Long-Term Tracking With Deep Tracklet Association

Zhang, Yang; Sheng, Hao; Wu, Yubin; Wang, Shuai; Lyu, Weifeng; Ke, Wei; Zhang, Xiong

doi:10.1109/tip.2020.2993073

Cited by 97 publications

(56 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the spirit of combining optimization-based methods with learning, Zhang et al (2020) revisits CRF-based tracking models and learns unary and pairwise potential functions in an end-to-end manner. On MOT16, this method attains MOTA of 50.31%.…”

Section: Learning To Combine Association Cuesmentioning

confidence: 99%

MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking

Dendorfer¹,

Ošep²,

et al. 2020

View full text Add to dashboard Cite

Standardized benchmarks have been crucial in pushing the performance of computer vision algorithms, especially since the advent of deep learning. Although leaderboards should not be over-claimed, they often provide the most objective measure of performance and are therefore important guides for research. We present MOTChallenge, a benchmark for single-camera Multiple Object Tracking (MOT) launched in late 2014, to collect existing and new data and create a framework for the standardized evaluation of multiple object tracking methods. The benchmark is focused on multiple people tracking, since pedestrians are by far the most studied object in the tracking community, with applications ranging from robot navigation to self-driving cars. This paper collects the first three releases of the benchmark: (i) MOT15, along with numerous state-of-the-art results that were submitted in the last years, (ii) MOT16, which contains new challenging videos, and (iii) MOT17, that extends MOT16 sequences with more precise labels and evaluates tracking performance on three different object detectors. The second and third release not only offers a significant increase in the number of labeled boxes, but also provide labels for multiple object classes beside pedestrians, as well as the level of visibility for every single object of interest. We finally provide a categorization of state-of-the-art trackers and a broad error analysis. This will help newcomers understand the related work and research trends in the MOT community, and hopefully shed some light into potential future research directions.

show abstract

Section: Learning To Combine Association Cuesmentioning

confidence: 99%

MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking

Dendorfer¹,

Ošep²,

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The algorithm achieves the new state-of-the-art performances compared with other online models. In [21], the author focused on solving the problem of tracking trajectory integrity and introduced an iterative clustering method that generates more tracklets while maintaining high confidence. In terms of motion and appearance, two evaluation networks of motion evaluation network and appearance evaluation network were constructed to learn long-term features of tracklets for association.…”

Section: Related Workmentioning

confidence: 99%

Real-Time Multiobject Tracking Based on Multiway Concurrency

Gong

et al. 2021

Sensors

View full text Add to dashboard Cite

This paper explored a pragmatic approach to research the real-time performance of a multiway concurrent multiobject tracking (MOT) system. At present, most research has focused on the tracking of single-image sequences, but in practical applications, multiway video streams need to be processed in parallel by MOT systems. There have been few studies on the real-time performance of multiway concurrent MOT systems. In this paper, we proposed a new MOT framework to solve multiway concurrency scenario based on a tracking-by-detection (TBD) model. The new framework mainly focuses on concurrency and real-time based on limited computing and storage resources, while considering the algorithm performance. For the former, three aspects were studied: (1) Expanded width and depth of tracking-by-detection model. In terms of width, the MOT system can support the process of multiway video sequence at the same time; in terms of depth, image collectors and bounding box collectors were introduced to support batch processing. (2) Considering the real-time performance and multiway concurrency ability, we proposed one kind of real-time MOT algorithm based on directly driven detection. (3) Optimization of system level—we also utilized the inference optimization features of NVIDIA TensorRT to accelerate the deep neural network (DNN) in the tracking algorithm. To trade off the performance of the algorithm, a negative sample (false detection sample) filter was designed to ensure tracking accuracy. Meanwhile, the factors that affect the system real-time performance and concurrency were studied. The experiment results showed that our method has a good performance in processing multiple concurrent real-time video streams.

show abstract

“…While this alleviate the requirement for good quality detections, most of the works regress in the image plane. The projection from 3D world to the image plane makes it hard to make this prediction, therefore these methods need to learn non-linear motion models [2,4,45]. Compared to these methods, PHALP predicts short-term location in 3D coordinates, by simple linear regression.…”

Section: Related Workmentioning

confidence: 99%

Tracking People by Predicting 3D Appearance, Location & Pose

Rajasegaran¹,

Pavlakos²,

Kanazawa³

et al. 2021

Preprint

View full text Add to dashboard Cite

In this paper, we present an approach for tracking people in monocular videos, by predicting their future 3D representations. To achieve this, we first lift people to 3D from a single frame in a robust way. This lifting includes information about the 3D pose of the person, his or her location in the 3D space, and the 3D appearance. As we track a person, we collect 3D observations over time in a tracklet representation. Given the 3D nature of our observations, we build temporal models for each one of the previous attributes. We use these models to predict the future state of the tracklet, including 3D location, 3D appearance, and 3D pose. For a future frame, we compute the similarity between the predicted state of a tracklet and the single frame observations in a probabilistic manner. Association is solved with simple Hungarian matching, and the matches are used to update the respective tracklets. We evaluate our approach on various benchmarks and report state-of-the-art results.

show abstract

Long-Term Tracking With Deep Tracklet Association

Cited by 97 publications

References 55 publications

MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking

MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking

Real-Time Multiobject Tracking Based on Multiway Concurrency

Tracking People by Predicting 3D Appearance, Location & Pose

Contact Info

Product

Resources

About