Multi-Object Tracking Through Simultaneous Long Occlusions and Split-Merge Conditions

Perera, A. G. Amitha; Srinivas, Chintakindi; Hoogs, Anthony; Brooksby, G.; Hu, Wensheng

doi:10.1109/cvpr.2006.195

Cited by 217 publications

(176 citation statements)

References 6 publications

Supporting

Mentioning

174

Contrasting

Order By: Relevance

“…Our method for evaluation is similar to [2] and measures performance of both detection and tracking. We compute the following distance measure between generated tracks and ground truth tracks:…”

Section: Resultsmentioning

confidence: 99%

“…Data obtained from such a sensor is quite different from the standard aerial and ground surveillance datasets, such as VIVID and NGSIM, which have been used in [1,2], as well as aerial surveillance scenario [3][4][5]. First, objects in WAS data are much smaller, with vehicle sizes ranging from 4 to 70 pixels in grayscale imagery, compared to over 1500 pixels in color imagery in the VIVID dataset.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Detection and Tracking of Large Number of Targets in Wide Area Surveillance

Reilly

Idrees

Shah

2010

Lecture Notes in Computer Science

146

147

View full text Add to dashboard Cite

Abstract. In this paper, we tackle the problem of object detection and tracking in a new and challenging domain of wide area surveillance. This problem poses several challenges: large camera motion, strong parallax, large number of moving objects, small number of pixels on target, single channel data and low framerate of video. We propose a method that overcomes these challenges and evaluate it on CLIF dataset. We use median background modeling which requires few frames to obtain a workable model. We remove false detections due to parallax and registration errors using gradient information of the background image. In order to keep complexity of the tracking problem manageable, we divide the scene into grid cells, solve the tracking problem optimally within each cell using bipartite graph matching and then link tracks across cells. Besides tractability, grid cells allow us to define a set of local scene constraints such as road orientation and object context. We use these constraints as part of cost function to solve the tracking problem which allows us to track fast-moving objects in low framerate videos. In addition to that, we manually generated groundtruth for four sequences and performed quantitative evaluation of the proposed algorithm.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Detection and Tracking of Large Number of Targets in Wide Area Surveillance

Reilly

Idrees

Shah

2010

Lecture Notes in Computer Science

146

147

View full text Add to dashboard Cite

show abstract

“…A popular approach to multi-object tracking is to run a low-level tracker to obtain "tracklets", and then stitch together tracklets using various graph-based formalisms or greedy heuristics [15,22,16,19,2]. Such graph-based algorithms include flow-networks [25], linear-programming formulations [14], and matching algorithms [15].…”

Section: Related Workmentioning

confidence: 99%

“…Inference would "explain away" evidence and enforce exclusion. In practice, the typical solution is to apply non-max suppression (NMS) as a pre-process to prune the set of candidate locations V prior to multi-object tracking [19,6,14,25].…”

Section: Track Interdependencementioning

confidence: 99%

Globally-optimal greedy algorithms for tracking a variable number of objects

2011

View full text Add to dashboard Cite

We analyze the computational problem of multi-object tracking in video sequences. We formulate the problem using a cost function that requires estimating the number of tracks, as well as their birth and death states. We show that the global solution can be obtained with a greedy algorithm that sequentially instantiates tracks using shortest path computations on a flow network. Greedy algorithms allow one to embed pre-processing steps, such as nonmax suppression, within the tracking algorithm. Furthermore, we give a near-optimal algorithm based on dynamic programming which runs in time linear in the number of objects and linear in the sequence length. Our algorithms are fast, simple, and scalable, allowing us to process dense input data. This results in state-of-the-art performance.

show abstract

“…They rely on Conditional Random Fields [17,27], belief Propagation [29,9], Dynamic or Linear Programming [3,10]. Among the latter, some operate on graphs whose nodes can either be all the spatial locations of potential people presence [26,11,5,1], only those where a detector has fired [25,15], or short temporal sequences of consecutive detections that are very likely to correspond to the same person [21,30,23,4].…”

Section: Related Workmentioning

confidence: 99%

Tracking Interacting Objects Optimally Using Integer Programming

Wang

Türetken

Fleuret

et al. 2014

Computer Vision – ECCV 2014

View full text Add to dashboard Cite

Abstract. In this paper, we show that tracking different kinds of interacting objects can be formulated as a network-flow Mixed Integer Program. This is made possible by tracking all objects simultaneously and expressing the fact that one object can appear or disappear at locations where another is in terms of linear flow constraints. We demonstrate the power of our approach on scenes involving cars and pedestrians, bags being carried and dropped by people, and balls being passed from one player to the next in a basketball game. In particular, we show that by estimating jointly and globally the trajectories of different types of objects, the presence of the ones which were not initially detected based solely on image evidence can be inferred from the detections of the others.

show abstract

Multi-Object Tracking Through Simultaneous Long Occlusions and Split-Merge Conditions

Cited by 217 publications

References 6 publications

Detection and Tracking of Large Number of Targets in Wide Area Surveillance

Detection and Tracking of Large Number of Targets in Wide Area Surveillance

Globally-optimal greedy algorithms for tracking a variable number of objects

Tracking Interacting Objects Optimally Using Integer Programming

Contact Info

Product

Resources

About