{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,12,28]],"date-time":"2023-12-28T19:53:51Z","timestamp":1703793231696},"reference-count":25,"publisher":"Fuji Technology Press Ltd.","issue":"6","funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["JP22K12082"],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JRM","J. Robot. Mechatron."],"published-print":{"date-parts":[[2023,12,20]]},"abstract":"We are exploring the use of semantic scene understanding in autonomous navigation for the Tsukuba Challenge. However, manually creating a comprehensive dataset that covers various outdoor scenes with time and weather variations to ensure high accuracy in semantic segmentation is onerous. Therefore, we propose modifications to the model and backbone of semantic segmentation, along with data augmentation techniques. The data augmentation techniques, including the addition of virtual shadows, histogram matching, and style transformations, aim to improve the representation of variations in shadow presence and color tones. In our evaluation using images from the Tsukuba Challenge course, we achieved the highest accuracy by switching the model to PSPNet and changing the backbone to ResNeXt. Furthermore, the adaptation of shadow and histogram proved effective for critical classes in robot navigation, such as road, sidewalk, and terrain. In particular, the combination of histogram matching and shadow application demonstrated effectiveness for data not included in the base training dataset.<\/jats:p>","DOI":"10.20965\/jrm.2023.p1450","type":"journal-article","created":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T15:03:14Z","timestamp":1702998194000},"page":"1450-1459","source":"Crossref","is-referenced-by-count":1,"title":["Data Augmentation for Semantic Segmentation Using a Real Image Dataset Captured Around the Tsukuba City Hall"],"prefix":"10.20965","volume":"35","author":[{"given":"Yuriko","family":"Ueda","sequence":"first","affiliation":[{"name":"Department of Computer Science, Graduate School of Science and Technology, Meiji University, 1-1-1 Higashimita, Tama-ku, Kawasaki, Kanagawa 214-8571, Japan"}]},{"ORCID":"http:\/\/orcid.org\/0009-0000-3802-4866","authenticated-orcid":true,"given":"Miho","family":"Adachi","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Graduate School of Science and Technology, Meiji University, 1-1-1 Higashimita, Tama-ku, Kawasaki, Kanagawa 214-8571, Japan"}]},{"given":"Junya","family":"Morioka","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Graduate School of Science and Technology, Meiji University, 1-1-1 Higashimita, Tama-ku, Kawasaki, Kanagawa 214-8571, Japan"}]},{"given":"Marin","family":"Wada","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Graduate School of Science and Technology, Meiji University, 1-1-1 Higashimita, Tama-ku, Kawasaki, Kanagawa 214-8571, Japan"}]},{"ORCID":"http:\/\/orcid.org\/0000-0001-9450-4493","authenticated-orcid":true,"given":"Ryusuke","family":"Miyamoto","sequence":"additional","affiliation":[{"name":"Department of Computer Science, School of Science and Technology, Meiji University, 1-1-1 Higashimita, Tama-ku, Kawasaki, Kanagawa 214-8571, Japan"}]}],"member":"8550","published-online":{"date-parts":[[2023,12,20]]},"reference":[{"key":"key-10.20965\/jrm.2023.p1450-1","doi-asserted-by":"crossref","unstructured":"L. