Online Multi-target Tracking with Strong and Weak Detections

Sánchez-Matilla, Ricardo; Poiesi, Fabio; Cavallaro, Andrea

doi:10.1007/978-3-319-48881-3_7

Cited by 189 publications

(99 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ablation study proves that GMPHD-OGM (w/ SIOA) is more efficient to solve the defined problems than the given baseline methods such as GMPHD-HDA and GMPHD-OGM (w/ IOU). GMPHD-OGM achieves the best MOTA scores in MOT15 and MOT17 datasets, respectively, in comparison with the PHD filter based online trackers [16], [18], [22], [38], [41]- [43]. Finally, by the comprehensive evaluation, we conclude the proposed tracker (GMPHD-OGM) against state-of-the-art algorithms including online with DNN even including offline, GMPHD-OGM shows the competitive value in "MOTA versus speed".…”

Section: Discussionmentioning

confidence: 72%

“…The proposed method is still comparative and positioned at meaningful spot for realtime application as shown in Figure 5-(b). In addition to our tracking algorithm (GMPHD-OGM), many PHD filter based online approaches [16], [18], [22], [38], [41]- [43] have been proposed in the past decade. Against them, GMPHD-OGM achieves not only the best MOTA, MOTP, MT, ML, FN, and speed scores on MOT15 but also the second best MOTA, speed, and best MT, FN, and Frag scores in MOT17.…”

Section: B Evaluation Resultsmentioning

confidence: 99%

“…Recently, the closed-form implementations [2], [3] of the probability hypothesis density (PHD) filtering have been employed as an emerging theory for many online MOT methods [16]- [18], [22], [38], [41]- [43]. That is because Vo et al [2], [3] provided not only theoretically optimal approach to the online multi-target Bayes filtering but also approximate the original PHD recursions involving multiple integrals, which alleviate the computational intractability.…”

mentioning

confidence: 99%

“…They make the GMPHD filter be sophisticated and fit to video based MOT. Besides, various tracking methods [22], [38], [41] utilizing the PHD filters have been proposed.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Online Multi-Object Tracking With GMPHD Filter and Occlusion Group Management

Song

Yoon

et al. 2019

IEEE Access

View full text Add to dashboard Cite

In this paper, we propose an efficient online multiobject tracking framework based on the Gaussian mixture probability hypothesis density (GMPHD) filter and occlusion group management scheme where the GMPHD filter utilizes hierarchical data association to reduce the false negatives caused by miss detection. The hierarchical data association consists of two steps: detection-to-track and track-to-track associations, which can recover the lost tracks and their switched IDs. In addition, the proposed framework is equipped with an object grouping management scheme which handles occlusion problems with two main parts. The first part is "track merging" which can merge the false positive tracks caused by false positive detections from occlusions, where the false positive tracks are usually occluded with a measure. The measure is the occlusion ratio between visual objects, sum-of-intersection-over-area (SIOA) we defined instead of intersection-over-union (IOU) metric. The second part is "occlusion group energy minimization (OGEM)" which prevents the occluded true positive tracks from false "track merging". We define each group of the occluded objects as an energy function and find an optimal hypothesis which makes the energy minimal. We evaluate the proposed tracker in benchmark datasets such as MOT15 and MOT17 which are built for multi-person tracking. An ablation study in training dataset shows that not only "track merging" and "OGEM" complement each other but also the proposed tracking method has more robust performance and less sensitive to parameters than baseline methods. Also, SIOA works better than IOU for various sizes of false positives. Experimental results show that the proposed tracker efficiently handles occlusion situations and achieves competitive performance compared to the state-of-theart methods. Especially, our method shows the best multi-object tracking accuracy among the online and real-time executable methods.

show abstract

Section: Discussionmentioning

confidence: 72%

Section: B Evaluation Resultsmentioning

confidence: 99%

mentioning

confidence: 99%

“…They make the GMPHD filter be sophisticated and fit to video based MOT. Besides, various tracking methods [22], [38], [41] utilizing the PHD filters have been proposed.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Online Multi-Object Tracking With GMPHD Filter and Occlusion Group Management

Song

Yoon

et al. 2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Alternatively, a hybrid detector may be built by switching entirely among more available detectors based on the current estimated difficulty of the scene [9]. In the context of online multi-target tracking, [10] proposes to exploit a batch of classifiers and obtain strong and weak detections on the basis of a confidence score. Although these strategies are beneficial for real-time performance, they are not well suited for difficult settings such as high-density crowds, as the individual classifiers exhibit rather modest performance, and the final decision does not necessarily exploit all the available information.…”

Section: B Fusionmentioning

confidence: 99%

Belief Function Definition for Ensemble Methods - Application to Pedestrian Detection in Dense Crowds

Vandoni

Hegarar-Mascle

Aldea

2018

2018 21st International Conference on Information Fusion (FUSION)

View full text Add to dashboard Cite

Transfer learning‐based online multiperson tracking with Gaussian process regression

Zhang

Huang

et al. 2018

Concurrency and Computation

View full text Add to dashboard Cite

Summary Most existing tracking‐by‐detection approaches are affected by abrupt pedestrian pose changes, lighting conditions, scale changes, and real‐time processing, which leads to issues such as detection errors and drifts. To deal with these issues, we present a novel multi‐person tracking framework by introducing a new Gaussian Process Regression based observation model, which learns in a semi‐supervised manner. The background information is taken into consideration to build the discriminative tracker, training samples are re‐weighted appropriately to ease the impact of the potential sample misalignment and noisy during model updating. Unlabeled samples from the current frame provide rich information, which is used for enhancing the tracking inference. Experimental results show that the proposed approach outperforms a number of state‐of‐the‐art methods on some benchmark datasets.

show abstract

Online Multi-target Tracking with Strong and Weak Detections

Cited by 189 publications

References 20 publications

Online Multi-Object Tracking With GMPHD Filter and Occlusion Group Management

Online Multi-Object Tracking With GMPHD Filter and Occlusion Group Management

Belief Function Definition for Ensemble Methods - Application to Pedestrian Detection in Dense Crowds

Transfer learning‐based online multiperson tracking with Gaussian process regression

Contact Info

Product

Resources

About