{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T07:04:48Z","timestamp":1744095888582,"version":"3.37.3"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2020,6,17]],"date-time":"2020-06-17T00:00:00Z","timestamp":1592352000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,6,17]],"date-time":"2020-06-17T00:00:00Z","timestamp":1592352000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Innoswiss","award":["25358.1"],"award-info":[{"award-number":["25358.1"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2020,9]]},"DOI":"10.1007\/s00138-020-01089-y","type":"journal-article","created":{"date-parts":[[2020,6,17]],"date-time":"2020-06-17T18:04:11Z","timestamp":1592417051000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["WatchNet++: efficient and accurate depth-based network for detecting people attacks and intrusion"],"prefix":"10.1007","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2066-6665","authenticated-orcid":false,"given":"M.","family":"Villamizar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A.","family":"Mart\u00ednez-Gonz\u00e1lez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"O.","family":"Can\u00e9vet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J.-M.","family":"Odobez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,6,17]]},"reference":[{"issue":"4","key":"1089_CR1","first-page":"567","volume":"10","author":"M Ahmad","year":"2019","unstructured":"Ahmad, M., Ahmed, I., Ullah, K., Khan, I., Khattak, A., Adnan, A.: Person detection from overhead view: a survey. Int. J. Adv. Comput. Sci. Appl. 10(4), 567\u2013577 (2019)","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"issue":"1","key":"1089_CR2","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1007\/s10586-017-0968-3","volume":"21","author":"I Ahmed","year":"2018","unstructured":"Ahmed, I., Adnan, A.: A robust algorithm for detecting people in overhead views. Clust. Comput. 21(1), 633\u2013654 (2018)","journal-title":"Clust. Comput."},{"key":"1089_CR3","doi-asserted-by":"crossref","unstructured":"Bondi, E., Seidenari, L., Bagdanov, A.D., Del\u00a0Bimbo, A.: Real-time people counting from depth imagery of crowded environments. In: 2014 11th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 337\u2013342. IEEE (2014)","DOI":"10.1109\/AVSS.2014.6918691"},{"key":"1089_CR4","doi-asserted-by":"crossref","unstructured":"Boominathan, L., Kruthiventi, S.S., Babu, R.V.: Crowdnet: A deep convolutional network for dense crowd counting. In: Proceedings of the 2016 ACM on Multimedia Conference (2016)","DOI":"10.1145\/2964284.2967300"},{"key":"1089_CR5","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2d pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7291\u20137299 (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"1089_CR6","doi-asserted-by":"crossref","unstructured":"Carincotte, C., Naturel, X., Hick, M., Odobez, J.M., Yao, J., Bastide, A., Corbucci, B.: Understanding metro station usage using closed circuit television cameras analysis. In: ITSC (2008)","DOI":"10.1109\/ITSC.2008.4732571"},{"key":"1089_CR7","doi-asserted-by":"crossref","unstructured":"Carletti, V., Del\u00a0Pizzo, L., Percannella, G., Vento, M.: An efficient and effective method for people detection from top-view depth cameras. In: 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 1\u20136. IEEE (2017)","DOI":"10.1109\/AVSS.2017.8078531"},{"key":"1089_CR8","unstructured":"Chen, S., Bremond, F., Nguyen, H., Thomas, H.: Exploring depth information for head detection with depth images. In: 2016 13th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 228\u2013234. IEEE (2016)"},{"key":"1089_CR9","doi-asserted-by":"crossref","unstructured":"Del\u00a0Pizzo, L., Foggia, P., Greco, A., Percannella, G., Vento, M.: A versatile and effective method for counting people on either rgb or depth overhead cameras. In: 2015 IEEE International Conference on Multimedia & Expo Workshops (ICMEW), pp. 1\u20136. IEEE (2015)","DOI":"10.1109\/ICMEW.2015.7169795"},{"key":"1089_CR10","doi-asserted-by":"crossref","unstructured":"Dumoulin, J., Can\u00e9vet, O., Villamizar, M., Nunes, H., Khaled, O.A., Mugellini, E., Moscheni, F., Odobez, J.M.: