{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T14:03:17Z","timestamp":1774965797806,"version":"3.50.1"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T00:00:00Z","timestamp":1642032000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T00:00:00Z","timestamp":1642032000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1007\/s10489-021-03073-z","type":"journal-article","created":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T08:03:31Z","timestamp":1642061011000},"page":"10398-10416","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["SIRA: Scale illumination rotation affine invariant mask R-CNN for pedestrian detection"],"prefix":"10.1007","volume":"52","author":[{"given":"Ujwalla","family":"Gawande","sequence":"first","affiliation":[]},{"given":"Kamal","family":"Hajari","sequence":"additional","affiliation":[]},{"given":"Yogesh","family":"Golhar","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,1,13]]},"reference":[{"issue":"4","key":"3073_CR1","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1109\/TPAMI.2011.155","volume":"34","author":"P Dollar","year":"2012","unstructured":"Dollar P, Wojek C, Schiele B, Perona P (2012) Pedestrian detection: An evaluation of the state of the art. TPAMI 34(4):743\u2013761","journal-title":"TPAMI"},{"key":"3073_CR2","unstructured":"Bochkovskiy A (2020) \u201cYOLOv4: Optimal Speed and Accuracy of Object Detection\u201d, CVPR, 23 April 2020"},{"key":"3073_CR3","unstructured":"Long X (2020) \u201cPP-YOLO: An Effective and Efficient Implementation of Object Detector\u201d, CVPR, 3 August 2020"},{"key":"3073_CR4","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) \u201cYOLO\u201d, CVPR, pp. 1-10, Las Vegas, Nevada, USA, 26 June-1 July 2016"},{"issue":"2","key":"3073_CR5","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1109\/TPAMI.2018.2844175","volume":"42","author":"K He","year":"2020","unstructured":"He K, Gkioxari G, Dollar P, Girshick R (2020) Mask R-CNN. TPAMI 42(2):386\u2013397","journal-title":"TPAMI"},{"key":"3073_CR6","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Dollar and Girshick (2017) \u201cMask R-CNN\u201d, ICCV, pp. 2980-2988, Italy, 22-29 October 2017","DOI":"10.1109\/ICCV.2017.322"},{"issue":"6","key":"3073_CR7","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) \u201cFaster R-CNN\u2019\u2019. IEEE Trans Pattern Ana Machine Intell (TPAMI) 39(6):1137\u20131149","journal-title":"IEEE Trans Pattern Ana Machine Intell (TPAMI)"},{"key":"3073_CR8","unstructured":"Ren S, He K, Girshick R, Sun J (2015) \u201cFaster R-CNN\u201d, NIPS, Montreal, pp. 1-9, Canada, 7-12 December 2015"},{"key":"3073_CR9","doi-asserted-by":"crossref","unstructured":"Girshick R (2015)\u201cFast R-CNN\u201d, ICCV, pp 1441-1448, Santiago, Chile 7-13 December 2015","DOI":"10.1109\/ICCV.2015.169"},{"key":"3073_CR10","unstructured":"Dai J, Li Y, He K, Sun J (2016) \u201cR-FCN: Object Detection via Region-based FCN\u201d, CVPR, pp 1-11, USA, July 2016"},{"key":"3073_CR11","unstructured":"Liu, Anguelov D, Erhan D, Szegedy C (2016) \u201cSSD\u201d, ECCV, pp 1-17, Netherlands, 11-14 October 2016"},{"key":"3073_CR12","unstructured":"Anguelov J, Shelh E, Darrell T (2015) \u201cFCN for Semantic Segmentation\u201d, CVPR, pp1-10, Boston, 8-10 June 2015"},{"key":"3073_CR13","unstructured":"Radford A, Metz L, Chintala S (2015) Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks, CVPR, pp 1-10, Boston, Massachusetts, 8-10 June 2015"},{"key":"3073_CR14","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Deep Residual Learning, CVPR, pp 1-10, Boston, 8-10 June 2015"},{"key":"3073_CR15","doi-asserted-by":"crossref","unstructured":"Szegedy C, Ioffe S, Vanhoucke V, Alemi A (2016) Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning, CVPR, pp 1-10, LA, Nevada, USA, 26 June-1 July 2016","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"3073_CR16","unstructured":"K S, Zisserman A (2015) Very Deep Convolutional Networks for Large-Scale Image Recog., CVPR, pp 1-10, Boston, 8-10 June 2015"},{"key":"3073_CR17","unstructured":"Zeiler M, Fergus (2013) Visualizing and Understanding Convolutional Networks, CVPR, pp 1-11, USA, June 2013"},{"key":"3073_CR18","unstructured":"Alex K, Sutskever I, Hinton G (2012) ImageNet Classification with Deep Convolutional Neural Networks, NIPS, pp 1-9, Nevada, United States, 3-6 December 2012"},{"issue":"3","key":"3073_CR19","first-page":"77","volume":"17","author":"L Kangming","year":"2016","unstructured":"Kangming L (2016) Research on an improved pedestrian detection method based on DBN