2016
DOI: 10.1007/978-3-319-48881-3_4
|View full text |Cite
|
Sign up to set email alerts
|

Long-Term Time-Sensitive Costs for CRF-Based Tracking by Detection

Abstract: Abstract. We present a Conditional Random Field (CRF) approach to tracking-by-detection in which we model pairwise factors linking pairs of detections and their hidden labels, as well as higher order potentials defined in terms of label costs. Our method considers long-term connectivity between pairs of detections and models cue similarities as well as dissimilarities between them using time-interval sensitive models. In addition to position, color, and visual motion cues, we investigate in this paper the use … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
27
0

Year Published

2017
2017
2023
2023

Publication Types

Select...
6
3
1

Relationship

0
10

Authors

Journals

citations
Cited by 43 publications
(27 citation statements)
references
References 7 publications
0
27
0
Order By: Relevance
“…Simple appearance models are widely used in MTT. Many models are based on raw pixel template representation for simplicity [77,4,74,55,54], while color histogram is the most popular representation for appearance modeling in MTT approaches [9,38,68,35]. Other approaches use covariance matrix representation, pixel comparison representation, SIFT-like features, or pose features [25,83,29,22,50].…”
Section: Appearance Modelmentioning
confidence: 99%
“…Simple appearance models are widely used in MTT. Many models are based on raw pixel template representation for simplicity [77,4,74,55,54], while color histogram is the most popular representation for appearance modeling in MTT approaches [9,38,68,35]. Other approaches use covariance matrix representation, pixel comparison representation, SIFT-like features, or pose features [25,83,29,22,50].…”
Section: Appearance Modelmentioning
confidence: 99%
“…We compare our CRF-RNN method with the top published works on the MOT16 test set, and report the quantitative results in Table 2 . Our method also has significant advantages over LTCRF [20], another CRF-based approach. The main reason for high FP is that our method uses linear interpolation to connect fragments, which is unable to produce more accurate prediction in complex scenes.…”
Section: Comparison With the State Of The Artmentioning
confidence: 99%
“…Bagherzadeh, and Yazdi [172] used the saliency map to extract the appearance features in frequency domain and then applied the regularized least squared classifier to classify pixels belonging to a moving object. Another popular strategy from moving object tracking in moving camera is tracking-by-detection [173,174,175].…”
Section: Extract Target Featuresmentioning
confidence: 99%