Unicity: A depth maps database for people detection in security airlocks. In: 2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 1\u20136. IEEE (2018)","DOI":"10.1109\/AVSS.2018.8639152"},{"key":"1089_CR11","doi-asserted-by":"crossref","unstructured":"Gal\u010d\u00edk, F., Gargal\u00edk, R.: Real-time depth map based people counting. In: International Conference on Advanced Concepts for Intelligent Vision Systems, pp. 330\u2013341. Springer (2013)","DOI":"10.1007\/978-3-319-02895-8_30"},{"issue":"2","key":"1089_CR12","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1007\/s12369-016-0389-0","volume":"9","author":"A Garrell","year":"2017","unstructured":"Garrell, A., Villamizar, M., Moreno-Noguer, F., Sanfeliu, A.: Teaching robot\u2019s proactive behavior using human assistance. Int. J. Soc. Robot. 9(2), 231\u2013249 (2017)","journal-title":"Int. J. Soc. Robot."},{"key":"1089_CR13","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 249\u2013256 (2010)"},{"key":"1089_CR14","doi-asserted-by":"crossref","unstructured":"Hu, R., Wang, R., Shan, S., Chen, X.: Robust head-shoulder detection using a two-stage cascade framework. In: 2014 22nd International Conference on Pattern Recognition, pp. 2796\u20132801. IEEE (2014)","DOI":"10.1109\/ICPR.2014.482"},{"key":"1089_CR15","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. CoRR abs\/1502.03167 (2015)"},{"key":"1089_CR16","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR abs\/1412.6980 (2014)"},{"key":"1089_CR17","doi-asserted-by":"crossref","unstructured":"Kreiss, S., Bertoni, L., Alahi, A.: Pifpaf: Composite fields for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11977\u201311986 (2019)","DOI":"10.1109\/CVPR.2019.01225"},{"key":"1089_CR18","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"1089_CR19","doi-asserted-by":"crossref","unstructured":"Lejbolle, A.R., Krogh, B., Nasrollahi, K., Moeslund, T.B.: Attention in multimodal neural networks for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 179\u2013187 (2018)","DOI":"10.1109\/CVPRW.2018.00055"},{"key":"1089_CR20","unstructured":"Lempitsky, V., Zisserman, A.: Learning to count objects in images. In: Advances in Neural Information Processing Systems, pp. 1324\u20131332 (2010)"},{"issue":"12","key":"1089_CR21","doi-asserted-by":"publisher","first-page":"2663","DOI":"10.1109\/TMI.2018.2845918","volume":"37","author":"X Li","year":"2018","unstructured":"Li, X., Chen, H., Qi, X., Dou, Q., Fu, C.W., Heng, P.A.: H-denseunet: hybrid densely connected unet for liver and tumor segmentation from ct volumes. IEEE Trans. Med. Imag. 37(12), 2663\u20132674 (2018)","journal-title":"IEEE Trans. Med. Imag."},{"key":"1089_CR22","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"1089_CR23","doi-asserted-by":"crossref","unstructured":"Ma, Z., Chan, A.B.: Crossing the line: Crowd counting by integer programming with local features. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2539\u20132546 (2013)","DOI":"10.1109\/CVPR.2013.328"},{"key":"1089_CR24","doi-asserted-by":"crossref","unstructured":"Nalepa, J., Szymanek, J., Kawulok, M.: Real-time people counting from depth images. In: International Conference: Beyond Databases, Architectures and Structures (2015)","DOI":"10.1007\/978-3-319-18422-7_34"},{"key":"1089_CR25","doi-asserted-by":"crossref","unstructured":"Rauter, M.: Reliable human detection and tracking in top-view depth images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 529\u2013534 (2013)","DOI":"10.1109\/CVPRW.2013.84"},{"key":"1089_CR26","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"1089_CR27","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234\u2013241. Springer (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"1089_CR28","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 (2014)"},{"key":"1089_CR29","unstructured":"Song, H., Sun, S., Akhtar, N., Zhang, C., Li, J., Mian, A.: Benchmark data and method for real-time people counting in cluttered scenes using depth sensors. arXiv:1804.04339 (2018)"},{"key":"1089_CR30","doi-asserted-by":"crossref","unstructured":"Tremblay, J., Prakash, A., Acuna, D., Brophy, M., Jampani, V., Anil, C., To, T., Cameracci, E., Boochoon, S., Birchfield, S.: