A study of a target tracking algorithm using global nearest neighbor approach

Konstantinova, Pavlina; Udvarev, Alexander; Semerdjiev, Tzvetan

doi:10.1145/973620.973668

Cited by 179 publications

(115 citation statements)

References 3 publications

Supporting

Mentioning

106

Contrasting

Order By: Relevance

“…The cost metric used in our tracking system is the Mahalanobis distance 1 between the detection z i k and the propagated track x j k|k−1 . The covariance used to calculate this distance is the innovation 1 Note that other GNN data association approaches have recommended minimizing the square of this distance [39]. We found best results minimizing the non-squared distance in our applications.…”

Section: Global Nearest Neighbour Data Associationmentioning

confidence: 83%

“…The Global Nearest Neighbour (GNN) approach is a data association method which minimizes the cumulative distance of all assignments in the matrix D. This typically results in less assignment errors compared to the NN approach [39].…”

Section: Global Nearest Neighbourmentioning

confidence: 99%

“…Tracks can be initiated in the simplest case by starting a new track for every unassigned measurement at each timestep [39,52]. A more conservative approach, which is useful in situations where noisy background measurements can arise, is to first start a potential track for every unassigned measurement, then to only intiate a confirmed track once the potential track has been assigned measurements across multiple timesteps [29].…”

Section: Track Initiation and Deletionmentioning

confidence: 99%

See 2 more Smart Citations

Person tracking and following with 2D laser scanners

Leigh

Pineau

Olmedo

et al. 2015

2015 IEEE International Conference on Robotics and Automation (ICRA)

155

127

View full text Add to dashboard Cite

ACKNOWLEDGEMENTSThis thesis would not have been possible without the help of a great many people who provided me with inspiration, direction and encouragement.Foremost, I would like to thank my supervisor, Joelle Pineau. You've been the ideal mixture of supportive, easy-going and motivating during my master's. You were at once hands-off, letting me pursue the research ideas I was most interested in, and engaged, constantly providing me with valuable feedback on whatever we were working on. You listened to my ideas from day one so I would grow and learn to think for myself rather than follow orders. You were patient when research went slow and were quick to offer praise when things went well. I could not have asked for more from a supervisor. In this thesis we propose a new algorithm for robust detection, tracking and following from laser scanners mounted at leg height. We develop a set of quantitative benchmarks based on the CLEAR MOT metrics which demonstrate that the approach is more effective than currently available alternatives in a variety of environments, both indoor and outdoor, and on different robot platforms (the intelligent power wheelchair and a Clearpath Husky). To the best of our knowledge, these are the first benchmarks which evaluate person tracking performance from a mobile robot with laser scanners at leg height. We further integrate our novel person tracking system with a person following control system to demonstrate its usefulness in this application. The method has been implemented in the Robot Operating System (ROS) framework and will be publicly released as a ROS package. Dans cette thèse nous proposons un nouvel algorithme pour la détection, la localisation et le suivià partir de capteurs lasers situésà hauteur de la jambe.Nous développons un ensemble de mesures de référence quantitatives basées sur les métriques CLEAR MOT, qui démontrent que notre approche est plus efficace que les alternatives actuelles, ce dans une variété d'environnements,à la fois intérieurs et extérieurs, et sur différentes plateformes de robots (le fauteuil roulantélectrique intelligent et un Clearpath Husky). Au mieux de notre connaissance, nous sommes les premiersàévaluer la performance du suivi de personnes depuis un robot mobilé equipé de capteurs lasersà hauteur de la jambe. De plus, pour en démontrer l'utilité, nous intégrons notre nouveau système de localisation de personnes avec un système de contrôle automatique permettant au robot de se déplacer en suivant une personne.

show abstract

Section: Global Nearest Neighbour Data Associationmentioning

confidence: 83%

Section: Global Nearest Neighbourmentioning

confidence: 99%

Section: Track Initiation and Deletionmentioning

confidence: 99%

See 1 more Smart Citation

Person tracking and following with 2D laser scanners

Leigh

Pineau

Olmedo

et al. 2015

2015 IEEE International Conference on Robotics and Automation (ICRA)

155

127

View full text Add to dashboard Cite

show abstract

“…4(a). A global nearest neighbor (GNN) was devised with the fish posture to solve the data association issue for tracking multiple individuals (Cai et al, 2006;Konstantinova et al, 2003). The symbol f i t − 1 and f i t indicate the ith individual fish at time t − 1 and time t, respectively.…”

Section: Multiple Individual Trackingmentioning

confidence: 99%

Posture tracking of multiple individual fish for behavioral monitoring with visual sensors

Xia

Chon

Liu

et al. 2016

Ecological Informatics

View full text Add to dashboard Cite

a b s t r a c t a r t i c l e i n f oArticle history: Received 8 January 2015 Received in revised form 7 July 2016 Accepted 12 July 2016 Available online xxxx A novel scheme for the behavioral monitoring of multiple fish is presented based on measurements of the fish posture. Image identification of the fish head and tail is proposed by examining the gray level appearance features. A simplified posture of fish was calculated from its head and centroid. Multiple individual tracking was developed by incorporating the fish posture and global nearest neighbor. The proposed tracking scheme was tested with 2-5 individual Zebra fish (Cyprinidae, Danio rerio) under laboratory conditions. The experimental results confirmed the stability of the identification of a fish head and tail and a robust tracking performance was achieved. The proposed method could accurately record the movement trajectories and posture information of each individual. The tracking errors were only 0.278%-1.572% for 2-5 individual fish while the posture measurement error rates were less than 0.16%. Furthermore, the movement patterns of the fish, e.g., angular variations and distribution of the movement angle, were investigated from the behavioral data, which revealed the advantages of the proposed posture measurement for behavioral studies. The aggregation behavior of multiple fish was also analyzed to reveal the interaction patterns of the individuals in response to the spatial formation of the neighbors.

show abstract

“…Although our detection algorithm is fairly robust, it is also not person-specific, and therefore in a small indoor environment there are always ambiguities, arising from neighboring targets, as well as from missing detections and false alarms caused by background clutter. To this respect we employ the Global Nearest Neighbor (GNN) approach, that gives a good solution for this problem (Konstantinova et al, 2003), while requiring relative low computational cost.…”

Section: Multiple People Trackingmentioning

confidence: 99%

Multi-Camera People Tracking With Hierarchical Likelihood Grids

Chen

Panin

Knoll

2011

Proceedings of the International Conference on Computer Vision Theory and Applications

View full text Add to dashboard Cite

Abstract:In this paper, we present a grid-based tracking by detection methodology, applied to 3D people tracking for multi-camera video surveillance. In particular, frame-by-frame detection is performed by means of hierarchical likelihood grids, using edge matching through the oriented distance transform on each camera view and a simple person model, followed by likelihood grids clustering in state-space. Subsequently, the tracking module performs a global nearest neighbor data association, in order to initiate, maintain and terminate tracks automatically. The proposed system can easily include additional features, such as color or background subtraction, it can be scaled to more camera views, and it can be used to track other items as well. We demonstrate it through experiments in indoor sequences, using a calibrated multi-camera setup.

show abstract

A study of a target tracking algorithm using global nearest neighbor approach

Cited by 179 publications

References 3 publications

Person tracking and following with 2D laser scanners

Person tracking and following with 2D laser scanners

Posture tracking of multiple individual fish for behavioral monitoring with visual sensors

Multi-Camera People Tracking With Hierarchical Likelihood Grids

Contact Info

Product

Resources

About