PETS2009: Dataset and challenge

Ferryman, James; Shahrokni, Ali

doi:10.1109/pets-winter.2009.5399556

Cited by 419 publications

(223 citation statements)

References 0 publications

Supporting

Mentioning

217

Contrasting

Unclassified

Order By: Relevance

“…1. For our study, we use the first half (frames 1-218) of the challenging PETS S2.L2 dataset [1] as our mining sequence, and we employ a recent multi-target tracker based on energy minimization [2]. The ouput of the method is a joint detector that is tailored to detect occlusion patterns that are most relevant for multi-target tracking.…”

Section: Inputmentioning

confidence: 99%

See 1 more Smart Citation

Learning People Detectors for Tracking in Crowded Scenes

Tang

Andriluka

Milan

et al. 2013

2013 IEEE International Conference on Computer Vision

View full text Add to dashboard Cite

People tracking in crowded real-world scenes is challenging due to frequent and long-term occlusions. Recent tracking methods obtain the image evidence from object (people) detectors, but typically use off-the-shelf detectors and treat them as black box components. In this paper we argue that for best performance one should explicitly train people detectors on failure cases of the overall tracker instead. To that end, we first propose a novel joint people detector that combines a state-of-the-art single person detector with a detector for pairs of people, which explicitly exploits common patterns of person-person occlusions across multiple viewpoints that are a common failure case for tracking in crowded scenes. To explicitly address remaining failure cases of the tracker we explore two methods. First, we analyze typical failure cases of trackers and train a detector explicitly on those failure cases. And second, we train the detector with the people tracker in the loop, focusing on the most common tracker failures. We show that our joint multi-person detector significantly improves both detection accuracy as well as tracker performance, improving the state-of-the-art on standard benchmarks

show abstract

Section: Inputmentioning

confidence: 99%

“…We evaluate the proposed joint person detector and its application to tracking on three challenging sequences: PETS S2.L2, S1.L2 [1], and ParkingLot [3]. By analyzing and mining occlusion patterns, we obtain very competitive detection results both in terms of recall and precision, as shown in Fig.…”

Section: Experiments and Conclusionmentioning

confidence: 99%

Learning People Detectors for Tracking in Crowded Scenes

Tang

Andriluka

Milan

et al. 2013

2013 IEEE International Conference on Computer Vision

View full text Add to dashboard Cite

show abstract

“…We demonstrate our approach on eight different sequences. The first set consists of six publicly available videos including the PETS 2009 benchmark [34] 1 and TUD Stadtmitte [35]. All videos show pedestrians in a single view but they exhibit a large variation in person count, camera viewpoint and motion patterns.…”

Section: Methodsmentioning

confidence: 99%

Improving Global Multi-target Tracking with Local Updates

Milan

Gade

Dick

et al. 2015

Computer Vision - ECCV 2014 Workshops

View full text Add to dashboard Cite

Abstract. We propose a scheme to explicitly detect and resolve ambiguous situations in multiple target tracking. During periods of uncertainty, our method applies multiple local single target trackers to hypothesise short term tracks. These tracks are combined with the tracks obtained by a global multi-target tracker, if they result in a reduction in the global cost function. Since tracking failures typically arise when targets become occluded, we propose a local data association scheme to maintain the target identities in these situations. We demonstrate a reduction of up to 50% in the global cost function, which in turn leads to superior performance on several challenging benchmark sequences. Additionally, we show tracking results in sports videos where poor video quality and frequent and severe occlusions between multiple players pose difficulties for state-of-the-art trackers.

show abstract

“…The challenging factors of these sequences are listed in Table 1. car [19] large illumination change, distraction from other objects jumping [13] image blur, fast motion face [1] long-duration occlusion singer [14] large illumination variation, large scale change PETS2009 [8] out-of-plane pose change, heavy occlusion Avatar1 large scale change, low contrast Construct an initial over-complete dictionary D 1 , and learn a linear classifier with parameter w 1 .…”

Section: Methodsmentioning

confidence: 99%

Online discriminative object tracking with local sparse representation

Wang

Chen

Wang

et al. 2012

2012 IEEE Workshop on the Applications of Computer Vision (WACV)

110

120

View full text Add to dashboard Cite

We propose an online algorithm based on local sparse representation for robust object tracking. Local image patches of a target object are represented by their sparse codes with an over-complete dictionary constructed online, and a classifier is learned to discriminate the target from the background. To alleviate the visual drift problem often encountered in object tracking, a two-stage algorithm is proposed to exploit both the ground truth information of the first frame and observations obtained online. Different from recent discriminative tracking methods that use a pool of features or a set of boosted classifiers, the proposed algorithm learns sparse codes and a linear classifier directly from raw image patches. In contrast to recent sparse representation based tracking methods which encode holistic object appearance within a generative framework, the proposed algorithm employs a discrimination formulation which facilitates the tracking task in complex environments. Experiments on challenging sequences with evaluation of the state-of-the-art methods show effectiveness of the proposed algorithm.

show abstract

PETS2009: Dataset and challenge

Cited by 419 publications

References 0 publications

Learning People Detectors for Tracking in Crowded Scenes

Learning People Detectors for Tracking in Crowded Scenes

Improving Global Multi-target Tracking with Local Updates

Online discriminative object tracking with local sparse representation

Contact Info

Product

Resources

About