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

Le, Nam; Heili, Alexander; Odobez, Jean-Marc

doi:10.1007/978-3-319-48881-3_4

Cited by 43 publications

(27 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

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%

Tracking the Untrackable: Learning to Track Multiple Cues with Long-Term Dependencies

Sadeghian

Alahi

Savarese

2017

2017 IEEE International Conference on Computer Vision (ICCV)

509

406

View full text Add to dashboard Cite

The majority of existing solutions to the Multi-Target Tracking (MTT) problem do not combine cues in a coherent end-to-end fashion over a long period of time. However, we present an online method that encodes long-term temporal dependencies across multiple cues. One key challenge of tracking methods is to accurately track occluded targets or those which share similar appearance properties with surrounding objects. To address this challenge, we present a structure of Recurrent Neural Networks (RNN) that jointly reasons on multiple cues over a temporal window. We are able to correct many data association errors and recover observations from an occluded state. We demonstrate the robustness of our data-driven approach by tracking multiple targets using their appearance, motion, and even interactions. Our method outperforms previous works on multiple publicly available datasets including the challenging MOT benchmark.

show abstract

Section: Appearance Modelmentioning

confidence: 99%

Tracking the Untrackable: Learning to Track Multiple Cues with Long-Term Dependencies

Sadeghian

Alahi

Savarese

2017

2017 IEEE International Conference on Computer Vision (ICCV)

509

406

View full text Add to dashboard Cite

show abstract

“…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%

End-to-End Learning Deep CRF Models for Multi-Object Tracking Deep CRF Models

Xiang

et al. 2021

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Existing deep multi-object tracking (MOT) approaches first learn a deep representation to describe target objects and then associate detection results by optimizing a linear assignment problem. Despite demonstrated successes, it is challenging to discriminate target objects under mutual occlusion or to reduce identity switches in crowded scenes. In this paper, we propose learning deep conditional random field (CRF) networks, aiming to model the assignment costs as unary potentials and the long-term dependencies among detection results as pairwise potentials. Specifically, we use a bidirectional long short-term memory (LSTM) network to encode the long-term dependencies. We pose the CRF inference as a recurrent neural network learning process using the standard gradient descent algorithm, where unary and pairwise potentials are jointly optimized in an end-to-end manner. Extensive experimental results on the challenging MOT datasets including MOT-2015 and MOT-2016, demonstrate that our approach achieves the state of the art performances in comparison with published works on both benchmarks.

show abstract

“…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%

New trends on moving object detection in video images captured by a moving camera: A survey

Yazdi

Bouwmans

2018

Computer Science Review

209

View full text Add to dashboard Cite

This paper presents a survey on the latest methods of moving object detection in video sequences captured by a moving camera. Although many researches and excellent works have reviewed the methods of object detection and background subtraction for a fixed camera, there is no survey which presents a complete review of the existing different methods in the case of moving camera. Most methods in this field can be classified into four categories: modelling based background subtraction, trajectory classification, low rank and sparse matrix decomposition, and object tracking. We discuss in details each category and present the main methods which proposed improvements in the general concept of the techniques. We also present challenges and main concerns in this field as well as performance metrics and some benchmark databases available to evaluate the performance of different moving object detection algorithms.

show abstract

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

Cited by 43 publications

References 7 publications

Tracking the Untrackable: Learning to Track Multiple Cues with Long-Term Dependencies

Tracking the Untrackable: Learning to Track Multiple Cues with Long-Term Dependencies

End-to-End Learning Deep CRF Models for Multi-Object Tracking Deep CRF Models

New trends on moving object detection in video images captured by a moving camera: A survey

Contact Info

Product

Resources

About