2016 13th Conference on Computer and Robot Vision (CRV) 2016
DOI: 10.1109/crv.2016.19
|View full text |Cite
|
Sign up to set email alerts
|

Data-Driven Probabilistic Occlusion Mask to Promote Visual Tracking

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
11
0

Year Published

2017
2017
2018
2018

Publication Types

Select...
3
2

Relationship

2
3

Authors

Journals

citations
Cited by 7 publications
(11 citation statements)
references
References 30 publications
0
11
0
Order By: Relevance
“…The weighted patch descriptor [10] is more flexible for partial occlusion and appearance changes of the object. Similar to SOWP, some methods [41,42] weight the sample with patch likelihoods in particle filters, and [43] used adaptive weighting in patch-based correlation filters to mitigate the effect of occlusion. However, when the object is occluded for a long time, SOWP still has drift, and it is difficult to distinguish target and background when there are some appearance similarities brought by background blur or target occlusion in the bounding box.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…The weighted patch descriptor [10] is more flexible for partial occlusion and appearance changes of the object. Similar to SOWP, some methods [41,42] weight the sample with patch likelihoods in particle filters, and [43] used adaptive weighting in patch-based correlation filters to mitigate the effect of occlusion. However, when the object is occluded for a long time, SOWP still has drift, and it is difficult to distinguish target and background when there are some appearance similarities brought by background blur or target occlusion in the bounding box.…”
Section: Related Workmentioning
confidence: 99%
“…The red number is the best result. We also compared our tracker with the occlusion probability mask-based tracker (OPM) [41]. We ran our method on the same sequences and adopted the same average center location error for comparing with this method, and the results are shown in Table 6.…”
Section: Evaluation On Otb-100mentioning
confidence: 99%
“…To address this, researchers came by different approaches to provide good samples for tracking using context [18,23], saliency maps [25], confidence maps [44], and optical flow [22]. Adaptive weights for the samples based on their appearance similarity to the target [35], occlusion state [30], and spatial distance to previous target location [47] have also been considered, however, selecting an efficient subset for classifier re-training have been ignored, as most of the trackers retrain on all of the data, a randomized subset of it [32], or in special cases re-sample the training data based on their boosting value [28]. A "clean" subset of training samples to re-train the classifier can achieve much higher performance than the full set [36,51], therefore, a principled ordering and selection of the samples reduces the cost of labeling and accelerate the performance with smaller re-training sample size [45].…”
Section: Related Workmentioning
confidence: 99%
“…The most general type of tracking is single-object model-free online tracking, in which the object is annotated in the first frame, and tracked in the subsequent frames with no prior knowledge about the target's appearance, its motions, the background, the configurations of the camera, and other conditions of the scene. Visual tracking is still considered as a challenging problem despite that many efforts have been made to address abrupt appearance changes of the target [1], its sophisticated transformations [2] and deformations [3], background clutter [4], occlusion [5], and motion artifacts [6].…”
Section: Introductionmentioning
confidence: 99%
“…To address these issues, various solutions have been introduced in the literature, yet a comprehensive solution is to be proposed. Adaptive weights for the samples based on their appearance similarity to the target [8], occlusion state [5], [24], and spatial distance to previous target location [25] have been considered, especially in the context of trackingby-detection, boosting [26], [27] have been extensively investigated [18], [28], [29]. On the other hand, mistakes of the labeler manifest themselves as label noise that confuses the classifier.…”
Section: Introductionmentioning
confidence: 99%