{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T20:48:45Z","timestamp":1775594925267,"version":"3.50.1"},"reference-count":25,"publisher":"Fuji Technology Press Ltd.","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JRM","J. Robot. Mechatron."],"published-print":{"date-parts":[[2020,6,20]]},"abstract":"<jats:p>The frequency of pedestrian traffic accidents continues to increase in Japan. Thus, a driver assistance system is expected to reduce the number of accidents. However, it is difficult for the current environmental recognition sensors to detect crossing pedestrians when turning at intersections, owing to the field of view and the cost. We propose a pedestrian detection system that utilizes surround-view fisheye cameras with a wide field of view. The system can be realized at low cost if the fisheye cameras are already equipped. It is necessary to detect the positioning of pedestrians accurately because more precise prediction of future collision points is required at intersections. Stereo vision is suitable for this purpose. However, there are some concerns regarding realizing stereo vision using fisheye cameras due to the distortion of the lens, asynchronous capturing, and fluctuating camera postures. As a countermeasure, we propose a novel method combining various machine-learning techniques. The D-Brief with histogram of oriented gradients and normalized cross-correlation are combined by a support-vector machine for stereo matching. A random forest was adopted to discriminate the pedestrians from noise in the 3D reconstructed point cloud. We evaluated this for images of crossing pedestrians at actual intersections. A tracking rate of 96.0% was achieved as the evaluation result. It was verified that this algorithm can accurately detect a pedestrian with an average position error of 0.17 m.<\/jats:p>","DOI":"10.20965\/jrm.2020.p0494","type":"journal-article","created":{"date-parts":[[2020,6,19]],"date-time":"2020-06-19T15:05:05Z","timestamp":1592579105000},"page":"494-502","source":"Crossref","is-referenced-by-count":7,"title":["Stereo Vision by Combination of Machine-Learning Techniques for Pedestrian Detection at Intersections Utilizing Surround-View Cameras"],"prefix":"10.20965","volume":"32","author":[{"given":"Tokihiko","family":"Akita","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuji","family":"Yamauchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hironobu","family":"Fujiyoshi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"name":"Toyota Technological Institute 2-12-1 Hisakata, Tempaku-ku, Nagoya, Aichi 468-8511, Japan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"name":"Chubu University 1200 Matsumoto-cho, Kasugai, Aichi 487-8501, Japan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"8550","published-online":{"date-parts":[[2020,6,20]]},"reference":[{"key":"key-10.20965\/jrm.2020.p0494-1","doi-asserted-by":"crossref","unstructured":"Y. Matsui et al., \u201cFeatures of fatal pedestrian injuries in vehicle-to-pedestrian accidents in Japan,\u201d SAE Int. J. of Transportation Safety, Vol.1, pp. 297-308, 2013.","DOI":"10.4271\/2013-01-0777"},{"key":"key-10.20965\/jrm.2020.p0494-2","unstructured":"Y. Matsui et al., \u201cCar-to-pedestrian contact situations in near-miss incidents and real-world accidents in Japan,\u201d Proc. of the 22nd Int. Technical Conf. on the Enhanced Safety of Vehicles (ESV), 11-0164, 2011."