An online learned CRF model for multi-target tracking

Yang, Bo; Nevatia, Ram

doi:10.1109/cvpr.2012.6247907

Cited by 210 publications

(270 citation statements)

References 12 publications

Supporting

Mentioning

269

Contrasting

Order By: Relevance

“…Methods that use stronger and more comprehensive evidence have demonstrated superior performance. These methods consider evidence from all observation pairs [13], observation triplets [14] or higher order relationships [15][16][17][18]. The better performance however comes at a cost of increased computational complexity due to the problem's combinatorial nature.…”

Section: Relationship To Prior Workmentioning

confidence: 99%

Tracking Multiple People Online and in Real Time

Ristani

Tomasi

2015

Computer Vision -- ACCV 2014

View full text Add to dashboard Cite

Abstract. We cast the problem of tracking several people as a graph partitioning problem that takes the form of an NP-hard binary integer program. We propose a tractable, approximate, online solution through the combination of a multi-stage cascade and a sliding temporal window. Our experiments demonstrate significant accuracy improvement over the state of the art and real-time post-detection performance.

show abstract

Section: Relationship To Prior Workmentioning

confidence: 99%

Tracking Multiple People Online and in Real Time

Ristani

Tomasi

2015

Computer Vision -- ACCV 2014

View full text Add to dashboard Cite

show abstract

“…Approaches [2,4,8,19] considering both the past and the future information typically require low-level observations such as foreground, tracklet, or trajectory, etc. These types of low level observations can be obtained by background modelling [35] (to acquire foreground), or by associating confident responses of a human detector, head detector or part-based detector into tracklets [7,12,17,25,33,43,44,45] (this is the most popular approach since significant progress has been made in the detection field [13,16]), or by estimating trajectories based on the KLT tracker [36] or Kalman Filter [12]. Then, these types of low level observations are associated by optimisation methods, such as Markov Chain Monte Carlo (MCMC) [35], Dynamic Programming, Hungarian algorithm [33,43], greedy bipartite algorithm [34], network flow [41] and K-Shortest Paths (KSP) algorithm [5].…”

Section: Related Workmentioning

confidence: 99%

Generic Object Crowd Tracking by Multi-Task Learning

Luo

Kim

2013

Procedings of the British Machine Vision Conference 2013

View full text Add to dashboard Cite

We address Multiple Object Tracking (MOT) in crowds, where the type of target objects is generic and not limited to pedestrians as in most previous work. Following the popular tracking-by-detection strategy, we decompose this problem into two main tasks, detection and tracking, and formulate them under the Multiple Task Learning (MTL) framework. A binary detector is learnt to detect objects in images, whilst multiple trackers are learnt on top of the detector by MTL to trace detected objects in subsequent frames. The detector is utilised to anchor the trackers, helping them not drift away from targets. The trackers are jointly learnt by sharing common features. To further improve the performance, we use a smoothness term which considers all labelled and unlabelled data globally. Experiments on challenging new generic object sequences as well as a publicly available sequence show that the proposed method significantly outperforms the state-of-the-art methods.

show abstract

“…Our approach falls in the category of tracking by detection methods [4,5,7,33,44], where category-level detectors are utilized to track the target of interest. However, in contrast to these methods, our focus is on tracking continuous 3D pose and 3D aspect parts.…”

Section: Related Workmentioning

confidence: 99%

Monocular Multiview Object Tracking with 3D Aspect Parts

Xiang

Song

Mottaghi

et al. 2014

Computer Vision – ECCV 2014

View full text Add to dashboard Cite

Abstract. In this work, we focus on the problem of tracking objects under significant viewpoint variations, which poses a big challenge to traditional object tracking methods. We propose a novel method to track an object and estimate its continuous pose and part locations under severe viewpoint change. In order to handle the change in topological appearance introduced by viewpoint transformations, we represent objects with 3D aspect parts and model the relationship between viewpoint and 3D aspect parts in a part-based particle filtering framework. Moreover, we show that instance-level online-learned part appearance can be incorporated into our model, which makes it more robust in difficult scenarios with occlusions. Experiments are conducted on a new dataset of challenging YouTube videos and a subset of the KITTI dataset [14] that include significant viewpoint variations, as well as a standard sequence for car tracking. We demonstrate that our method is able to track the 3D aspect parts and the viewpoint of objects accurately despite significant changes in viewpoint.

show abstract

An online learned CRF model for multi-target tracking

Cited by 210 publications

References 12 publications

Tracking Multiple People Online and in Real Time

Tracking Multiple People Online and in Real Time

Generic Object Crowd Tracking by Multi-Task Learning

Monocular Multiview Object Tracking with 3D Aspect Parts

Contact Info

Product

Resources

About