{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T05:01:18Z","timestamp":1777179678253,"version":"3.51.4"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2021,5,22]],"date-time":"2021-05-22T00:00:00Z","timestamp":1621641600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,5,22]],"date-time":"2021-05-22T00:00:00Z","timestamp":1621641600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100007120","name":"King Mongkut\u2019s Institute of Technology Ladkrabang","doi-asserted-by":"publisher","award":["2564-02-06-002"],"award-info":[{"award-number":["2564-02-06-002"]}],"id":[{"id":"10.13039\/501100007120","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2022,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Evaluation of car damages from an accident is one of the most important processes in the car insurance business. Currently, it still needs a manual examination of every basic part. It is expected that a smart device will be able to do this evaluation more efficiently in the future. In this study, we evaluated and compared five deep learning algorithms for semantic segmentation of car parts. The baseline reference algorithm was Mask R-CNN, and the other algorithms were HTC, CBNet, PANet, and GCNet. Runs of instance segmentation were conducted with those five algorithms. HTC with ResNet-50 was the best algorithm for instance segmentation on various kinds of cars such as sedans, trucks, and SUVs. It achieved a mean average precision at 55.2 on our original data set, that assigned different labels to the left and right sides and 59.1 when a single label was assigned to both sides. In addition, the models from every algorithm were tested for robustness, by running them on images of parts, in a real environment with various weather conditions, including snow, frost, fog and various lighting conditions. GCNet was the most robust; it achieved a mean performance under corruption, mPC = 35.2, and a relative degradation of performance on corrupted data, compared to clean data (rPC), of 64.4%, when left and right sides were assigned different labels, and mPC = 38.1 and rPC =<jats:inline-formula><jats:alternatives><jats:tex-math>$$69.6\\%$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\"><mml:mrow><mml:mn>69.6<\/mml:mn><mml:mo>%<\/mml:mo><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>when left- and right-side parts were considered the same part. The findings from this study may directly benefit developers of automated car damage evaluation system in their quest for the best design.<\/jats:p>","DOI":"10.1007\/s40747-021-00397-8","type":"journal-article","created":{"date-parts":[[2021,5,22]],"date-time":"2021-05-22T11:02:31Z","timestamp":1621681351000},"page":"3613-3625","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":49,"title":["Evaluation of deep learning algorithms for semantic segmentation of car parts"],"prefix":"10.1007","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8359-9888","authenticated-orcid":false,"given":"Kitsuchart","family":"Pasupa","sequence":"first","affiliation":[]},{"given":"Phongsathorn","family":"Kittiworapanya","sequence":"additional","affiliation":[]},{"given":"Napasin","family":"Hongngern","sequence":"additional","affiliation":[]},{"given":"Kuntpong","family":"Woraratpanya","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,5,22]]},"reference":[{"issue":"4","key":"397_CR1","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1109\/MITS.2014.2343262","volume":"6","author":"P Handel","year":"2014","unstructured":"Handel P, Skog I, Wahlstrom J, Bonawiede F, Welch R, Ohlsson J et al (2014) Insurance telematics: opportunities and challenges with the smartphone solution. IEEE Intell Transp Syst Mag 6(4):57\u201370","journal-title":"IEEE Intell Transp Syst Mag"},{"key":"397_CR2","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1016\/j.proeng.2015.01.436","volume":"100","author":"S Husnjak","year":"2015","unstructured":"Husnjak S, Perakovi\u0107 D, Forenbacher