OneShotDA: Online Multi-Object Tracker With One-Shot-Learning-Based Data Association

Yoon, Kang Sup; Gwak, Jeonghwan; Song, Young-min; Yoon, Young-Gui; Jeon, Moongu

doi:10.1109/access.2020.2975912

Cited by 35 publications

(18 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We restrict our evaluation to only those methods that are published in peer reviewed journals and conferences. We evaluate 37 different trackers (Brasó and Leal-Taixé 2020;Wang et al 2019;Bergmann et al 2019;Sheng et al 2018;Maksai and Fua 2019;Yoon et al 2020;Zhu et al 2018;Keuper et al 2018;Chen et al 2017Chen et al , 2019Xu et al 2019;Henschel et al 2018Henschel et al , 2019Long et al 2018;Kim et al 2015Kim et al , 2018Yoon et al 2018;Fu et al 2018Fu et al , 2019Chu and Ling 2019;Liu et al 2019;Song et al 2019;Karunasekera et al 2019;Babaee et al 2019;Cavallaro 2016, 2019;Bewley et al 2016;Bochinski et al 2017;Baisa 2018;Song and Jeon 2016;Baisa 2019;Eiselein et al 2012;Kutschbach et al 2017; Baisa and Wallace 2019) on MOT17 (Milan et al 2016). This includes all of the trackers for which the relevant bibliographic information was available when this analysis was performed on the 1st April 2020.…”

Section: Evaluating Trackers With Hota On Motchallengementioning

confidence: 99%

“…2018 ) 4 7 ( 3) 7 ( 3) 43.6 51.8 54.7 43.6 44 46.9 73.4 49.3 69.8 SAS_MOT17 (Maksai and Fua 2019 ) 5 31 ( 26) 3 ( 2) 43 44.2 57.2 37.5 49.6 40 72.8 53.2 75.8 YOONKJ17 (Yoon et al. 2020 ) 6 8 ( 2) 10 ( 4) 42.9 51.4 54 43 43.1 46 74.1 48 70.4 DMAN (Zhu et al. 2018 ) 7 21 ( 14) 5 ( 2) 42.7 48.2 55.7 39.9 46 42.4 73.2 49.6 72.7 jCC (Keuper et al.…”

Section: Analysing Previous Evaluation Metricsmentioning

confidence: 99%

See 1 more Smart Citation

HOTA: A Higher Order Metric for Evaluating Multi-object Tracking

Luiten

Ošep²,

Dendorfer³

et al. 2020

Int J Comput Vis

641

234

View full text Add to dashboard Cite

Multi-object tracking (MOT) has been notoriously difficult to evaluate. Previous metrics overemphasize the importance of either detection or association. To address this, we present a novel MOT evaluation metric, higher order tracking accuracy (HOTA), which explicitly balances the effect of performing accurate detection, association and localization into a single unified metric for comparing trackers. HOTA decomposes into a family of sub-metrics which are able to evaluate each of five basic error types separately, which enables clear analysis of tracking performance. We evaluate the effectiveness of HOTA on the MOTChallenge benchmark, and show that it is able to capture important aspects of MOT performance not previously taken into account by established metrics. Furthermore, we show HOTA scores better align with human visual evaluation of tracking performance.

show abstract

Section: Evaluating Trackers With Hota On Motchallengementioning

confidence: 99%

Section: Analysing Previous Evaluation Metricsmentioning

confidence: 99%

HOTA: A Higher Order Metric for Evaluating Multi-object Tracking

Luiten

Ošep²,

Dendorfer³

et al. 2020

Int J Comput Vis

641

234

View full text Add to dashboard Cite

show abstract

“…In the second experiment on the tracking performance, we compared the state-of-the-art methods with the proposed method using the MOT 17 dataset, as shown in Table V. To verify the effectiveness of the proposed tracking method, the same performance was measured using 10 state-of-the-art methods: (1) DMAN [6], (2) DEEP_TAMA [42] using deep temporal appearance matching, (3) STRN [46] applying a spatial-temporal relation network, (4) FAMNet [23] using a multi-object assignment, (5) Tracktor [21], (6) TrctrD17 [33], (7) YoonKJ17 [47] applying one-shot-learning, (8) the proposed SiameseRF without rule distillation, and (9) the proposed SiameseRF with 30% rule distillation. Unlike in Table IV, in Table V, public detection results are listed instead of private detection to evaluate a more accurate tracking performance.…”