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille, \u201cDeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs,\u201d IEEE Trans. Pattern Anal. Mach. Intell., Vol.40, No.4, pp. 834-848, 2018. https:\/\/doi.org\/10.1109\/TPAMI.2017.2699184","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"key-10.20965\/jrm.2023.p1450-2","doi-asserted-by":"crossref","unstructured":"J. Xu, Z. Xiong, and S. P. Bhattacharyya, \u201cPIDNet: A Real-time Semantic Segmentation Network Inspired from PID Controller,\u201d Proc. of IEEE Conf. Comput. Vis. Pattern Recognit., pp. 19529-19539, 2023. https:\/\/doi.org\/10.1109\/CVPR52729.2023.01871","DOI":"10.1109\/CVPR52729.2023.01871"},{"key":"key-10.20965\/jrm.2023.p1450-3","doi-asserted-by":"crossref","unstructured":"H. Zhao, X. Qi, X. Shen, J. Shi, and J. Jia, \u201cICNet for Real-Time Semantic Segmentation on High-Resolution Images,\u201d Proc. of European Conf. Comput. Vis., pp. 418-434, 2018. https:\/\/doi.org\/10.1007\/978-3-030-01219-9_25","DOI":"10.1007\/978-3-030-01219-9_25"},{"key":"key-10.20965\/jrm.2023.p1450-4","doi-asserted-by":"crossref","unstructured":"H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, \u201cPyramid scene parsing network,\u201d Proc. of IEEE Conf. Comput. Vis. Pattern Recognit., pp. 2881-2890, 2017. https:\/\/doi.org\/10.1109\/CVPR.2017.660","DOI":"10.1109\/CVPR.2017.660"},{"key":"key-10.20965\/jrm.2023.p1450-5","doi-asserted-by":"crossref","unstructured":"M. Adachi, S. Shatari, and R. Miyamoto, \u201cVisual Navigation Using a Webcam Based on Semantic Segmentation for Indoor Robots,\u201d Proc. of SITIS, 2019. https:\/\/doi.org\/10.1109\/SITIS.2019.00015","DOI":"10.1109\/SITIS.2019.00015"},{"key":"key-10.20965\/jrm.2023.p1450-6","doi-asserted-by":"crossref","unstructured":"M. Adachi, K. Honda, and R. Miyamoto, \u201cTurning at Intersections Using Virtual LiDAR Signals Obtained from a Segmentation Result,\u201d J. Robot. Mechatron., Vol.35, No.2, pp. 347-361, 2023. https:\/\/doi.org\/10.20965\/jrm.2023.p0347","DOI":"10.20965\/jrm.2023.p0347"},{"key":"key-10.20965\/jrm.2023.p1450-7","doi-asserted-by":"crossref","unstructured":"M. Adachi and R. Miyamoto, \u201cModel-Based Estimation of Road Direction in Urban Scenes Using Virtual LiDAR Signals,\u201d Proc. of IEEE Int. Conf. on Systems, Man, and Cybernetics, 2020. https:\/\/doi.org\/10.1109\/SMC42975.2020.9282925","DOI":"10.1109\/SMC42975.2020.9282925"},{"key":"key-10.20965\/jrm.2023.p1450-8","doi-asserted-by":"crossref","unstructured":"R. Miyamoto, Y. Nakamura, M. Adachi, T. Nakajima, H. Ishida, K. Kojima, R. Aoki, T. Oki, and S. Kobayashi, \u201cVision-Based Road-Following Using Results of Semantic Segmentation for Autonomous Navigation,\u201d Proc. of ICCE Berlin, pp. 194-199, 2019. https:\/\/doi.org\/10.1109\/ICCE-Berlin47944.2019.8966198","DOI":"10.1109\/ICCE-Berlin47944.2019.8966198"},{"key":"key-10.20965\/jrm.2023.p1450-9","doi-asserted-by":"crossref","unstructured":"R. Miyamoto, M. Adachi, H. Ishida, T. Watanabe, K. Matsutani, H. Komatsuzaki, S. Sakata, R. Yokota, and S. Kobayashi, \u201cVisual Navigation Based on Semantic Segmentation Using Only a Monocular Camera