{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,3]],"date-time":"2026-01-03T03:29:11Z","timestamp":1767410951600,"version":"3.48.0"},"reference-count":50,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2026,1,1]]},"DOI":"10.1587\/transinf.2024edp7318","type":"journal-article","created":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T18:07:26Z","timestamp":1751825246000},"page":"180-192","source":"Crossref","is-referenced-by-count":0,"title":["ROD-YOLO: A Fast and Accurate Obstacle Detection Framework for Railways Based on Feature Enhancement and Context Aggregation"],"prefix":"10.1587","volume":"E109.D","author":[{"given":"Cong","family":"GUAN","sequence":"first","affiliation":[{"name":"Graduate School of Information, Production and Systems, Waseda University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuya","family":"IEIRI","sequence":"additional","affiliation":[{"name":"Graduate School of Information, Production and Systems, Waseda University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Osamu","family":"YOSHIE","sequence":"additional","affiliation":[{"name":"Institute for Global Strategies on Industry-Academia Fusion (IGSIAF), Waseda University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"doi-asserted-by":"publisher","unstructured":"[1] F.U. Rahman, M.T. Ahmed, M.M. Hasan, and N. Jahan, \u201cReal-time obstacle detection over railway track using deep neural networks,\u201d Procedia Comput. Sci., vol.215, pp.289-298, 2022. 10.1016\/j.procs.2022.12.031","key":"1","DOI":"10.1016\/j.procs.2022.12.031"},{"doi-asserted-by":"publisher","unstructured":"[2] D. Risti\u0107-Durrant, M.A. Haseeb, M. Bani\u0107, D. Stamenkovi\u0107, M. Simonovi\u0107, and D. Nikoli\u0107, \u201cSMART on-board multi-sensor obstacle detection system for improvement of rail transport safety,\u201d Proc. Inst. Mech. Eng. Part F J. Rail Rapid Transit, vol.236, no.6, pp.623-636, 2022. 10.1177\/09544097211032738","key":"2","DOI":"10.1177\/09544097211032738"},{"doi-asserted-by":"publisher","unstructured":"[3] D. Risti\u0107-Durrant, M. Franke, and K. Michels, \u201cA review of vision-based on-board obstacle detection and distance estimation in railways,\u201d Sensors, vol.21, no.10, p.3452, 2021. 10.3390\/s21103452","key":"3","DOI":"10.3390\/s21103452"},{"doi-asserted-by":"publisher","unstructured":"[4] S. Fontul, E. Fortunato, F. De Chiara, R. Burrinha, and M. Baldeiras, \u201cRailways track characterization using ground penetrating radar,\u201d Procedia Eng., vol.143, pp.1193-1200, 2016. 10.1016\/j.proeng.2016.06.120","key":"4","DOI":"10.1016\/j.proeng.2016.06.120"},{"doi-asserted-by":"publisher","unstructured":"[5] R. Yang and Y. Yu, \u201cArtificial convolutional neural network in object detection and semantic segmentation for medical imaging analysis,\u201d Front. Oncol., vol.11, 2021. 10.3389\/fonc.2021.638182","key":"5","DOI":"10.3389\/fonc.2021.638182"},{"doi-asserted-by":"publisher","unstructured":"[6] M. Rezaei, M. Azarmi, and F.M.P. Mir, \u201c3d-net: Monocular 3d object recognition for traffic monitoring,\u201d Expert Systems with Applications, vol.227, pp.120253-120270, 2023. 10.1016\/j.eswa.2023.120253","key":"6","DOI":"10.1016\/j.eswa.2023.120253"},{"doi-asserted-by":"publisher","unstructured":"[7] Y. Shen, F. Zhang, D. Liu, W. Pu, and Q. Zhang, \u201cManhattan-distance IoU loss for fast and accurate bounding box regression and object detection,\u201d Neurocomputing, vol.500, pp.99-114, 2022. 10.1016\/j.neucom.2022.05.052","key":"7","DOI":"10.1016\/j.neucom.2022.05.052"},{"doi-asserted-by":"publisher","unstructured":"[8] Q. Zhang, Y. Li, Z. Zhang, S. Yin, and L. Ma, \u201cMarine target detection for PPI images based on YOLO-SWFormer,\u201d Alexandria Eng. J., vol.82, pp.396-403, 2023. 