Section: Evaluation On Mot17 Challenge Datasetmentioning

confidence: 99%

Online Multiple Object Tracking Using Rule Distillated Siamese Random Forest

Lee

Kim

2020

IEEE Access

View full text Add to dashboard Cite

In a multiple object tracking (MOT) system, an association check between the tracker and detected objects is an important factor in determining the tracking performance. Siamese convolution neural network (CNN) is the most popular data association method in MOT owing to its good matching performance and network sharing support. However, it is unsuitable for real-time online tracking in low-end systems because numerous parameters and operations are still required. In this paper, instead of a CNN, we propose using a SiameseRF algorithm which combines Siamese structure and random forest (RF), enabling highspeed learning and classification. SiameseRF has a shared-rule based Siamese structure rather than shared weight, which improves the matching performance and solves existing slow CNN-based tracking issues. During the learning process, the shared RFs consisting of tree rules are learned in the directions of increasing similarity to the positive pair {anchor, positive} and increasing difference between the negative pair {anchor, negative}. However, because many rules that make up SiameseRF remain a burden for online processing, this study proposes an additional rule distillation algorithm to effectively remove redundant and unimportant rules causing an overfitting with SiameseRF. This reduction in the number of rules reduces the processing time and number of parameters in the rule distilled SiameseRF. In experiments conducted on MOT benchmark datasets, our proposed 30% rule distilled SiameseRF achieved up to a 1.12-times faster speed and a 1.13-times higher compression rate than basic SiameseRF while maintaining a similar or somewhat better tracking performance than other state-of-the-art CNN-based MOT algorithms.

show abstract

“…Chen et al [38] utilized R-FCN detector scores [48] to select reliable candidate bounding boxes. Yoon et al [18] introduced an one-shot learning method for data association and integrated it into the MHT framework.…”

Section: Related Work a Multiple Object Trackingmentioning

confidence: 99%

Online Multiple Object Tracking Based on Open-Set Few-Shot Learning

Kim

Koh

2020

IEEE Access

View full text Add to dashboard Cite

How to make an online tracking model effectively adapt to newly appearing objects and object disappearance as well as appearance variations of target objects from few examples is an essential issue in multiple object tracking (MOT). Learning target appearances from few examples is a few-shot classification problem, while identifications of newly appearing objects and object disappearance has the aspect of open-set classification. In this work, we regard online MOT as open-set few-show classification to address both learning from few examples (few-shot classification) and unknown classes such as new objects (open-set classification). Specifically, we develop an embedding neural network, called VOFNet, consisting of convolutional and recurrent parts, to perform open-set few-shot classification. The convolutional part constructs a feature from an example of a target object and the recurrent part determines a representative feature of a target object from few examples. Then VOFNet is trained to provide effective features for openset few-shot classification. Finally, we develop an online multiple object tracker based on the combination of VOFNet and the bipartite matching. The proposed tracker achieves 49.2 multiple object tracking accuracy (MOTA) with 28.9 frames per second on MOT17 dataset, which shows a significantly better trade-off between the accuracy and the speed than the existing algorithms. For example, the proposed algorithm yields about 3.17 times faster speed with 0.99 times lower accuracy than recent existing MOT algorithm [1]. INDEX TERMS Multiple object tracking, online tracking, open-set classification, few-shot classification.

show abstract

OneShotDA: Online Multi-Object Tracker With One-Shot-Learning-Based Data Association

Cited by 35 publications

References 35 publications

HOTA: A Higher Order Metric for Evaluating Multi-object Tracking

HOTA: A Higher Order Metric for Evaluating Multi-object Tracking

Online Multiple Object Tracking Using Rule Distillated Siamese Random Forest

Online Multiple Object Tracking Based on Open-Set Few-Shot Learning

Contact Info

Product

Resources

About