Robust and Efficient Corner Detector Using Non-Corners Exclusion
Corner detection is a traditional type of feature point detection method. Among methods used, with its good accuracy and the properties of invariance for rotation, noise and illumination, the Harris corner detector is widely used in the fields of vision tasks and image processing. Although it posses...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/2/443 |
| _version_ | 1819157399430234112 |
|---|---|
| author | Tao Luo Zaifeng Shi Pumeng Wang |
| author_facet | Tao Luo Zaifeng Shi Pumeng Wang |
| author_sort | Tao Luo |
| collection | DOAJ |
| description | Corner detection is a traditional type of feature point detection method. Among methods used, with its good accuracy and the properties of invariance for rotation, noise and illumination, the Harris corner detector is widely used in the fields of vision tasks and image processing. Although it possesses a good performance in detection quality, its application is limited due to its low detection efficiency. The efficiency is crucial in many applications because it determines whether the detector is suitable for real-time tasks. In this paper, a robust and efficient corner detector (RECD) improved from Harris corner detector is proposed. First, we borrowed the principle of the feature from accelerated segment test (FAST) algorithm for corner pre-detection, in order to rule out non-corners and retain many strong corners as real corners. Those uncertain corners are looked at as candidate corners. Second, the gradients are calculated in the same way as the original Harris detector for those candidate corners. Third, to reduce additional computation amount, only the corner response function (CRF) of the candidate corners is calculated. Finally, we replace the highly complex non-maximum suppression (NMS) by an improved NMS to obtain the resulting corners. Experiments demonstrate that RECD is more competitive than some popular corner detectors in detection quality and speed. The accuracy and robustness of our method is slightly better than the original Harris detector, and the detection time is only approximately 8.2% of its original value. |
| first_indexed | 2024-12-22T16:08:09Z |
| format | Article |
| id | doaj.art-66b22f208ddd49fcb3c29fee3d252b8d |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-22T16:08:09Z |
| publishDate | 2020-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-66b22f208ddd49fcb3c29fee3d252b8d2022-12-21T18:20:32ZengMDPI AGApplied Sciences2076-34172020-01-0110244310.3390/app10020443app10020443Robust and Efficient Corner Detector Using Non-Corners ExclusionTao Luo0Zaifeng Shi1Pumeng Wang2College of Intelligence and Computing, Tianjin University, Tianjin 300072, ChinaSchool of Microelectronics, Tianjin University, Tianjin 300072, ChinaSchool of Microelectronics, Tianjin University, Tianjin 300072, ChinaCorner detection is a traditional type of feature point detection method. Among methods used, with its good accuracy and the properties of invariance for rotation, noise and illumination, the Harris corner detector is widely used in the fields of vision tasks and image processing. Although it possesses a good performance in detection quality, its application is limited due to its low detection efficiency. The efficiency is crucial in many applications because it determines whether the detector is suitable for real-time tasks. In this paper, a robust and efficient corner detector (RECD) improved from Harris corner detector is proposed. First, we borrowed the principle of the feature from accelerated segment test (FAST) algorithm for corner pre-detection, in order to rule out non-corners and retain many strong corners as real corners. Those uncertain corners are looked at as candidate corners. Second, the gradients are calculated in the same way as the original Harris detector for those candidate corners. Third, to reduce additional computation amount, only the corner response function (CRF) of the candidate corners is calculated. Finally, we replace the highly complex non-maximum suppression (NMS) by an improved NMS to obtain the resulting corners. Experiments demonstrate that RECD is more competitive than some popular corner detectors in detection quality and speed. The accuracy and robustness of our method is slightly better than the original Harris detector, and the detection time is only approximately 8.2% of its original value.https://www.mdpi.com/2076-3417/10/2/443corner detectionharris corner detectornon-corners exclusionfeatures from accelerated segment test |
| spellingShingle | Tao Luo Zaifeng Shi Pumeng Wang Robust and Efficient Corner Detector Using Non-Corners Exclusion Applied Sciences corner detection harris corner detector non-corners exclusion features from accelerated segment test |
| title | Robust and Efficient Corner Detector Using Non-Corners Exclusion |
| title_full | Robust and Efficient Corner Detector Using Non-Corners Exclusion |
| title_fullStr | Robust and Efficient Corner Detector Using Non-Corners Exclusion |
| title_full_unstemmed | Robust and Efficient Corner Detector Using Non-Corners Exclusion |
| title_short | Robust and Efficient Corner Detector Using Non-Corners Exclusion |
| title_sort | robust and efficient corner detector using non corners exclusion |
| topic | corner detection harris corner detector non-corners exclusion features from accelerated segment test |
| url | https://www.mdpi.com/2076-3417/10/2/443 |
| work_keys_str_mv | AT taoluo robustandefficientcornerdetectorusingnoncornersexclusion AT zaifengshi robustandefficientcornerdetectorusingnoncornersexclusion AT pumengwang robustandefficientcornerdetectorusingnoncornersexclusion |