10.1016\/j.aej.2023.10.014","key":"8","DOI":"10.1016\/j.aej.2023.10.014"},{"doi-asserted-by":"crossref","unstructured":"[9] R. Girshick, J. Donahue, T. Darrell, and J. Malik, \u201cRich feature hierarchies for accurate object detection and semantic segmentation,\u201d Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp.580-587, 2014. 10.1109\/cvpr.2014.81","key":"9","DOI":"10.1109\/CVPR.2014.81"},{"doi-asserted-by":"crossref","unstructured":"[10] R. Girshick, \u201cFast R-CNN,\u201d Proc. IEEE Int. Conf. Comput. Vis., pp.1440-1448, 2015. 10.1109\/iccv.2015.169","key":"10","DOI":"10.1109\/ICCV.2015.169"},{"doi-asserted-by":"publisher","unstructured":"[11] S. Ren, K. He, R. Girshick, and J. Sun, \u201cFaster R-CNN: Towards real-time object detection with region proposal networks,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.39, no.6, pp.1137-1149, 2016. 10.1109\/tpami.2016.2577031","key":"11","DOI":"10.1109\/TPAMI.2016.2577031"},{"unstructured":"[12] R. Joseph, S. Divvala, R. Girshick, and A. Farhadi, \u201cYou only look once: Unified, real-time object detection,\u201d arXiv preprint arXiv:1506.02640, 2015.","key":"12"},{"unstructured":"[13] R. Joseph and A. Farhadi, \u201cYOLO9000: Better, faster, stronger,\u201d arXiv preprint arXiv:1612.08242, 2016.","key":"13"},{"doi-asserted-by":"crossref","unstructured":"[14] C.-Y. Wang, A. Bochkovskiy, and H.-Y.M. Liao, \u201cYOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors,\u201d Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.7464-7475, 2023. 10.1109\/cvpr52729.2023.00721","key":"14","DOI":"10.1109\/CVPR52729.2023.00721"},{"unstructured":"[15] \u201cYolov8: A new state-of-the-art computer vision model.\u201d https:\/\/yolov8.com\/, accessed Dec. 2023.","key":"15"},{"doi-asserted-by":"crossref","unstructured":"[16] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A.C. Berg, \u201cSSD: Single shot multibox detector,\u201d Proc. Eur. Conf. Comput. Vis., pp.21-37, Springer, 2016. 10.1007\/978-3-319-46448-0_2","key":"16","DOI":"10.1007\/978-3-319-46448-0_2"},{"doi-asserted-by":"crossref","unstructured":"[17] R. Gasparini, A. D\u2019Eusanio, G. Borghi, S. Pini, G. Scaglione, S. Calderara, E. Fedeli, and R. Cucchiara, \u201cAnomaly detection, localization and classification for railway inspection,\u201d Proc. Int. Conf. Pattern Recognit., pp.3419-3426, 2021. 10.1109\/icpr48806.2021.9412972","key":"17","DOI":"10.1109\/ICPR48806.2021.9412972"},{"doi-asserted-by":"publisher","unstructured":"[18] R. Kapoor, R. Goel, and A. Sharma, \u201cAn intelligent railway surveillance framework based on recognition of object and railway track using deep learning,\u201d Multimed. Tools Appl., vol.81, no.15, pp.21083-21109, 2022. 10.1007\/s11042-022-12059-z","key":"18","DOI":"10.1007\/s11042-022-12059-z"},{"doi-asserted-by":"publisher","unstructured":"[19] D. He, Z. Zou, Y. Chen, B. Liu, X. Yao, and S. Shan, \u201cObstacle detection of rail transit based on deep learning,\u201d Measurement, vol.176, p.109241, 2021. 10.1016\/j.measurement.2021.109241","key":"19","DOI":"10.1016\/j.measurement.2021.109241"},{"doi-asserted-by":"publisher","unstructured":"[20] L. Guan, L. Jia, Z. Xie, and C. Yin, \u201cA lightweight framework for obstacle detection in the railway image based on fast region proposal and improved YOLO-tiny network,\u201d IEEE Trans. Instrum. Meas., vol.71, pp.1-16, 2022. 10.1109\/tim.2022.3150584","key":"20","DOI":"10.1109\/TIM.2022.3150584"},{"doi-asserted-by":"publisher","unstructured":"[21] B. Li, X. Ran, Y. Liu, W. Li, and Q. Duan, \u201cVh-yolov5s: Detecting the skin color of plectropomus leopardus in aquaculture using mobile phones,\u201d IEICE Trans. Inf. & Syst., vol.E107-D, no.7, pp.835-844, 2024. 10.1587\/transinf.2023edp7170","key":"21","DOI":"10.1587\/transinf.2023EDP7170"},{"doi-asserted-by":"publisher","unstructured":"[22] M. Gao, G. Chen, J. Gu, and C. Zhang, \u201cResearch on mask-wearing detection algorithm based on improved yolov7-tiny,\u201d IEICE Trans. Inf. & Syst., vol.E107-D, no.7, pp.878-889, 2024. 