classification algorithm. RISTI 17(3):77\u201387","journal-title":"RISTI"},{"issue":"11","key":"3073_CR20","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proceedings of the IEEE 86(11):2278\u20132324","journal-title":"Proceedings of the IEEE"},{"key":"3073_CR21","doi-asserted-by":"crossref","unstructured":"Kang S, Byun H, Lee S (2002) Real-Time Pedestrian Detection Using Support Vector Machines, First International Workshop on SVM: Pattern Recog. with SVM, pp 268-277, Canada, 10 August 2002","DOI":"10.1007\/3-540-45665-1_21"},{"key":"3073_CR22","unstructured":"Geronimo D, Sappa A, Lopez A, Ponsa D (2006) Pedestrian detection using AdaBoost learning of features and vehicle pitch estimation, International Conference on Visualization, Image and Image Processing, pp 1-8, Spain, 28-30 August 2006"},{"issue":"290","key":"3073_CR23","first-page":"1","volume":"8","author":"C Wu","year":"2019","unstructured":"Wu C, Yue J, Wang L, Lyu F (2019) Detection and Classification of Recessive Weakness in Superbuck Converter Based on WPD-PCA and Probabilistic Neural Network. MDPI Electronics 8(290):1\u201317","journal-title":"MDPI Electronics"},{"key":"3073_CR24","unstructured":"Alireza A, Mollaie, Reza, Yasser, Andi, Hosein (2011) Improved Object Tracking Using RBFNN, MVIP, Iran, pp 1-5, 16-17 November 2011"},{"key":"3073_CR25","unstructured":"Emil N, Neghina, Mihai (2009) A NN approach to pedestrian detection, ICCOMP, pp 374-379, USA, 23 July 2009"},{"key":"3073_CR26","unstructured":"Lin T, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Piotr Dollar, Lawrence Zitnick C (2014) MS COCO:, ECCV, Springer, Switzerland, pp 1-15, 6-12 September 2014"},{"key":"3073_CR27","unstructured":"Ess A, Leibe B, Gool L (2017) Depth and appearance for mobile scene analysis, ICCV, pp 1-8, Italy, 22-29 October 2017"},{"key":"3073_CR28","doi-asserted-by":"crossref","unstructured":"Geiger A, Lenz P, Urtasun R (2012) Are we ready for autonomous driving? the KITTI vision benchmark suite, CVPR, pp 3354-3361, RI, USA, 16-21 June 2012","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"3073_CR29","doi-asserted-by":"crossref","unstructured":"Gong Y, Wang L, Guo R, Lazebnik S (2014) Multiscale orderless pooling of deep convolutional activation features, ECCV, pp 392-407, Zurich, Switzerland, 6-12 September 2014","DOI":"10.1007\/978-3-319-10584-0_26"},{"issue":"4","key":"3073_CR30","first-page":"985","volume":"20","author":"J Li","year":"2018","unstructured":"Li J, Li X (2018) Scale-aware Fast R-CNN for Pedestrian Detec. IEEE Trans Multi 20(4):985\u2013996","journal-title":"IEEE Trans Multi"},{"issue":"2","key":"3073_CR31","first-page":"1","volume":"16","author":"K Wang","year":"2019","unstructured":"Wang K, Zhou W (2019) Pedestrian and cyclist detection based on deep neural network fast R-CNN. Inter. Journal of Advanced Robotic Systems, SAGE 16(2):1\u201310","journal-title":"Inter. Journal of Advanced Robotic Systems, SAGE"},{"key":"3073_CR32","doi-asserted-by":"crossref","unstructured":"Pobar M, Kosm M (2018) Mask R-CNN and Optical flow-based method for detection and marking of handball actions, CISP-BMEI 2018, pp 1-6, China, 13-15 October 2018","DOI":"10.1109\/CISP-BMEI.2018.8633201"},{"key":"3073_CR33","unstructured":"Minkesh A, Worranitta K, Taizo M (2019) Human extraction and scene transition utilizing Mask R-CNN, CVPR, pp 1-6, CA, United States, 16-20 June 2019"},{"key":"3073_CR34","doi-asserted-by":"crossref","unstructured":"Gawande, Ujwalla, Hajari, Kamal, Golhar, Yogesh (2020) Pedestrian Detection and Tracking in Video Surveillance System: Issues, Comprehensive Review, and Challenges, Recent Trends in Computational Intelligence, IntechOpen, 1-24, April 2020","DOI":"10.5772\/intechopen.90810"},{"key":"3073_CR35","doi-asserted-by":"crossref","unstructured":"Gawande U, Hajari K, Golhar Y (2020) Deep Learning Approach to Key Frame Detection in Human Action Videos, Recent Trends in Computational Intelligence, IntechOpen, 1-17 February 2020","DOI":"10.5772\/intechopen.91188"},{"key":"3073_CR36","unstructured":"Dalal N, Triggs B (2005) HOG for Human Detection, CVPR, pp 886-893, CA, USA, 20-25 June 2005"},{"key":"3073_CR37","doi-asserted-by":"crossref","unstructured":"Wang X, Han TX, Yan S (2009) An HOG-LBP human detector with partial occlusion handling, ICCV, pp 32-39, Japan, 29 September-2 October 2009","DOI":"10.1109\/ICCV.2009.5459207"},{"key":"3073_CR38","doi-asserted-by":"crossref","unstructured":"Dollar P, Tu Z, Per P, Bel S (2009) Integral channel features, BMVC, UK, pp 1-11, 7-10 September 