},{"key":"key-10.20965\/jrm.2020.p0494-3","unstructured":"T. Hagiwara, H. Hamaoka, D. Uchibori, and K. Suzuki, \u201cInvestigation of the driver\u2019s avoidance behavior caused by the conflicts with the pedestrian\/cyclists at night at an urban signalized intersection,\u201d Proc. of JSAE Annual Congresses in Spring, 188-20105256, 2010 (in Japanese)."},{"key":"key-10.20965\/jrm.2020.p0494-4","unstructured":"T. Hagiwara, \u201cTraffic safety countermeasure utilizing ICT the 3rd,\u201d Nikkei Electronics 2012.4.2, pp. 90-96, 2012 (in Japanese)."},{"key":"key-10.20965\/jrm.2020.p0494-5","unstructured":"F. Mroz and T. P. Breckon, \u201cAn empirical comparison of real-time dense stereo approaches for use in the automotive environment,\u201d EURASIP J. on Image and Video Processing, Vol.2012, 13, 2012."},{"key":"key-10.20965\/jrm.2020.p0494-6","unstructured":"K. Saneyoshi, K. Hanawa, Y. Sogawa, and K. Arai, \u201cStereo Image Recognition System for Drive Assist,\u201d PRMU, Vol.97, No.41, pp. 39-46, 1997 (in Japanese)."},{"key":"key-10.20965\/jrm.2020.p0494-7","unstructured":"J. Hariyono, V. D. Hoang, and K. H. Jo, \u201cMoving Object Localization Using Optical Flow for Pedestrian Detection from a Moving Vehicle,\u201d The Scientific World J., Vol.2014, 196415, 2014."},{"key":"key-10.20965\/jrm.2020.p0494-8","doi-asserted-by":"crossref","unstructured":"N. Hatakeyama, T. Sasaki, K. Terabayashi, M. Funato, and M. Jindai, \u201cPosition and Posture Measurement Method of the Omnidirectional Camera Using Identification Markers,\u201d J. Robot. Mechatron., Vol.30, No.3, pp. 354-362, 2018.","DOI":"10.20965\/jrm.2018.p0354"},{"key":"key-10.20965\/jrm.2020.p0494-9","unstructured":"M. Yahiaoui et al., \u201cFisheyeMODNet: Moving Object detection on Surround-view Cameras for Autonomous Driving,\u201d Proc. of the 21st Irish Machine Vision and Image Processing Conf. (IMVIP 2019), 33, 2019."},{"key":"key-10.20965\/jrm.2020.p0494-10","doi-asserted-by":"crossref","unstructured":"S. Kamijo, K. Fujimura, and Y. Shibayama, \u201cPedestrian Detection Algorithm for On-board Cameras of Multi View Angles,\u201d IEEE Intelligent Vehicles Symp., pp. 973-980, 2010.","DOI":"10.1109\/IVS.2010.5548113"},{"key":"key-10.20965\/jrm.2020.p0494-11","unstructured":"T. Ito, Y. Tanaka, and M. H. Sofian, \u201cCrossing Pedestrian Detection Using Deep Learning by On-board Camera,\u201d Proc. of JSAE Annual Congresses in Spring, 20184569, 2018 (in Japanese)."},{"key":"key-10.20965\/jrm.2020.p0494-12","doi-asserted-by":"crossref","unstructured":"A. Seki and M. Okutomi, \u201cSimultaneous Optimization of Structure and Motion in Dynamic Scenes Using Unsynchronized Stereo Cameras,\u201d Proc. of 2007 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 1-8, 2007.","DOI":"10.1109\/CVPR.2007.383160"},{"key":"key-10.20965\/jrm.2020.p0494-13","doi-asserted-by":"crossref","unstructured":"A. Ohashi et al., \u201cFisheye stereo camera using equirectangular images,\u201d Proc. of 2016 11th France-Japan 9th Europe-Asia Congress on Mechatronics (MECATRONICS) \/17th Int. Conf. on Research and Education in Mechatronics (REM), pp. 284-289, 2016.","DOI":"10.1109\/MECATRONICS.2016.7547156"},{"key":"key-10.20965\/jrm.2020.p0494-14","doi-asserted-by":"crossref","unstructured":"B. Khomutenko et al., \u201cDirect fisheye stereo correspondence using enhanced unified camera model and semi-global matching algoirthm,\u201d Proc. of 2016 14th Int. Conf. on Control, Automation, Robotics and Vision (ICARCV), pp. 1-6, 2016.","DOI":"10.1109\/ICARCV.2016.7838761"},{"key":"key-10.20965\/jrm.2020.p0494-15","unstructured":"Y. Kanazawa and K. Kanatani, \u201cDetection of Feature Points for Computer Vision,\u201d J. of the Institute of Electronics, Information and Communication Engineers, Vol.87, No.12, pp. 1043-1048, 2004 (in Japanese)."