I, Mumdziev M (2015) Telematics system in usage based motor insurance. Procedia Eng 100:816\u2013825","journal-title":"Procedia Eng"},{"issue":"8","key":"397_CR3","doi-asserted-by":"publisher","first-page":"1738","DOI":"10.1109\/JPROC.2019.2918951","volume":"107","author":"Z Zhou","year":"2019","unstructured":"Zhou Z, Chen X, Li E, Zeng L, Luo K, Zhang J (2019) Edge intelligence: paving the last mile of artificial intelligence with edge computing. Proc IEEE 107(8):1738\u20131762","journal-title":"Proc IEEE"},{"issue":"1","key":"397_CR4","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1109\/COMST.2017.2762345","volume":"20","author":"J Ni","year":"2018","unstructured":"Ni J, Zhang K, Lin X, Shen X (2018) Securing Fog computing for internet of things applications: challenges and solutions. IEEE Commun Surv Tutor 20(1):601\u2013628","journal-title":"IEEE Commun Surv Tutor"},{"issue":"5","key":"397_CR5","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1109\/JIOT.2016.2579198","volume":"3","author":"W Shi","year":"2016","unstructured":"Shi W, Cao J, Zhang Q, Li Y, Xu L (2016) Edge computing: vision and challenges. IEEE Internet Things J 3(5):637\u2013646","journal-title":"IEEE Internet Things J"},{"key":"397_CR6","unstructured":"Papers with Code\u2013COCO test-dev Benchmark (Instance Segmentation) (2020) https:\/\/paperswithcode.com\/sota\/instance-segmentation-on-coco. Accessed 1 Nov 2020"},{"issue":"9","key":"397_CR7","doi-asserted-by":"publisher","first-page":"1432","DOI":"10.3390\/electronics9091432","volume":"9","author":"A Velichko","year":"2020","unstructured":"Velichko A (2020) Neural network for low-memory IoT devices and MNIST image recognition using kernels based on logistic map. Electronics 9(9):1432","journal-title":"Electronics"},{"key":"397_CR8","unstructured":"Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T et\u00a0al (2017) MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861v1"},{"key":"397_CR9","doi-asserted-by":"crossref","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC (2018) MobileNetV2: inverted residuals and linear bottlenecks. arXiv:1801.04381v4","DOI":"10.1109\/CVPR.2018.00474"},{"key":"397_CR10","doi-asserted-by":"crossref","unstructured":"Tuli S, Basumatary N, Buyya R (2019) EdgeLens: deep learning based object detection in integrated IoT, Fog and cloud computing environments. In: Proceedings of the international conference on information systems and computer networks (ISCON), p 496\u2013502","DOI":"10.1109\/ISCON47742.2019.9036216"},{"key":"397_CR11","doi-asserted-by":"crossref","unstructured":"Zhang S, Li R, Dong X, Rosin P, Cai Z, Han X et\u00a0al (2019) Pose2Seg: detection free human instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), p 889\u2013898","DOI":"10.1109\/CVPR.2019.00098"},{"key":"397_CR12","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick R (2017) Mask R-CNN. In: Proceedings of the IEEE international conference on computer vision (ICCV), p 2980\u20132988","DOI":"10.1109\/ICCV.2017.322"},{"key":"397_CR13","unstructured":"Yi J, Tang H, Wu P, Liu B, Hoeppner DJ, Metaxas DN et\u00a0al (2019) Object-guided instance segmentation for biological images. arXiv:1911.09199v1"},{"key":"397_CR14","doi-asserted-by":"crossref","unstructured":"Lee Y, Park J (2019) CenterMask: real-time anchor-free instance segmentation. arXiv:1911.06667v6","DOI":"10.1109\/CVPR42600.2020.01392"},{"key":"397_CR15","doi-asserted-by":"crossref","unstructured":"Tian Z, Shen C, Chen H, He T (2019) FCOS: fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), p 9626\u20139635","DOI":"10.1109\/ICCV.2019.00972"},{"issue":"6","key":"397_CR16","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren S, He K, Girshick R, Sun J (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137\u20131149","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"397_CR17","doi-asserted-by":"crossref","unstructured":"Wang X, Kong T, Shen C, Jiang Y, Li L (2019) SOLO: segmenting objects by