{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T22:11:20Z","timestamp":1773699080321,"version":"3.50.1"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,6,17]],"date-time":"2023-06-17T00:00:00Z","timestamp":1686960000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,17]],"date-time":"2023-06-17T00:00:00Z","timestamp":1686960000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001409","name":"Department of Science and Technology, Ministry of Science and Technology","doi-asserted-by":"publisher","award":["CPS-Individual\/2018\/403(G)"],"award-info":[{"award-number":["CPS-Individual\/2018\/403(G)"]}],"id":[{"id":"10.13039\/501100001409","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1007\/s11042-023-15365-2","type":"journal-article","created":{"date-parts":[[2023,6,17]],"date-time":"2023-06-17T03:31:27Z","timestamp":1686972687000},"page":"6755-6781","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["IRUVD: a new still-image based dataset for automatic vehicle detection"],"prefix":"10.1007","volume":"83","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4034-1956","authenticated-orcid":false,"given":"Asfak","family":"Ali","sequence":"first","affiliation":[]},{"given":"Ram","family":"Sarkar","sequence":"additional","affiliation":[]},{"given":"Debesh Kumar","family":"Das","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,6,17]]},"reference":[{"key":"15365_CR1","doi-asserted-by":"crossref","unstructured":"Bhattacharyya A, Bhattacharya A, Maity S, Singh P, Sarkar R (2023) Juvdsi v1: developing and benchmarking a new still image database in Indian scenario for automatic vehicle detection. Multimed Tools Appl 1\u201333","DOI":"10.1007\/s11042-023-14661-1"},{"key":"15365_CR2","unstructured":"Bileschi SM, Wolf L (2006) Cbcl streetscenes. Technical report"},{"key":"15365_CR3","unstructured":"Bochkovskiy A, Wang C-Y, Liao H-YM (2020) Yolov4: optimal speed and accuracy of object detection. arXiv:2004.10934"},{"key":"15365_CR4","doi-asserted-by":"crossref","unstructured":"Bodla N, Singh B, Chellappa R, Davis LS (2017) Improving object detection with one line of code. arXiv:1704.04503","DOI":"10.1109\/ICCV.2017.593"},{"key":"15365_CR5","doi-asserted-by":"crossref","unstructured":"Cordts M, Omran M, Ramos S, Rehfeld T, Enzweiler M, Benenson R, Franke U, Roth S, Schiele B (2016) The cityscapes dataset for semantic urban scene understanding. arXiv:1604.01685","DOI":"10.1109\/CVPR.2016.350"},{"key":"15365_CR6","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Li F-F (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"15365_CR7","doi-asserted-by":"crossref","unstructured":"Doll\u00e1r P, Wojek C, Schiele B, Perona P (2009) Pedestrian detection: a benchmark. In: 2009 IEEE conference on computer vision and pattern recognition. IEEE, pp 304\u2013311","DOI":"10.1109\/CVPR.2009.5206631"},{"issue":"4","key":"15365_CR8","doi-asserted-by":"publisher","first-page":"2247","DOI":"10.1109\/TITS.2015.2402438","volume":"16","author":"Z Dong","year":"2015","unstructured":"Dong Z, Wu Y, Pei M, Jia Y (2015) Vehicle type classification using a semisupervised convolutional neural network. IEEE Trans Intell Transp Syst 16(4):2247\u20132256","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"15365_CR9","doi-asserted-by":"crossref","unstructured":"Du X, Lin T-Y, Jin P, Ghiasi G, Tan M, Cui Y, Le QV, Song X (2019) Spinenet: learning scale-permuted backbone for recognition and localization. arXiv:1912.05027","DOI":"10.1109\/CVPR42600.2020.01161"},{"issue":"2","key":"15365_CR10","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":"15365_CR11","unstructured":"Ershad S F (2013) Developing feature representation and respected innovative database collecting algorithm for texture analysis 11"},{"key":"15365_CR12","unstructured":"Ge Z, Liu S, Wang F, Li Z, Sun J (2021) Yolox: exceeding yolo series in 2021. arXiv:2107.08430"},{"key":"15365_CR13","doi-asserted-by":"crossref","unstructured":"Geiger A, Lenz P, Urtasun R (2012) Are we ready for autonomous driving? The kitti vision benchmark suite. In: 2012 IEEE conference on computer vision and pattern recognition. IEEE, pp 3354\u20133361","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"15365_CR14","doi-asserted-by":"crossref","unstructured":"Ghiasi G, Lin T-Y, Pang R, Le QV (2019) NAS-FPN: learning scalable feature pyramid architecture for object detection. arXiv:1904.07392","DOI":"10.1109\/CVPR.2019.00720"},{"key":"15365_CR15","unstructured":"India tops the world with 11% of global death in road accidents: World bank report. shorturl.at\/goEXZ, February 