as an External Sensor,\u201d J. Robot. Mechatron., Vol.32, No.6, pp. 1137-1153, 2020. https:\/\/doi.org\/10.20965\/jrm.2020.p1137","DOI":"10.20965\/jrm.2020.p1137"},{"key":"key-10.20965\/jrm.2023.p1450-10","doi-asserted-by":"crossref","unstructured":"M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele, \u201cThe Cityscapes Dataset for Semantic Urban Scene Understanding,\u201d Proc. of IEEE Conf. Comput. Vis. Pattern Recognit., 2016. https:\/\/doi.org\/10.1109\/CVPR.2016.350","DOI":"10.1109\/CVPR.2016.350"},{"key":"key-10.20965\/jrm.2023.p1450-11","doi-asserted-by":"crossref","unstructured":"A. Geiger, P. Lenz, and R. Urtasun, \u201cAre we ready for Autonomous Driving? The KITTI Vision Benchmark Suite,\u201d Proc. of IEEE Conf. Comput. Vis. Pattern Recognit., 2012. https:\/\/doi.org\/10.1109\/CVPR.2012.6248074","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"key-10.20965\/jrm.2023.p1450-12","doi-asserted-by":"crossref","unstructured":"Y. Liao, J. Xie, and A. Geiger, \u201cKITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D,\u201d IEEE Trans. Pattern Anal. Mach. Intell., Vol.45, No.3, pp. 3292-3310, 2022. https:\/\/doi.org\/10.1109\/TPAMI.2022.3179507","DOI":"10.1109\/TPAMI.2022.3179507"},{"key":"key-10.20965\/jrm.2023.p1450-13","doi-asserted-by":"crossref","unstructured":"R. Miyamoto, M. Adachi, Y. Nakamura, T. Nakajima, H. Ishida, and S. Kobayashi, \u201cAccuracy Improvement of Semantic Segmentation Using Appropriate Datasets for Robot Navigation,\u201d Proc. of CoDIT, pp. 1610-1615, 2019. https:\/\/doi.org\/10.1109\/CoDIT.2019.8820616","DOI":"10.1109\/CoDIT.2019.8820616"},{"key":"key-10.20965\/jrm.2023.p1450-14","doi-asserted-by":"crossref","unstructured":"Y. Takagi and Y. Ji, \u201cMotion Control of Mobile Robot for Snowy Environment-Performance Improvement of Semantic Segmentation by Using GAN in Snow-covered Road,\u201d Proc. of the 2022 JMSE Conf. on Robotics and Mechatronics, 2022. https:\/\/doi.org\/10.1299\/jsmermd.2022.2P1-F06","DOI":"10.1299\/jsmermd.2022.2P1-F06"},{"key":"key-10.20965\/jrm.2023.p1450-15","doi-asserted-by":"crossref","unstructured":"J. Choi, T. Kim, and C. Kim, \u201cSelf-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentation,\u201d Proc. of IEEE Int. Conf. Comput. Vis., pp. 6830-6840, 2019. https:\/\/doi.org\/10.1109\/ICCV.2019.00693","DOI":"10.1109\/ICCV.2019.00693"},{"key":"key-10.20965\/jrm.2023.p1450-16","doi-asserted-by":"crossref","unstructured":"X. Huang and S. Belongie, \u201cArbitrary Style Transfer in Real-time with Adaptive Instance Normalization,\u201d Proc. of IEEE Int. Conf. Comput. Vis., pp. 1501-1510, 2017. https:\/\/doi.org\/10.1109\/ICCV.2017.167","DOI":"10.1109\/ICCV.2017.167"},{"key":"key-10.20965\/jrm.2023.p1450-17","doi-asserted-by":"crossref","unstructured":"P. Isola, J.