2009","DOI":"10.5244\/C.23.91"},{"issue":"2","key":"3073_CR39","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1504\/IJBM.2018.091629","volume":"10","author":"U Gawande","year":"2018","unstructured":"Gawande U, Golhar Y (2018) Biometric security system: a rigorous review of unimodal and multimodal biometrics techniques. IJBM, InderScience 10(2):142\u2013175","journal-title":"IJBM, InderScience"},{"key":"3073_CR40","volume-title":"Fergus","author":"N Sil","year":"2014","unstructured":"Sil N, Son D (2014) Fergus. Instance Seg. of Indoor Scenes Using a Coverage Loss, ECCV, Switzerland"},{"key":"3073_CR41","unstructured":"Li GY, Yifan Q, Xingda (2019) \u201cDeep Learning Approaches on Pedestrian Detection in Hazy Weather\u201d, IEEE Transaction on Industrial Electronics, IEEE Transactions on Industrial Electronics, vol 1, 1 November 2019"},{"issue":"2","key":"3073_CR42","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1109\/TPAMI.2013.124","volume":"36","author":"X Wang","year":"2014","unstructured":"Wang X, Wang M, Li W (2014) Scene-specific pedestrian detection for static video. TPAMI 36(2):361\u2013374","journal-title":"TPAMI"},{"key":"3073_CR43","doi-asserted-by":"crossref","unstructured":"Tian Y, Luo P, Wang X, Tang X (2015) Pedestrian detection aided by deep learning semantic tasks, CVPR, pp 1-10, Boston, 8-10 June 2015","DOI":"10.1109\/CVPR.2015.7299143"},{"key":"3073_CR44","doi-asserted-by":"crossref","unstructured":"Xu C, Wang G, Yan S, Yu J, Zhang B, Dai S, Li Y, Xu L (2020) \u201cFast Vehicle and Pedestrian Detection Using Improved Mask R-CNN\u201d, Mathematical Problems in Engineering, vol 2020, Hindawi, pp 1-15, 2020","DOI":"10.1155\/2020\/5761414"},{"key":"3073_CR45","doi-asserted-by":"crossref","unstructured":"Han B, Wang Y, Yang Z, Gao X (2020) \u201cSmall-Scale Pedestrian Detection Based on Deep Neural Network\u201d, IEEE Transactions on Intelligent Transportation Systems, 21:(7), 2020","DOI":"10.1109\/TITS.2019.2923752"},{"key":"3073_CR46","unstructured":"Wang H, Wang LY, Shengjin (2019) \u201cFast Pedestrian Detection With Attention-Enhanced Multi-Scale RPN and Soft-Cascaded Decision Trees\u201d, IEEE Transactions on Intelligent Transportation Systems vol 1, No 8, 2019"},{"key":"3073_CR47","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1186\/s13640-017-0236-8","volume":"2017","author":"M Sharif","year":"2017","unstructured":"Sharif M, Khan MA, Akram T et al (2017) A framework of human detection and action recognition based on uniform segmentation and combination of Euclidean distance and joint entropy-based features selection. J Image Video Proc. 2017:89","journal-title":"J Image Video Proc."},{"key":"3073_CR48","doi-asserted-by":"crossref","unstructured":"Wojek C, Walk S, Schiele B (2009) \u201cMulti-cue onboard pedestrian detection,\u201d IEEE Conference on Computer Vision and Pattern Recognition, 2009","DOI":"10.1109\/CVPRW.2009.5206638"},{"issue":"3","key":"3073_CR49","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1109\/6979.892151","volume":"1","author":"L Zhao","year":"2000","unstructured":"Zhao L, Thorpe C (2000) Stereo and neural network-based pedestrian detection. IEEE Trans Intell Trans Syst 1(3):148\u2013154","journal-title":"IEEE Trans Intell Trans Syst"},{"key":"3073_CR50","doi-asserted-by":"crossref","unstructured":"Dai J, He K, Sun J (2016) \u201cInstance-aware semantic segmentation via multi-task network cascades\u201d, In: Computer Vision and Pattern Recognition (CVPR), 2016","DOI":"10.1109\/CVPR.2016.343"},{"key":"3073_CR51","doi-asserted-by":"crossref","unstructured":"Li Y, Qi H, Dai J, Ji X, Wei Y (2017) \u201cFully convolutional instanceaware semantic segmentation\u201d, In: Computer Vision and Pattern Recognition (CVPR), 2017","DOI":"10.1109\/CVPR.2017.472"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-03073-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-021-03073-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-03073-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T11:36:58Z","timestamp":1744198618000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-021-03073-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,13]]},"references-count":51,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2022,7]]}},"alternative-id":["3073"],"URL":"https:\/\/doi.org\/10.1007\/s10489-021-03073-z","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,13]]},"assertion":[{"value":"2 December 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 January 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interest"}}]}}