2021"},{"key":"15365_CR16","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/j.jvcir.2018.03.008","volume":"53","author":"M Jian","year":"2018","unstructured":"Jian M, Qi Q, Dong J, Yin Y, Lam K-M (2018) Integrating qdwd with pattern distinctness and local contrast for underwater saliency detection. J Vis Commun Image Represent 53:31\u201341","journal-title":"J Vis Commun Image Represent"},{"key":"15365_CR17","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1016\/j.asoc.2019.04.025","volume":"80","author":"M Jian","year":"2019","unstructured":"Jian M, Qi Q, Yu H, Dong J, Cui C, Nie X, Zhang H, Yin Y, Lam K-M (2019) The extended marine underwater environment database and baseline evaluations. Appl Soft Comput 80:425\u2013437","journal-title":"Appl Soft Comput"},{"key":"15365_CR18","unstructured":"Jocher G, Stoken A, Borovec J, NanoCode012, Chaurasia A, TaoXie, Liu C., Abhiram V, Laughing, tkianai, yxNONG, Hogan A, Mammana L, AlexWang1900, Hajek J, Diaconu L, Marc Y, Kwon O, Wanghaoyang0106, Defretin Y, Lohia A, ml5ah, Milanko B, Fineran B, Khromov D, Ding Y, Doug D, Ingham F (2021) ultralytics\/yolov5: v6.0 - YOLOv5n \u2018Nano\u2019 models, Roboflow integration, TensorFlow export, OpenCV DNN support"},{"key":"15365_CR19","unstructured":"Khosravi H, Gholamalinejad H (2020) Irvd: a large-scale dataset for classification of iranian vehicles in urban streets 06"},{"key":"15365_CR20","doi-asserted-by":"crossref","unstructured":"Krause J, Stark M, Deng J, Li F-F (2013) 3d object representations for fine-grained categorization. In: 2013 IEEE International conference on computer vision workshops, pp 554\u2013561","DOI":"10.1109\/ICCVW.2013.77"},{"key":"15365_CR21","unstructured":"Li C, Li L, Jiang H, Weng K, Geng Y, Li L, Ke Z, Li Q, Cheng M, Nie W et al (2022) Yolov6: a single-stage object detection framework for industrial applications. arXiv:2209.02976"},{"key":"15365_CR22","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie SJ, Bourdev LD, Girshick RB, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft COCO: common objects in context. arXiv:1405.0312","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"15365_CR23","doi-asserted-by":"crossref","unstructured":"Lin T-Yi, Doll\u00e1r P, Girshick RB, He K, Hariharan B, Belongie SJ (2016) Feature pyramid networks for object detection. arXiv:1612.03144","DOI":"10.1109\/CVPR.2017.106"},{"key":"15365_CR24","doi-asserted-by":"crossref","unstructured":"Liu S, Lu Q, Qin H, Shi J, Jia J (2018) Path aggregation network for instance segmentation. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition, pp 8759\u20138768","DOI":"10.1109\/CVPR.2018.00913"},{"key":"15365_CR25","unstructured":"Liu S, Di H, Wang Y (2019) Learning spatial fusion for single-shot object detection. arXiv:1911.09516"},{"key":"15365_CR26","doi-asserted-by":"crossref","unstructured":"Maity S, Bhattacharyya A, Singh P, Kumar M, Sarkar R (2022) Last decade in vehicle detection and classification: a comprehensive survey. Arch Comput Methods Eng 1\u201338","DOI":"10.1007\/s11831-022-09764-1"},{"issue":"11","key":"15365_CR27","doi-asserted-by":"publisher","first-page":"1863","DOI":"10.1109\/TPAMI.2006.217","volume":"28","author":"S Munder","year":"2006","unstructured":"Munder S, Gavrila DM (2006) An experimental study on pedestrian classification. IEEE Trans Pattern Anal Mach Intell 28(11):1863\u20131868","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"15365_CR28","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1016\/j.procs.2020.04.022","volume":"171","author":"S Namburi","year":"2020","unstructured":"Namburi S, Joseph A, Umamaheswaran S, Priyanka C h, Malavika M, Sankaran P (2020) Nitcad\u2014developing an object detection, classification and stereo vision dataset for autonomous navigation in indian roads. Procedia Comput Sci 171:207\u2013216 (01)","journal-title":"Procedia Comput Sci"},{"key":"15365_CR29","doi-asserted-by":"crossref","unstructured":"Neuhold G, Ollmann T, Bul\u00f2 SR, Kontschieder P (2017) The mapillary vistas dataset for semantic understanding of street scenes. In: 2017 IEEE International conference on computer vision (ICCV), pp 5000\u20135009","DOI":"10.1109\/ICCV.2017.534"},{"key":"15365_CR30","doi-asserted-by":"crossref","unstructured":"Peng Y, Jin JS, Luo S, Min X, Cui Y (2012) Vehicle type classification using pca with self-clustering. In: 2012 IEEE International conference on multimedia and expo workshops. IEEE, pp 384\u2013389","DOI":"10.1109\/ICMEW.2012.73"},{"key":"15365_CR31","unstructured":"Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv:1804.02767"},{"key":"15365_CR32","unstructured":"Sener