locations. arXiv:1912.04488v3","DOI":"10.1007\/978-3-030-58523-5_38"},{"key":"397_CR18","unstructured":"Wang X, Zhang R, Kong T, Li L, Shen C (2020) SOLOv2: dynamic and fast instance segmentation. ArXiv:2003.10152v3"},{"key":"397_CR19","doi-asserted-by":"crossref","unstructured":"Xie E, Sun P, Song X, Wang W, Liang D, Shen C et\u00a0al (2019) PolarMask: single shot instance segmentation with polar representation. arXiv:1909.13226v4","DOI":"10.1109\/CVPR42600.2020.01221"},{"key":"397_CR20","unstructured":"Wang S, Gong Y, Xing J, Huang L, Huang C, Hu W (2019) RDSNet: a new deep architecture for reciprocal object detection and instance segmentation. arXiV:1912.05070v1"},{"key":"397_CR21","doi-asserted-by":"crossref","unstructured":"Bolya D, Zhou C, Xiao F, Lee YJ (2019) Better Real-time Instance Segmentation. arxiv:1912.06218","DOI":"10.1109\/ICCV.2019.00925"},{"key":"397_CR22","doi-asserted-by":"crossref","unstructured":"Liu S, Qi L, Qin H, Shi J, Jia J (2018) Path aggregation network for instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), p 8759\u20138768","DOI":"10.1109\/CVPR.2018.00913"},{"key":"397_CR23","doi-asserted-by":"crossref","unstructured":"Huang Z, Huang L, Gong Y, Huang C, Wang X (2019) Mask scoring R-CNN. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), p 6402\u20136411","DOI":"10.1109\/CVPR.2019.00657"},{"key":"397_CR24","doi-asserted-by":"crossref","unstructured":"Chen H, Sun K, Tian Z, Shen C, Huang Y, Yan Y (2020) BlendMask: top-down meets bottom-up for instance segmentation. arXiv:2001.00309v3","DOI":"10.1109\/CVPR42600.2020.00860"},{"key":"397_CR25","doi-asserted-by":"crossref","unstructured":"Lu W, Lian X, Yuille A (2014) Parsing semantic parts of cars using graphical models and segment appearance consistency. arXiv:1406.2375v2","DOI":"10.5244\/C.28.118"},{"key":"397_CR26","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1016\/j.jvcir.2016.01.010","volume":"36","author":"Y Liu","year":"2016","unstructured":"Liu Y, Zou L, Li J, Yan J, Shi W, Deng D (2016) Segmentation by weighted aggregation and perceptual hash for pedestrian detection. J Vis Commun Image Represent 36:80\u201389","journal-title":"J Vis Commun Image Represent"},{"key":"397_CR27","doi-asserted-by":"crossref","unstructured":"Singh R, Ayyar MP, Sri Pavan TV, Gosain S, Shah RR (2019) Automating car insurance claims using deep learning techniques. In: Proceedings of the IEEE international conference on multimedia big data (BigMM), p 199\u2013207","DOI":"10.1109\/BigMM.2019.00-25"},{"key":"397_CR28","doi-asserted-by":"crossref","unstructured":"Dhieb N, Ghazzai H, Besbes H, Massoud Y (2019) A very deep transfer learning model for vehicle damage detection and localization. In: Proceedings of the international conference on microelectronics (ICM), p 158\u2013161","DOI":"10.1109\/ICM48031.2019.9021687"},{"key":"397_CR29","doi-asserted-by":"crossref","unstructured":"Patil K, Kulkarni M, Sriraman A, Karande S (2017) Deep learning based car damage classification. In: Proceedings of the IEEE international conference on machine learning and applications (ICMLA), p 50\u201354","DOI":"10.1109\/ICMLA.2017.0-179"},{"key":"397_CR30","doi-asserted-by":"crossref","unstructured":"Dwivedi M, Malik HS, Omkar SN, Monis EB, Khanna B, Samal SR et\u00a0al (2020) Deep learning-based car damage classification and detection. In: Advances in artificial intelligence and data engineering. Springer, p 207\u2013221","DOI":"10.1007\/978-981-15-3514-7_18"},{"issue":"2","key":"397_CR31","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Van Gool L, Williams CKI, Winn J, Zisserman A (2010) The PASCAL visual object classes (VOC) challenge. Int J Comput Vis 88(2):303\u2013338","journal-title":"Int J Comput Vis"},{"key":"397_CR32","doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D et\u00a0al (2014) Microsoft COCO: common objects in context. