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking (2020, neutral): “78 MOTDT17 [Long et al., 2018] 50.”
Spatial-Temporal Relation Networks for Multi-Object Tracking (2019, neutral): “9 MOTDT [10] 47.”