Training deep networks with synthetic data: Bridging the reality gap by domain randomization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 969\u2013977 (2018)","DOI":"10.1109\/CVPRW.2018.00143"},{"key":"1089_CR31","doi-asserted-by":"crossref","unstructured":"Tu, J., Zhang, C., Hao, P.: Robust real-time attention-based head-shoulder detection for video surveillance. In: 2013 IEEE International Conference on Image Processing, pp. 3340\u20133344. IEEE (2013)","DOI":"10.1109\/ICIP.2013.6738688"},{"key":"1089_CR32","doi-asserted-by":"crossref","unstructured":"Varol, G., Romero, J., Martin, X., Mahmood, N., Black, M.J., Laptev, I., Schmid, C.: Learning from synthetic humans. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 109\u2013117 (2017)","DOI":"10.1109\/CVPR.2017.492"},{"key":"1089_CR33","doi-asserted-by":"crossref","unstructured":"Vera, P., Zenteno, D., Salas, J.: Counting pedestrians in bidirectional scenarios using zenithal depth images. In: Mexican Conference on Pattern Recognition (2013)","DOI":"10.1007\/978-3-642-38989-4_9"},{"issue":"2","key":"1089_CR34","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1109\/TPAMI.2017.2676778","volume":"40","author":"M Villamizar","year":"2018","unstructured":"Villamizar, M., Andrade-Cetto, J., Sanfeliu, A., Moreno-Noguer, F.: Boosted random ferns for object detection. IEEE Trans. Pattern Anal. Mach. Intell. 40(2), 272\u2013288 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1089_CR35","doi-asserted-by":"crossref","unstructured":"Villamizar, M., Mart\u00ednez-Gonz\u00e1lez, A., Can\u00e9vet, O., Odobez, J.M.: Watchnet: efficient and depth-based network for people detection in video surveillance systems. In: IEEE International Conference on Advanced Video and Signal-based Surveillance (2018)","DOI":"10.1109\/AVSS.2018.8639165"},{"issue":"12","key":"1089_CR36","doi-asserted-by":"publisher","first-page":"2878","DOI":"10.1109\/TPAMI.2012.261","volume":"35","author":"Y Yang","year":"2012","unstructured":"Yang, Y., Ramanan, D.: Articulated human detection with flexible mixtures of parts. IEEE Trans. Pattern Anal. Mach. Intell. 35(12), 2878\u20132890 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1089_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, X., Yan, J., Feng, S., Lei, Z., Yi, D., Li, S.Z.: Water filling: Unsupervised people counting via vertical kinect sensor. In: 2012 IEEE Ninth International Conference on Advanced Video and Signal-based Surveillance, pp. 215\u2013220. IEEE (2012)","DOI":"10.1109\/AVSS.2012.82"},{"key":"1089_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhou, D., Chen, S., Gao, S., Ma, Y.: Single-image crowd counting via multi-column convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 589\u2013597 (2016)","DOI":"10.1109\/CVPR.2016.70"},{"key":"1089_CR39","doi-asserted-by":"crossref","unstructured":"Zhu, L., Wong, K.H.: Human tracking and counting using the kinect range sensor based on adaboost and kalman filter. In: International Symposium on Visual Computing (2013)","DOI":"10.1007\/978-3-642-41939-3_57"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-020-01089-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-020-01089-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-020-01089-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,16]],"date-time":"2021-06-16T23:33:55Z","timestamp":1623886435000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-020-01089-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,17]]},"references-count":39,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2020,9]]}},"alternative-id":["1089"],"URL":"https:\/\/doi.org\/10.1007\/s00138-020-01089-y","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"type":"print","value":"0932-8092"},{"type":"electronic","value":"1432-1769"}],"subject":[],"published":{"date-parts":[[2020,6,17]]},"assertion":[{"value":"11 December 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 May 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 May 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"41"}}