-Y. Zhu, T. Zhou, and A. A. Efros, \u201cImage-to-Image Translation with Conditional Adversarial Networks,\u201d Proc. of IEEE Conf. Comput. Vis. Pattern Recognit., 2017. https:\/\/doi.org\/10.1109\/CVPR.2017.632","DOI":"10.1109\/CVPR.2017.632"},{"key":"key-10.20965\/jrm.2023.p1450-18","unstructured":"T. Inoue, Y. Tomita, K. Gakuta, E. Yamada, A. Kariya, M. Kinosada, Y. Kitaide, and R. Miyamoto, \u201cImproving Classification Accuracy of Real Images by Style Transfer Utilized on Synthetic Training Data,\u201d Proc. of Int. Workshop on Smart Info-Media Systems in Asia, pp. 71-76, 2023. https:\/\/doi.org\/10.34385\/proc.77.RS3-2"},{"key":"key-10.20965\/jrm.2023.p1450-19","doi-asserted-by":"crossref","unstructured":"M. Wada, Y. Ueda, M. Adachi, and R. Miyamoto, \u201cDataset Generation for Semantic Segmentation from 3D Scanned Data Considering Domain Gap,\u201d Proc. of CoDIT, pp. 1711-1716, 2023. https:\/\/doi.org\/10.1109\/CODIT58514.2023.10284381","DOI":"10.1109\/CoDIT58514.2023.10284381"},{"key":"key-10.20965\/jrm.2023.p1450-20","doi-asserted-by":"crossref","unstructured":"E. Riba, D. Mishkin, D. Ponsa, E. Rublee, and G. Bradski, \u201cKornia: an Open Source Differentiable Computer Vision Library for PyTorch,\u201d Proc. of IEEE Winter Conf. Appl. Comput. Vis., pp. 3663-3672, 2020. https:\/\/doi.org\/10.1109\/WACV45572.2020.9093363","DOI":"10.1109\/WACV45572.2020.9093363"},{"key":"key-10.20965\/jrm.2023.p1450-21","doi-asserted-by":"crossref","unstructured":"A. Fournier, D. Fussell, and L. Carpenter, \u201cComputer Rendering of Stochastic Models,\u201d Commun. ACM, Vol.25, No.6, pp. 371-384, 1982. https:\/\/doi.org\/10.1145\/358523.358553","DOI":"10.1145\/358523.358553"},{"key":"key-10.20965\/jrm.2023.p1450-22","unstructured":"R. C. Gonzalez and R. E. Woods, \u201cDigital Image Processing (3rd Edition),\u201d Prentice-Hall, Inc., USA, 2006."},{"key":"key-10.20965\/jrm.2023.p1450-23","doi-asserted-by":"crossref","unstructured":"M. Kim and H. Byun, \u201cLearning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation,\u201d Proc. of IEEE Conf. Comput. Vis. Pattern Recognit., pp. 12972-12981, 2020. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01299","DOI":"10.1109\/CVPR42600.2020.01299"},{"key":"key-10.20965\/jrm.2023.p1450-24","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, and J. Sun, \u201cDeep Residual Learning for Image Recognition,\u201d Proc. of IEEE Conf. Comput. Vis. Pattern Recognit., pp. 770-778, 2016. https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"key-10.20965\/jrm.2023.p1450-25","doi-asserted-by":"crossref","unstructured":"S. Xie, R. Girshick, P. Doll\u00e1r, Z. Tu, and K. He, \u201cAggregated Residual Transformations for Deep Neural Networks,\u201d Proc. of IEEE Conf. Comput. Vis. Pattern Recognit., pp. 5987-5995, 2017. https:\/\/doi.org\/10.1109\/CVPR.2017.634","DOI":"10.1109\/CVPR.2017.634"}],"container-title":["Journal of Robotics and Mechatronics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.fujipress.jp\/main\/wp-content\/themes\/Fujipress\/hyosetsu.php?ppno=ROBOT003500060004","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T15:04:10Z","timestamp":1702998250000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.fujipress.jp\/jrm\/rb\/robot003500061450"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,20]]},"references-count":25,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2023,12,20]]},"published-print":{"date-parts":[[2023,12,20]]}},"URL":"https:\/\/doi.org\/10.20965\/jrm.2023.p1450","relation":{},"ISSN":["1883-8049","0915-3942"],"issn-type":[{"value":"1883-8049","type":"electronic"},{"value":"0915-3942","type":"print"}],"subject":[],"published":{"date-parts":[[2023,12,20]]}}}