E, Sebatli-Saglam A, Cavdur F (2021) Otonom-payla\u015f\u0131ml\u0131 ara\u00e7 y\u00f6netim sistemi. J Polytechnic"},{"key":"15365_CR33","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition"},{"key":"15365_CR34","unstructured":"Tan M, Le QV (2019) Efficientnet: rethinking model scaling for convolutional neural networks. arXiv:1905.11946"},{"key":"15365_CR35","doi-asserted-by":"crossref","unstructured":"Tan M, Pang R, Le QV (2019) Efficientdet: scalable and efficient object detection. arXiv:1911.09070","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"15365_CR36","unstructured":"Tzutalin (2015) Labelimg. git code. https:\/\/github.com\/tzutalin\/labelImg"},{"key":"15365_CR37","unstructured":"Udacity self driving car (2018). https:\/\/github.com\/udacity\/self-driving-car"},{"key":"15365_CR38","doi-asserted-by":"crossref","unstructured":"Varma G, Subramanian A, Namboodiri AM, Chandraker M, Jawahar CV (2018) IDD: a dataset for exploring problems of autonomous navigation in unconstrained environments. arXiv:1811.10200","DOI":"10.1109\/WACV.2019.00190"},{"key":"15365_CR39","doi-asserted-by":"crossref","unstructured":"Wang C-Y, Liao H-Y M, Yeh I-H, Wu Y-H, Chen P-Y, Hsieh J-W (2019) Cspnet: a new backbone that can enhance learning capability of CNN. arXiv:1911.11929","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"15365_CR40","doi-asserted-by":"crossref","unstructured":"Wang C-Y, Bochkovskiy A, Liao H-Y (2020) Scaled-yolov4: scaling cross stage partial network. arXiv:2011.08036","DOI":"10.1109\/CVPR46437.2021.01283"},{"key":"15365_CR41","unstructured":"Wang C-Y, Yeh I-H, Liao H-YM (2021) You only learn one representation: unified network for multiple tasks. arXiv:2105.04206"},{"key":"15365_CR42","doi-asserted-by":"crossref","unstructured":"Wang C-Y, Bochkovskiy A, Liao H-YM (2022) Yolov7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv:2207.02696","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"15365_CR43","doi-asserted-by":"crossref","unstructured":"Wojek C, Walk S, Schiele B (2009) Multi-cue onboard pedestrian detection. In: 2009 IEEE conference on computer vision and pattern recognition, pp 794\u2013801","DOI":"10.1109\/CVPR.2009.5206638"},{"key":"15365_CR44","unstructured":"Yu F, Xian W, Chen Y, Liu F, Liao M, Madhavan V, Darrell T (2018) BDD100K: a diverse driving video database with scalable annotation tooling. arXiv:1805.04687"},{"key":"15365_CR45","doi-asserted-by":"crossref","unstructured":"Zhang S, Benenson R, Schiele B (2017) Citypersons: a diverse dataset for pedestrian detection","DOI":"10.1109\/CVPR.2017.474"},{"key":"15365_CR46","doi-asserted-by":"publisher","first-page":"2778","DOI":"10.1109\/JSTARS.2020.2995703","volume":"13","author":"L Zhang","year":"2020","unstructured":"Zhang L, Zhang C, Quan S, Xiao H, Kuang G, Li L (2020) A class imbalance loss for imbalanced object recognition. IEEE J Sel Top Appl Earth Obs Remote Sens 13:2778\u20132792","journal-title":"IEEE J Sel Top Appl Earth Obs Remote Sens"},{"key":"15365_CR47","doi-asserted-by":"crossref","unstructured":"Zhao Q, Sheng T, Wang Y, Tang Z, Chen Y, Cai L, Ling H (2018) M2det: a single-shot object detector based on multi-level feature pyramid network. arXiv:1811.04533","DOI":"10.1609\/aaai.v33i01.33019259"},{"key":"15365_CR48","doi-asserted-by":"crossref","unstructured":"Zhou B, Zhao H, Puig X, Fidler S, Barriuso A, Torralba A (2016) Semantic understanding of scenes through the ADE20k dataset. arXiv:1608.05442","DOI":"10.1109\/CVPR.2017.544"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15365-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-15365-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15365-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,8]],"date-time":"2024-01-08T07:33:46Z","timestamp":1704699226000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-15365-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,17]]},"references-count":48,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["15365"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-15365-2","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,17]]},"assertion":[{"value":"27 August 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 April 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 April 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Ethical approval"}},{"value":"The authors declare that they have no conflict of interest.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of interests"}}]}}