},{"key":"key-10.20965\/jrm.2020.p0494-16","unstructured":"E. Rosten and T. Drummond, \u201cFusing Points and Lines for High Performance Tracking,\u201d Proc. of 10th IEEE Int. Conf. on Computer Vision (ICCV\u201905), Vol.2, pp. 1508-1515, 2005."},{"key":"key-10.20965\/jrm.2020.p0494-17","unstructured":"T. Akita, \u201cPedestrian detection system while turning at intersection by surround monitor camera,\u201d Proc. of the 3rd Int. Symp. on Future Active Safety Technology Toward Zero Traffic Accidents (FAST-zero\u201915), pp. 45-51, 2015."},{"key":"key-10.20965\/jrm.2020.p0494-18","unstructured":"K. Ito, T. Takahashi, and T. Aoki, \u201cA Study of a High-Accuracy Image Matching Method,\u201d The 25th Signal Processing Symp., pp. 547-552, 2010 (in Japanese)."},{"key":"key-10.20965\/jrm.2020.p0494-19","doi-asserted-by":"crossref","unstructured":"D. G. Lowe, \u201cDistinctive image features from scale-invariant keypoints,\u201d Int. J. of Computer Vision, Vol.60, No.2, pp. 91-110, 2004.","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"key-10.20965\/jrm.2020.p0494-20","unstructured":"H. Fujiyoshi, \u201cImage Local Feature amount SIFT and subsequent approach,\u201d Tutorial in MIRU2013, 2013 (in Japanese)."},{"key":"key-10.20965\/jrm.2020.p0494-21","unstructured":"T. Trzcinski and V. Lepetit, \u201cEfficient Discriminative Projections for Compact Binary Descriptors,\u201d ECCV 2012 Lecture Notes in Computer Science, Vol.7572, pp. 228-242, 2012."},{"key":"key-10.20965\/jrm.2020.p0494-22","unstructured":"W. Sato and Y. Yasumura, \u201cProbabilistic Stereo Matching Based on Machine Learning,\u201d The IEICE General Conf. 2014, p. 185, 2014 (in Japanese)."},{"key":"key-10.20965\/jrm.2020.p0494-23","unstructured":"J. Zbontar and Y. LeCun, \u201cStereo Matching by Training a Convolutional Neural Network to Compare Image Patches,\u201d J. of Machine Learning Research, Vol.17, pp. 1-32, 2016."},{"key":"key-10.20965\/jrm.2020.p0494-24","unstructured":"T. Akita, S. Yamamoto, Y. Yamauchi, and H. Fujiyoshi, \u201cApplication of stereo matching utilizing machine learning to surround view cameras,\u201d Proc. in JSAE 2016, 2016 (in Japanese)."},{"key":"key-10.20965\/jrm.2020.p0494-25","doi-asserted-by":"crossref","unstructured":"N. Dalal and B. Triggs, \u201cHistograms of Oriented Gradients for Human Detection,\u201d Proc. of IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, Vol.1, pp. 886-893, 2005.","DOI":"10.1109\/CVPR.2005.177"}],"container-title":["Journal of Robotics and Mechatronics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.fujipress.jp\/main\/wp-content\/themes\/Fujipress\/phyosetsu.php?ppno=ROBOT003200030002","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T00:56:25Z","timestamp":1723078585000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.fujipress.jp\/jrm\/rb\/robot003200030494"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,20]]},"references-count":25,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2020,6,20]]},"published-print":{"date-parts":[[2020,6,20]]}},"URL":"https:\/\/doi.org\/10.20965\/jrm.2020.p0494","relation":{},"ISSN":["1883-8049","0915-3942"],"issn-type":[{"value":"1883-8049","type":"electronic"},{"value":"0915-3942","type":"print"}],"subject":[],"published":{"date-parts":[[2020,6,20]]}}}