People Tracking in Camera Networks: Three Open Questions

Thakoor, Ninad; An, Le; Bhanu, Bir; Sunderrajan, Santhoshkumar; Manjunath, B.S.

doi:10.1109/mc.2015.83

Cited by 7 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For simplicity, the following explanation is given for two cameras. The object feet positions are obtained using parts based HOG model [14][15]. Let us denote detections as p i z and q j z in the perspective of camera i and j , where p and q are real labels in the two perspectives before implementing object association p j z and q j z are considered as a set of corresponding points in the event that they can project as a similar point on the world ground plane.…”

Section: Problem Statementmentioning

confidence: 99%

Multi Target Tracking Access with Data Association in Distributed Camera Networks

2019

IJRTE

View full text Add to dashboard Cite

Data Association in Distributed Camera Network is a new method to analyse the large volume of video information in camera networking. It is an important step in multi camera multi target tracking. Distributed processing is a new paradigm to analyse the videos in camera network and each camera acts on its own and all cameras cooperatively work together to achieve a common goal, In this paper, we have addresses the problem of Distributed Data Association(DDA) to obtain the feet position of the object. These positions are shared with its immediate neighbours and find local matches using homography. By propagating these local matches across the network in order to obtain the global associations. In this proposed method DDA is less complex and improves the high accuracy compared to the centralized methods (STSPIE, EMTIC, JPDAEKCF, CSPIF, and CEIF).

show abstract

Section: Problem Statementmentioning

confidence: 99%

Multi Target Tracking Access with Data Association in Distributed Camera Networks

2019

IJRTE

View full text Add to dashboard Cite

show abstract

“…Given the set of matching nodes, , and be the number of matching nodes, the system assigns uniform matching scores (positive labels) for those nodes in the query set, i.e. if otherwise (10) where is the preference/label vector. For similar appearance and spatial-temporal searching [see Fig.…”

Section: A Hypergraph-based User Query Rankingmentioning

confidence: 99%

“…17 shows the overall mean average recall (mean recall for 25 different queries averaged over 10 different scopes i.e. [5], [10], [15], [20], [25], [30], [35], [40], [45]) for different values of . Similar to [43], performs the best in the university dataset.…”

Section: G Effect Of Parametersmentioning

confidence: 99%

“…1(c)] events using person-focussed non-redundant snapshots across the network. The above-mentioned tasks arise in several fields such as e-commerce (fashion) [6], [5], surveillance [9], [10]. Towards this extent, we propose a distributed framework that enables users to re-identify person across multiple camera views, and provides a summary of persons's activity.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Context-Aware Hypergraph Modeling for Re-identification and Summarization

Sunderrajan

Manjunath

2016

IEEE Trans. Multimedia

Self Cite

View full text Add to dashboard Cite

Abstract-Tracking and re-identification in wide-area camera networks is a challenging problem due to non-overlapping visual fields, varying imaging conditions, and appearance changes. We consider the problem of person re-identification and tracking, and propose a novel clothing context-aware color extraction method that is robust to such changes. Annotated samples are used to learn color drift patterns in a non-parametric manner using the random forest distance (RFD) function. The color drift patterns are automatically transferred to associate objects across different views using a unified graph matching framework. A hypergraph representation is used to link related objects for search and re-identification. A diverse hypergraph ranking technique is proposed for person-focused network summarization. The proposed algorithm is validated on a wide-area camera network consisting of ten cameras on bike paths. Also, the proposed algorithm is compared with the state of the art person re-identification algorithms on the VIPeR dataset [1].

show abstract

“…While video based platforms offer the opportunity to extract unique, continuous, and rich information from the home environment, they also present a number of disadvantages, such as privacy issues [9], user acceptance and system cost and scalability. Finally, the accepted challenges of computer vision, such as arbitrary body poses, changing illumination, occlusion, and low cost/low resolution are still unsolved problems [23] even if depth data is combined with colour [6]. Furthermore, these issues are greatly amplified for AAL monitoring applications that operate in unconstrained environments and in long term scenarios.…”

Section: Introductionmentioning

confidence: 99%