Vehicle pose estimation for vehicle detection and tracking based on road direction
Vehicle has several types and each of them has different color, size, and shape. The appearance of vehicle also changes if viewed from different viewpoint of traffic surveillance camera. This situation can create many possibilities of vehicle poses. However, the one in common, vehicle pose usually f...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universitas Ahmad Dahlan
2017-03-01
|
| Series: | IJAIN (International Journal of Advances in Intelligent Informatics) |
| Subjects: | |
| Online Access: | http://ijain.org/index.php/IJAIN/article/view/88 |
| _version_ | 1819070542253129728 |
|---|---|
| author | Adhi Prahara Ahmad Azhari Murinto Murinto |
| author_facet | Adhi Prahara Ahmad Azhari Murinto Murinto |
| author_sort | Adhi Prahara |
| collection | DOAJ |
| description | Vehicle has several types and each of them has different color, size, and shape. The appearance of vehicle also changes if viewed from different viewpoint of traffic surveillance camera. This situation can create many possibilities of vehicle poses. However, the one in common, vehicle pose usually follows road direction. Therefore, this research proposes a method to estimate the pose of vehicle for vehicle detection and tracking based on road direction. Vehicle training data are generated from 3D vehicle models in four-pair orientation categories. Histogram of Oriented Gradients (HOG) and Linear-Support Vector Machine (Linear-SVM) are used to build vehicle detectors from the data. Road area is extracted from traffic surveillance image to localize the detection area. The pose of vehicle which estimated based on road direction will be used to select a suitable vehicle detector for vehicle detection process. To obtain the final vehicle object, vehicle line checking method is applied to the vehicle detection result. Finally, vehicle tracking is performed to give label on each vehicle. The test conducted on various viewpoints of traffic surveillance camera shows that the method effectively detects and tracks vehicle by estimating the pose of vehicle. Performance evaluation of the proposed method shows 0.9170 of accuracy and 0.9161 of balance accuracy (BAC). |
| first_indexed | 2024-12-21T17:07:35Z |
| format | Article |
| id | doaj.art-6044e476dbf949e388d166df6d27f961 |
| institution | Directory Open Access Journal |
| issn | 2442-6571 2548-3161 |
| language | English |
| last_indexed | 2024-12-21T17:07:35Z |
| publishDate | 2017-03-01 |
| publisher | Universitas Ahmad Dahlan |
| record_format | Article |
| series | IJAIN (International Journal of Advances in Intelligent Informatics) |
| spelling | doaj.art-6044e476dbf949e388d166df6d27f9612022-12-21T18:56:29ZengUniversitas Ahmad DahlanIJAIN (International Journal of Advances in Intelligent Informatics)2442-65712548-31612017-03-0131354610.26555/ijain.v3i1.8850Vehicle pose estimation for vehicle detection and tracking based on road directionAdhi Prahara0Ahmad Azhari1Murinto Murinto2Universitas Ahmad DahlanUniversitas Ahmad DahlanUniversitas Ahmad DahlanVehicle has several types and each of them has different color, size, and shape. The appearance of vehicle also changes if viewed from different viewpoint of traffic surveillance camera. This situation can create many possibilities of vehicle poses. However, the one in common, vehicle pose usually follows road direction. Therefore, this research proposes a method to estimate the pose of vehicle for vehicle detection and tracking based on road direction. Vehicle training data are generated from 3D vehicle models in four-pair orientation categories. Histogram of Oriented Gradients (HOG) and Linear-Support Vector Machine (Linear-SVM) are used to build vehicle detectors from the data. Road area is extracted from traffic surveillance image to localize the detection area. The pose of vehicle which estimated based on road direction will be used to select a suitable vehicle detector for vehicle detection process. To obtain the final vehicle object, vehicle line checking method is applied to the vehicle detection result. Finally, vehicle tracking is performed to give label on each vehicle. The test conducted on various viewpoints of traffic surveillance camera shows that the method effectively detects and tracks vehicle by estimating the pose of vehicle. Performance evaluation of the proposed method shows 0.9170 of accuracy and 0.9161 of balance accuracy (BAC).http://ijain.org/index.php/IJAIN/article/view/88Vehicle poseRoad detectionRoad directionVehicle detectionVehicle tracking |
| spellingShingle | Adhi Prahara Ahmad Azhari Murinto Murinto Vehicle pose estimation for vehicle detection and tracking based on road direction IJAIN (International Journal of Advances in Intelligent Informatics) Vehicle pose Road detection Road direction Vehicle detection Vehicle tracking |
| title | Vehicle pose estimation for vehicle detection and tracking based on road direction |
| title_full | Vehicle pose estimation for vehicle detection and tracking based on road direction |
| title_fullStr | Vehicle pose estimation for vehicle detection and tracking based on road direction |
| title_full_unstemmed | Vehicle pose estimation for vehicle detection and tracking based on road direction |
| title_short | Vehicle pose estimation for vehicle detection and tracking based on road direction |
| title_sort | vehicle pose estimation for vehicle detection and tracking based on road direction |
| topic | Vehicle pose Road detection Road direction Vehicle detection Vehicle tracking |
| url | http://ijain.org/index.php/IJAIN/article/view/88 |
| work_keys_str_mv | AT adhiprahara vehicleposeestimationforvehicledetectionandtrackingbasedonroaddirection AT ahmadazhari vehicleposeestimationforvehicledetectionandtrackingbasedonroaddirection AT murintomurinto vehicleposeestimationforvehicledetectionandtrackingbasedonroaddirection |