Individual and group tracking with the evaluation of social interactions
Tracking groups of people is a challenging problem. Groups may grow or shrink dynamically with merging and splitting of individuals and conventional trackers are not designed to handle such cases. In this study, the authors present a conjoint individual and group tracking (CIGT) framework based on p...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2017-04-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2016.0238 |
| _version_ | 1797685028346396672 |
|---|---|
| author | Ahmet Yigit Alptekin Temizel |
| author_facet | Ahmet Yigit Alptekin Temizel |
| author_sort | Ahmet Yigit |
| collection | DOAJ |
| description | Tracking groups of people is a challenging problem. Groups may grow or shrink dynamically with merging and splitting of individuals and conventional trackers are not designed to handle such cases. In this study, the authors present a conjoint individual and group tracking (CIGT) framework based on particle filter and online learning. CIGT has four complementary phases: two‐phase association, false positive elimination, tracking and learning. First, reliable tracklets are created and detection responses are associated to tracklets in two‐phase association. Then, hierarchal false positive elimination is performed for unassociated detection responses. In the tracking phase, CIGT calculates multiple weights from the observation and jointly models individuals and groups. Particle advection is used in the motion model of CIGT to facilitate tracking of dense groups. In the learning phase, the discriminative appearance model, consisting of shape, colour and texture features, is extracted and used in AdaBoost online learning. Using the discriminative learning model, state estimation is performed on both individuals and groups. The experimental results show that the performance of the proposed framework compares favourably with other individual and group‐tracking methods for both real and synthetic datasets. |
| first_indexed | 2024-03-12T00:39:19Z |
| format | Article |
| id | doaj.art-963cef5ed5cc4a15a4cc3ab945d2fa69 |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:39:19Z |
| publishDate | 2017-04-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-963cef5ed5cc4a15a4cc3ab945d2fa692023-09-15T09:16:46ZengWileyIET Computer Vision1751-96321751-96402017-04-0111325526310.1049/iet-cvi.2016.0238Individual and group tracking with the evaluation of social interactionsAhmet Yigit0Alptekin Temizel1Graduate School of InformaticsMiddle East Technical UniversityAnkaraTurkeyGraduate School of InformaticsMiddle East Technical UniversityAnkaraTurkeyTracking groups of people is a challenging problem. Groups may grow or shrink dynamically with merging and splitting of individuals and conventional trackers are not designed to handle such cases. In this study, the authors present a conjoint individual and group tracking (CIGT) framework based on particle filter and online learning. CIGT has four complementary phases: two‐phase association, false positive elimination, tracking and learning. First, reliable tracklets are created and detection responses are associated to tracklets in two‐phase association. Then, hierarchal false positive elimination is performed for unassociated detection responses. In the tracking phase, CIGT calculates multiple weights from the observation and jointly models individuals and groups. Particle advection is used in the motion model of CIGT to facilitate tracking of dense groups. In the learning phase, the discriminative appearance model, consisting of shape, colour and texture features, is extracted and used in AdaBoost online learning. Using the discriminative learning model, state estimation is performed on both individuals and groups. The experimental results show that the performance of the proposed framework compares favourably with other individual and group‐tracking methods for both real and synthetic datasets.https://doi.org/10.1049/iet-cvi.2016.0238social interaction evaluationconjoint individual and group tracking frameworkCIGT frameworkparticle filteronline learning phasetwo-phase association |
| spellingShingle | Ahmet Yigit Alptekin Temizel Individual and group tracking with the evaluation of social interactions IET Computer Vision social interaction evaluation conjoint individual and group tracking framework CIGT framework particle filter online learning phase two-phase association |
| title | Individual and group tracking with the evaluation of social interactions |
| title_full | Individual and group tracking with the evaluation of social interactions |
| title_fullStr | Individual and group tracking with the evaluation of social interactions |
| title_full_unstemmed | Individual and group tracking with the evaluation of social interactions |
| title_short | Individual and group tracking with the evaluation of social interactions |
| title_sort | individual and group tracking with the evaluation of social interactions |
| topic | social interaction evaluation conjoint individual and group tracking framework CIGT framework particle filter online learning phase two-phase association |
| url | https://doi.org/10.1049/iet-cvi.2016.0238 |
| work_keys_str_mv | AT ahmetyigit individualandgrouptrackingwiththeevaluationofsocialinteractions AT alptekintemizel individualandgrouptrackingwiththeevaluationofsocialinteractions |