10.1587\/transinf.2023edp7254","key":"22","DOI":"10.1587\/transinf.2023EDP7254"},{"unstructured":"[23] J. Glenn, \u201cYOLOv5 by Ultralytics,\u201d accessed Dec. 2023.","key":"23"},{"unstructured":"[24] G. Zheng, S. Liu, F. Wang, Z. Li, and J. Sun, \u201cYOLOX: Exceeding yolo series in 2021,\u201d arXiv preprint arXiv:2107.08430, 2021.","key":"24"},{"unstructured":"[25] C. Li, L. Li, H. Jiang, K. Weng, and Y. Geng, \u201cYOLOv6: A single-stage object detection framework for industrial applications,\u201d arXiv preprint arXiv:2209.02976, 2022.","key":"25"},{"doi-asserted-by":"crossref","unstructured":"[26] C.-Y. Wang, I.-H. Yeh, and H.-Y. Mark Liao, \u201cYOLOv9: Learning what you want to learn using programmable gradient information,\u201d arXiv preprint arXiv:2402.13616, 2024.","key":"26","DOI":"10.1007\/978-3-031-72751-1_1"},{"doi-asserted-by":"publisher","unstructured":"[27] K. He, X. Zhang, S. Ren, and J. Sun, \u201cSpatial pyramid pooling in deep convolutional networks for visual recognition,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.37, no.9, pp.1904-1916, 2015. 10.1109\/tpami.2015.2389824","key":"27","DOI":"10.1109\/TPAMI.2015.2389824"},{"doi-asserted-by":"crossref","unstructured":"[28] T.-Y. Lin, P. Doll\u00e1r, R. Girshick, K. He, B. Hariharan, and S. Belongie, \u201cFeature pyramid networks for object detection,\u201d Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp.936-944, 2017. 10.1109\/cvpr.2017.106","key":"28","DOI":"10.1109\/CVPR.2017.106"},{"unstructured":"[29] H. Li, P. Xiong, J. An, and L. Wang, \u201cPyramid attention network for semantic segmentation,\u201d arXiv:1805.10180, 2018.","key":"29"},{"doi-asserted-by":"crossref","unstructured":"[30] C. Wang, H. Liao, I. Yeh, Y. Wu, P. Chen, and J. Hsieh, \u201cCSPNet: A new backbone that can enhance learning capability of cnn,\u201d arXiv preprint arXiv:1911.11929, 2019.","key":"30","DOI":"10.1109\/CVPRW50498.2020.00203"},{"doi-asserted-by":"crossref","unstructured":"[31] J. Hu, L. Shen, and G. Sun, \u201cSqueeze-and-excitation networks,\u201d Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp.7132-7141, 2018. 10.1109\/cvpr.2018.00745","key":"31","DOI":"10.1109\/CVPR.2018.00745"},{"unstructured":"[32] X. Li, W. Wang, X. Hu, and J. Yang, \u201cSelective kernel networks,\u201d arXiv preprint arXiv:1903.06586, 2019.","key":"32"},{"doi-asserted-by":"crossref","unstructured":"[33] Z. Huang, X. Wang, L. Huang, C. Huang, Y. Wei, and W. Liu, \u201cCCNet: criss-cross attention for semantic segmentation,\u201d Proc. IEEE\/CVF Int. Conf. Comput. Vis., pp.603-612, 2019. 10.1109\/iccv.2019.00069","key":"33","DOI":"10.1109\/ICCV.2019.00069"},{"doi-asserted-by":"crossref","unstructured":"[34] X. Li, Z. Zhong, J. Wu, Y. Yang, Z. Lin, and H. Liu, \u201cExpectation-maximization attention networks for semantic segmentation,\u201d Proc. IEEE\/CVF Int. Conf. Comput. Vis., pp.9167-9176, 2019. 10.1109\/iccv.2019.00926","key":"34","DOI":"10.1109\/ICCV.2019.00926"},{"doi-asserted-by":"crossref","unstructured":"[35] S. Woo, J. Park, J.-Y. Lee, and I.S. Kweon, \u201cCBAM: convolutional block attention module,\u201d Proc. Eur. Conf. Comput. Vis., pp.3-19, 2018. 10.1007\/978-3-030-01234-2_1","key":"35","DOI":"10.1007\/978-3-030-01234-2_1"},{"doi-asserted-by":"crossref","unstructured":"[36] A.G. Roy, N. Navab, and C. Wachinger, \u201cConcurrent spatial and channel \u2018squeeze & excitation\u2019 in fully convolutional networks,\u201d Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Interv., pp.421-429, 2018. 10.1007\/978-3-030-00928-1_48","key":"36","DOI":"10.1007\/978-3-030-00928-1_48"},{"unstructured":"[37] Y. Liu, Z. Shao, Y. Teng, and N. Hoffmann, \u201cNAM: normalization-based attention module,\u201d arXiv:2111.12419, 2021.","key":"37"},{"doi-asserted-by":"crossref","unstructured":"[38] Y. Li, Q. Hou, Z. Zheng, M.