Target identity-aware network flow for online multiple target tracking
In this paper we show that multiple object tracking (MOT) can be formulated in a framework, where the detection and data-association are performed simultaneously. Our method allows us to overcome the confinements of data association based MOT approaches; where the performance is dependent on the obj...
| Main Authors: | , , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
IEEE
2015
|
| _version_ | 1826313886313218048 |
|---|---|
| author | Dehghan, A Tian, Y Torr, PHS Shah, M |
| author_facet | Dehghan, A Tian, Y Torr, PHS Shah, M |
| author_sort | Dehghan, A |
| collection | OXFORD |
| description | In this paper we show that multiple object tracking (MOT) can be formulated in a framework, where the detection and data-association are performed simultaneously. Our method allows us to overcome the confinements of data association based MOT approaches; where the performance is dependent on the object detection results provided at input level. At the core of our method lies structured learning which learns a model for each target and infers the best location of all targets simultaneously in a video clip. The inference of our structured learning is done through a new Target Identity-aware Network Flow (TINF), where each node in the network encodes the probability of each target identity belonging to that node. The proposed Lagrangian relaxation optimization finds the high quality solution to the network. During optimization a soft spatial constraint is enforced between the nodes of the graph which helps reducing the ambiguity caused by nearby targets with similar appearance in crowded scenarios. We show that automatically detecting and tracking targets in a single framework can help resolve the ambiguities due to frequent occlusion and heavy articulation of targets. Our experiments involve challenging yet distinct datasets and show that our method can achieve results better than the state-of-art. |
| first_indexed | 2024-09-25T04:23:28Z |
| format | Conference item |
| id | oxford-uuid:55d95879-5064-4543-b38f-f95f93dc271a |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-09-25T04:23:28Z |
| publishDate | 2015 |
| publisher | IEEE |
| record_format | dspace |
| spelling | oxford-uuid:55d95879-5064-4543-b38f-f95f93dc271a2024-08-21T15:13:18ZTarget identity-aware network flow for online multiple target trackingConference itemhttp://purl.org/coar/resource_type/c_5794uuid:55d95879-5064-4543-b38f-f95f93dc271aEnglishSymplectic ElementsIEEE2015Dehghan, ATian, YTorr, PHSShah, MIn this paper we show that multiple object tracking (MOT) can be formulated in a framework, where the detection and data-association are performed simultaneously. Our method allows us to overcome the confinements of data association based MOT approaches; where the performance is dependent on the object detection results provided at input level. At the core of our method lies structured learning which learns a model for each target and infers the best location of all targets simultaneously in a video clip. The inference of our structured learning is done through a new Target Identity-aware Network Flow (TINF), where each node in the network encodes the probability of each target identity belonging to that node. The proposed Lagrangian relaxation optimization finds the high quality solution to the network. During optimization a soft spatial constraint is enforced between the nodes of the graph which helps reducing the ambiguity caused by nearby targets with similar appearance in crowded scenarios. We show that automatically detecting and tracking targets in a single framework can help resolve the ambiguities due to frequent occlusion and heavy articulation of targets. Our experiments involve challenging yet distinct datasets and show that our method can achieve results better than the state-of-art. |
| spellingShingle | Dehghan, A Tian, Y Torr, PHS Shah, M Target identity-aware network flow for online multiple target tracking |
| title | Target identity-aware network flow for online multiple target tracking |
| title_full | Target identity-aware network flow for online multiple target tracking |
| title_fullStr | Target identity-aware network flow for online multiple target tracking |
| title_full_unstemmed | Target identity-aware network flow for online multiple target tracking |
| title_short | Target identity-aware network flow for online multiple target tracking |
| title_sort | target identity aware network flow for online multiple target tracking |
| work_keys_str_mv | AT dehghana targetidentityawarenetworkflowforonlinemultipletargettracking AT tiany targetidentityawarenetworkflowforonlinemultipletargettracking AT torrphs targetidentityawarenetworkflowforonlinemultipletargettracking AT shahm targetidentityawarenetworkflowforonlinemultipletargettracking |