Prior-Guided YOLOX for Tiny Roll Mark Detection on Strip Steel
Luo, Qiwu; Chen, Yangwen; Su, Jiaojiao; Yang, Chunhua; Silvén, Olli; Liu, Li (2024-03-18)
IEEE
18.03.2024
Q. Luo, Y. Chen, J. Su, C. Yang, O. Silvén and L. Liu, "Prior-Guided YOLOX for Tiny Roll Mark Detection on Strip Steel," in IEEE Sensors Journal, vol. 24, no. 9, pp. 15575-15587, 1 May1, 2024, doi: 10.1109/JSEN.2024.3374388.
https://rightsstatements.org/vocab/InC/1.0/
© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
https://rightsstatements.org/vocab/InC/1.0/
© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
https://rightsstatements.org/vocab/InC/1.0/
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:oulu-202411116674
https://urn.fi/URN:NBN:fi:oulu-202411116674
Tiivistelmä
Abstract
Accurate and efficient roll mark detection on the strip steel surfaces is a fundamental but “hard” ultra-tiny target detection problem due to its small pixel occupation in low-contrast images. By fully exploiting the prior information of roll marks, this article proposed a Prior-Guided YOLOX network (PG-YOLOX). First, inspired by the prior that the horizontal distribution of the roll marks is more uneven than the vertical direction, an orthogonal context attention (OCA) is carefully designed between the backbone and neck to better capture tiny target features by enhancing context representations. Besides, a cross-adaptive aggregation (CAA) module is constructed that adopts a cross-layer semantic prior during feature fusion to improve feature selection. Notably, a fresh tiny object detection dataset collected in an industrial scenario, Steel-Tiny, is released to the public. Based on experiments on the Steel-Tiny, our proposed PG-YOLOX has the highest mean average precision (mAP) (71.7%) for detecting roll marks, outperforming state-of-the-art methods. The generalization ability of our PG-YOLOX is demonstrated on the public remote sensing dataset VEDAI. The data will be publicly available at https://www.ilove-cv.com/steel-tiny-2/ .
Accurate and efficient roll mark detection on the strip steel surfaces is a fundamental but “hard” ultra-tiny target detection problem due to its small pixel occupation in low-contrast images. By fully exploiting the prior information of roll marks, this article proposed a Prior-Guided YOLOX network (PG-YOLOX). First, inspired by the prior that the horizontal distribution of the roll marks is more uneven than the vertical direction, an orthogonal context attention (OCA) is carefully designed between the backbone and neck to better capture tiny target features by enhancing context representations. Besides, a cross-adaptive aggregation (CAA) module is constructed that adopts a cross-layer semantic prior during feature fusion to improve feature selection. Notably, a fresh tiny object detection dataset collected in an industrial scenario, Steel-Tiny, is released to the public. Based on experiments on the Steel-Tiny, our proposed PG-YOLOX has the highest mean average precision (mAP) (71.7%) for detecting roll marks, outperforming state-of-the-art methods. The generalization ability of our PG-YOLOX is demonstrated on the public remote sensing dataset VEDAI. The data will be publicly available at https://www.ilove-cv.com/steel-tiny-2/ .
Kokoelmat
- Avoin saatavuus [38841]