D‐patches: effective traffic sign detection with occlusion handling
In advanced driver assistance systems, accurate detection of traffic signs plays an important role in extracting information about the road ahead. However, traffic signs are persistently occluded by vehicles, trees, and other structures on road. Performance of a detector decreases drastically when o...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2017-08-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2016.0303 |
| _version_ | 1827817645072711680 |
|---|---|
| author | Yawar Rehman Irfan Riaz Xue Fan Hyunchul Shin |
| author_facet | Yawar Rehman Irfan Riaz Xue Fan Hyunchul Shin |
| author_sort | Yawar Rehman |
| collection | DOAJ |
| description | In advanced driver assistance systems, accurate detection of traffic signs plays an important role in extracting information about the road ahead. However, traffic signs are persistently occluded by vehicles, trees, and other structures on road. Performance of a detector decreases drastically when occlusions are encountered especially when it is trained using full object templates. Therefore, we propose a new method called discriminative patches (d‐patches), which is a traffic sign detection (TSD) framework with occlusion handling capability. D‐patches are those regions of an object that possess the most discriminative features than their surroundings. They are mined during training and are used for classification instead of the full object templates. Furthermore, we observe that the distribution of redundant‐detections around a true‐positive is different from that around a false‐positive. Based on this observation, we propose a novel hypothesis generation scheme that uses a voting and penalisation mechanism to accurately select a true‐positive candidate. We also introduce a new Korean TSD (KTSD) dataset with several evaluation settings to facilitate detector's evaluation under different conditions. The proposed method achieves 100% detection accuracy on German TSD benchmark and achieves 4.0% better detection accuracy, when compared with other well‐known methods (under partially occluded settings), on KTSD dataset. |
| first_indexed | 2024-03-12T00:37:10Z |
| format | Article |
| id | doaj.art-71e8c0bbe0d149a9a9994959d30d5c88 |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:37:10Z |
| publishDate | 2017-08-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-71e8c0bbe0d149a9a9994959d30d5c882023-09-15T09:33:14ZengWileyIET Computer Vision1751-96321751-96402017-08-0111536837710.1049/iet-cvi.2016.0303D‐patches: effective traffic sign detection with occlusion handlingYawar Rehman0Irfan Riaz1Xue Fan2Hyunchul Shin3Department of Electronics and Communication EngineeringHanyang UniversityAnsan426‐791KoreaDepartment of Electronics and Communication EngineeringHanyang UniversityAnsan426‐791KoreaDepartment of Electronics and Communication EngineeringHanyang UniversityAnsan426‐791KoreaDepartment of Electronics and Communication EngineeringHanyang UniversityAnsan426‐791KoreaIn advanced driver assistance systems, accurate detection of traffic signs plays an important role in extracting information about the road ahead. However, traffic signs are persistently occluded by vehicles, trees, and other structures on road. Performance of a detector decreases drastically when occlusions are encountered especially when it is trained using full object templates. Therefore, we propose a new method called discriminative patches (d‐patches), which is a traffic sign detection (TSD) framework with occlusion handling capability. D‐patches are those regions of an object that possess the most discriminative features than their surroundings. They are mined during training and are used for classification instead of the full object templates. Furthermore, we observe that the distribution of redundant‐detections around a true‐positive is different from that around a false‐positive. Based on this observation, we propose a novel hypothesis generation scheme that uses a voting and penalisation mechanism to accurately select a true‐positive candidate. We also introduce a new Korean TSD (KTSD) dataset with several evaluation settings to facilitate detector's evaluation under different conditions. The proposed method achieves 100% detection accuracy on German TSD benchmark and achieves 4.0% better detection accuracy, when compared with other well‐known methods (under partially occluded settings), on KTSD dataset.https://doi.org/10.1049/iet-cvi.2016.0303advanced driver assistance systemstraffic signsfull object templatesdiscriminative patchesd-patchestraffic sign detection framework |
| spellingShingle | Yawar Rehman Irfan Riaz Xue Fan Hyunchul Shin D‐patches: effective traffic sign detection with occlusion handling IET Computer Vision advanced driver assistance systems traffic signs full object templates discriminative patches d-patches traffic sign detection framework |
| title | D‐patches: effective traffic sign detection with occlusion handling |
| title_full | D‐patches: effective traffic sign detection with occlusion handling |
| title_fullStr | D‐patches: effective traffic sign detection with occlusion handling |
| title_full_unstemmed | D‐patches: effective traffic sign detection with occlusion handling |
| title_short | D‐patches: effective traffic sign detection with occlusion handling |
| title_sort | d patches effective traffic sign detection with occlusion handling |
| topic | advanced driver assistance systems traffic signs full object templates discriminative patches d-patches traffic sign detection framework |
| url | https://doi.org/10.1049/iet-cvi.2016.0303 |
| work_keys_str_mv | AT yawarrehman dpatcheseffectivetrafficsigndetectionwithocclusionhandling AT irfanriaz dpatcheseffectivetrafficsigndetectionwithocclusionhandling AT xuefan dpatcheseffectivetrafficsigndetectionwithocclusionhandling AT hyunchulshin dpatcheseffectivetrafficsigndetectionwithocclusionhandling |