Sequential sensor fusion combining probability hypothesis density and kernelized correlation filters for multi-object tracking in video data

Kutschbach, Tino; Bochinski, Erik; Eiselein, Volker; Sikora, Thomas

doi:10.1109/avss.2017.8078517

Cited by 58 publications

(29 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach is an intuitive implementation of the GMPHD filter to handle tracking problems, but cannot correct the false associations already made in the detectionto-track association. T. Kutschbach et al [42] added the kernelized correlation filters (KCF) [53] for online appearance update to overcome occlusion with the naive GMPHD filtering process. They showed a robust online appearance learning to re-find the IDs of the lost tracks.…”

Section: Related Workmentioning

confidence: 99%

“…On the other hand, since the online approach cannot apply the global optimization models, intensive motion analysis and appearance feature learning have been popularly utilized with a hierarchical data association framework and the online Bayesian model [14], [15], [18], [21], [23], [25], [37], [42]. Yoon et al [23] proposed a relative motion analysis between all objects in a frame, and then improved the work [23] by adding the cost optimization function using context constraints in [21].…”

mentioning

confidence: 99%

“…Song et al [16] extended the GMPHD filter based tracking with the two-stage hierarchical data association strategy and use simple motion estimation and appearance matching to recover lost tracks. T. Kutschbach et al [42] joined the GMPHD filter with the kernelized correlation filters (KCF) [53] for online appearance update to overcome occlusion. Z. Fu et al [18] adopted an adaptive gating technique and an online group-structured dictionary (appearance) learning strategy into the GMPHD filter.…”

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

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: Related Workmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

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

“…Fusion based tracking is typically divided in three main categories: detection-level fusion [8], [19], feature-level fusion, and decision-level fusion [6]. Based on the processing level, sequential [14], [20], parallel [21]- [23] and hybrid data fusion [24] approaches are possible. The Generalized Covariance Intersection (GCI) [25] rule was proposed by Mahler [25] for fusion of multi-object functions.…”

Section: Introductionmentioning

confidence: 99%

“…In [35], authors proposed to integrate correlation filters (CFs) and a confidence-based relative motion network to perform a two-step data association to track multiple objects, where CFs are employed as a verifying step to confirm the target estimates. Furthermore, a recent RFS based tracking approach [20] was proposed to perform the KCF as an extended step after the PHD update, where the KCF is mainly used to perform the refinement of target prediction oriented by the label tree technique [36]. However, the above approaches can easily be sensitive to false positives, when CFs are performed with unreliable references or labels [16].…”

Section: Introductionmentioning

confidence: 99%

Multi-Level Cooperative Fusion of GM-PHD Filters for Online Multiple Human Tracking

Angelini

Chambers

et al. 2019

IEEE Trans. Multimedia

View full text Add to dashboard Cite

In this paper, we propose a multi-level cooperative fusion approach to address the online multiple human tracking problem in a Gaussian Mixture Probability Hypothesis Density (GM-PHD) filter framework. The proposed fusion approach consists essentially of three steps. Firstly, we integrate two human detectors with different characteristics (full-body and bodyparts), and investigate their complementary benefits for tracking multiple targets. For each detector domain, we then propose a novel Discriminative Correlation Matching (DCM) model, and fuse it with spatio-temporal information to address ambiguous identity association in the GM-PHD filter. Finally, we develop a robust fusion center with virtual and real zones to make a global decision based on preliminary candidate targets generated by each detector. This center also mitigates the sensitivity of missed detections in the Generalized Covariance Intersection (GCI) fusion process, thereby improving the fusion performance and tracking consistency. Experiments on the MOTChallenge Benchmark demonstrate the proposed method achieves improved performance over other state-of-the-art RFS based tracking methods.

show abstract

Online Multi-Object Tracking with Dual Matching Attention Networks

Zhu

Yang

Liu

et al. 2018

Lecture Notes in Computer Science

336

234

View full text Add to dashboard Cite

In this paper, we propose an online Multi-Object Tracking (MOT) approach which integrates the merits of single object tracking and data association methods in a unified framework to handle noisy detections and frequent interactions between targets. Specifically, for applying single object tracking in MOT, we introduce a cost-sensitive tracking loss based on the state-of-the-art visual tracker, which encourages the model to focus on hard negative distractors during online learning. For data association, we propose Dual Matching Attention Networks (DMAN) with both spatial and temporal attention mechanisms. The spatial attention module generates dual attention maps which enable the network to focus on the matching patterns of the input image pair, while the temporal attention module adaptively allocates different levels of attention to different samples in the tracklet to suppress noisy observations. Experimental results on the MOT benchmark datasets show that the proposed algorithm performs favorably against both online and offline trackers in terms of identity-preserving metrics.

show abstract

Sequential sensor fusion combining probability hypothesis density and kernelized correlation filters for multi-object tracking in video data

Cited by 58 publications

References 8 publications

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

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

Multi-Level Cooperative Fusion of GM-PHD Filters for Online Multiple Human Tracking

Online Multi-Object Tracking with Dual Matching Attention Networks

Contact Info

Product

Resources

About