-M. Cheng, J. Yang, and X. Li, \u201cLarge selective kernel network for remote sensing object detection,\u201d arXiv:2303.09030, 2023.","key":"38","DOI":"10.1109\/ICCV51070.2023.01540"},{"unstructured":"[39] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A.N. Gomez, \u0141. Kaiser, and I. Polosukhin, \u201cAttention is all you need,\u201d Adv. Neural Inf. Process. Syst., vol.30, 2017.","key":"39"},{"unstructured":"[40] L. Yang, R.Y. Zhang, L. Li, and X. Xie, \u201cSimAM: a simple, parameter-free attention module for convolutional neural networks,\u201d Proc. Int. Conf. Mach. Learn., pp.11863-11874, 2021.","key":"40"},{"unstructured":"[41] Y. Liu, Z. Shao, and N. Hoffmann, \u201cGlobal attention mechanism: retain information to enhance channel-spatial interactions,\u201d arXiv:2112.05561, 2021.","key":"41"},{"doi-asserted-by":"crossref","unstructured":"[42] Y. Cao, J. Xu, S. Lin, F. Wei, and H. Hu, \u201cGCNet: non-local networks meet squeeze-excitation networks and beyond,\u201d Proc. IEEE\/CVF Int. Conf. Comput. Vis. Workshops, pp.1971-1980, 2019. 10.1109\/iccvw.2019.00246","key":"42","DOI":"10.1109\/ICCVW.2019.00246"},{"doi-asserted-by":"crossref","unstructured":"[43] X. Wang, R. Girshick, A. Gupta, and K. He, \u201cNon-local neural networks,\u201d Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp.7794-7803, 2018. 10.1109\/cvpr.2018.00813","key":"43","DOI":"10.1109\/CVPR.2018.00813"},{"doi-asserted-by":"crossref","unstructured":"[44] O. Zendel, M. Murschitz, M. Zeilinger, D. Steininger, S. Abbasi, and C. Beleznai, \u201cRailsem19: A dataset for semantic rail scene understanding,\u201d Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp.1221-1229, 2019. 10.1109\/cvprw.2019.00161","key":"44","DOI":"10.1109\/CVPRW.2019.00161"},{"doi-asserted-by":"publisher","unstructured":"[45] M. Braun, S. Krebs, F. Flohr, and D.M. Gavrila, \u201cEurocity persons: A novel benchmark for person detection in traffic scenes,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.41, no.8, pp.1844-1861, Aug. 2019. 10.1109\/tpami.2019.2897684","key":"45","DOI":"10.1109\/TPAMI.2019.2897684"},{"doi-asserted-by":"crossref","unstructured":"[46] H. Gupta, O. Kotlyar, H. Andreasson, and A.J. Lilienthal, \u201cRobust object detection in challenging weather conditions,\u201d Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp.7523-7532, Jan. 2024. 10.1109\/wacv57701.2024.00735","key":"46","DOI":"10.1109\/WACV57701.2024.00735"},{"unstructured":"[47] Shenggan, \u201cBccd_dataset.\u201d https:\/\/github.com\/Shenggan\/BCCD_Dataset, accessed Dec. 2023.","key":"47"},{"doi-asserted-by":"publisher","unstructured":"[48] W. Yu, G. Cheng, M. Wang, Y. Yao, X. Xie, X. Yao, and J. Han, \u201cMar20: A benchmark for military aircraft recognition in remote sensing images,\u201d National Remote Sensing Bulletin (China), vol.27, no.12, pp.2688-2696, 2023. 10.11834\/jrs.20222139","key":"48","DOI":"10.11834\/jrs.20222139"},{"unstructured":"[49] \u201cSelf-driving cars dataset.\u201d https:\/\/universe.robo-flow.com\/selfdriving-car-qtywx\/self-driving-cars-lfjou, accessed Dec. 2023.","key":"49"},{"unstructured":"[50] M. Everingham, L. Van Gool, C.K.I. Williams, J. Winn, and A. Zisserman, \u201cThe PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results.\u201d http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2012\/workshop\/index.html, accessed Dec. 2023.","key":"50"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E109.D\/1\/E109.D_2024EDP7318\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,3]],"date-time":"2026-01-03T03:25:52Z","timestamp":1767410752000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E109.D\/1\/E109.D_2024EDP7318\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,1]]},"references-count":50,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2024edp7318","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"type":"print","value":"0916-8532"},{"type":"electronic","value":"1745-1361"}],"subject":[],"published":{"date-parts":[[2026,1,1]]},"article-number":"2024EDP7318"}}