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Proceedings of the European conference on computer vision (ECCV). Springer International Publishing, Cham, p 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"397_CR33","doi-asserted-by":"crossref","unstructured":"Chen K, Pang J, Wang J, Xiong Y, Li X, Sun S et\u00a0al (2019) Hybrid task cascade for instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), p 4969\u20134978","DOI":"10.1109\/CVPR.2019.00511"},{"key":"397_CR34","unstructured":"Liu Y, Wang Y, Wang S, Liang T, Zhao Q, Tang Z et\u00a0al (2019) CBNet: a novel composite backbone network architecture for object detection. arXiv:1909.03625v1"},{"key":"397_CR35","doi-asserted-by":"crossref","unstructured":"Cao Y, Xu J, Lin S, Wei F, Hu H (2019) GCNet: non-local networks meet squeeze-excitation networks and beyond. In: Proceedings of the IEEE\/CVF international conference on computer vision workshop (ICCVW), p 1971\u20131980","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"397_CR36","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), p 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"397_CR37","doi-asserted-by":"crossref","unstructured":"Lin T, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), p 936\u2013944","DOI":"10.1109\/CVPR.2017.106"},{"key":"397_CR38","doi-asserted-by":"crossref","unstructured":"Wang X, Girshick R, Gupta A, He K (2018) Non-local neural networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), p 7794\u20137803","DOI":"10.1109\/CVPR.2018.00813"},{"issue":"8","key":"397_CR39","doi-asserted-by":"publisher","first-page":"2011","DOI":"10.1109\/TPAMI.2019.2913372","volume":"42","author":"J Hu","year":"2020","unstructured":"Hu J, Shen L, Albanie S, Sun G, Wu E (2020) Squeeze-and-excitation networks. IEEE Trans Pattern Anal Mach Intell 42(8):2011\u20132023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"5","key":"397_CR40","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.1109\/TPAMI.2019.2956516","volume":"43","author":"Z Cai","year":"2019","unstructured":"Cai Z, Vasconcelos N (2019) Cascade R-CNN: high quality object detection and instance segmentation. IEEE Trans Pattern Anal Mach Intell 43(5):1483\u20131498","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"397_CR41","unstructured":"Chen K, Wang J, Pang J, Cao Y, Xiong Y, Li X et\u00a0al (2019) MMDetection: Open MMLab detection toolbox and benchmark. arXiv:190607155"},{"key":"397_CR42","unstructured":"Hendrycks D, Dietterich T (2019) Benchmarking neural network robustness to common corruptions and perturbations. arXiv:1903.12261v1"},{"key":"397_CR43","doi-asserted-by":"crossref","unstructured":"Michaelis C, Mitzkus B, Geirhos R, Rusak E, Bringmann O, Ecker AS et\u00a0al (2019) Benchmarking robustness in object detection: autonomous driving when winter is coming. arXiv:190707484","DOI":"10.12792\/icisip2019.002"},{"key":"397_CR44","volume-title":"Nonparametric statistics for the behavioral sciences","author":"S Siegel","year":"1988","unstructured":"Siegel S, Castellan NJ (1988) Nonparametric statistics for the behavioral sciences, 2nd edn. McGraw-Hill, New York","edition":"2"}],"container-title":["Complex &amp; Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-021-00397-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-021-00397-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-021-00397-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,31]],"date-time":"2024-08-31T10:47:23Z","timestamp":1725101243000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-021-00397-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,22]]},"references-count":44,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,10]]}},"alternative-id":["397"],"URL":"https:\/\/doi.org\/10.1007\/s40747-021-00397-8","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,22]]},"assertion":[{"value":"24 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 May 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 May 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We declare that we have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}