{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T20:26:55Z","timestamp":1769718415583,"version":"3.49.0"},"reference-count":61,"publisher":"SAGE Publications","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2023,8,1]]},"abstract":"<jats:p>With the development of convolutional neural networks, many improved algorithms have been successively proposed to promote the accuracy of dense crowd counting. However, these algorithms are deployed with expensive computing resources, which is unbearable for small devices such as embedded systems with limited computing resources. To realize the real-time counting on the small devices, it is of great significance how to trade off the computation cost and processing accuracy of the dense crowd-counting algorithm. Thus, we propose a lightweight dense crowd-counting algorithm (LCNNet) to improve this issue. Specifically, the proposed LCNNet consists of two subnetworks, a feature extraction subnetwork, and a regression subnetwork, with a bottleneck depth-separable convolution with a residuals module as the basic module. The LCNNet effectively improves computational efficiency and reduces the computational cost, which can be performed on small devices. Extensive evaluations on four benchmark datasets well demonstrate the effectiveness of the proposed LCNNet for dense crowd-counting models. Meanwhile, the proposed LCNNet can maintain a comparable level of computational accuracy and computational cost on Vehicle counting datasets.<\/jats:p>","DOI":"10.3233\/jifs-224081","type":"journal-article","created":{"date-parts":[[2023,5,26]],"date-time":"2023-05-26T13:19:19Z","timestamp":1685107159000},"page":"1991-2004","source":"Crossref","is-referenced-by-count":1,"title":["LCNNet: Light-weight convolutional neural networks for understanding the highly congested scenes"],"prefix":"10.1177","volume":"45","author":[{"given":"Renjie","family":"Wang","sequence":"first","affiliation":[{"name":"School of Physics and Telecommunication Engineering, South China Normal University, Guangzhou, China"}]},{"given":"Fei","family":"Tan","sequence":"additional","affiliation":[{"name":"School of Physics and Telecommunication Engineering, South China Normal University, Guangzhou, China"}]},{"given":"Kunlong","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Physics and Telecommunication Engineering, South China Normal University, Guangzhou, China"}]},{"given":"Yuwen","family":"Hao","sequence":"additional","affiliation":[{"name":"School of Physics and Telecommunication Engineering, South China Normal University, Guangzhou, China"}]},{"given":"Fengguo","family":"Li","sequence":"additional","affiliation":[{"name":"School of Physics and Telecommunication Engineering, South China Normal University, Guangzhou, China"}]},{"given":"Xiaoyuan","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Physics and Telecommunication Engineering, South China Normal University, Guangzhou, China"}]}],"member":"179","reference":[{"key":"10.3233\/JIFS-224081_ref1","first-page":"589","article-title":"Single-image crowd counting via multi-column convolutional neural network","author":"Zhang","year":"2016","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"10.3233\/JIFS-224081_ref2","unstructured":"Yiming M. , Sanchez V. and Guha T. , Fusioncount: Efficient crowd counting via multiscale feature fusion, Proceedings of the IEEE International Conference on Image Processing, Bordeaux, France, 2022."},{"key":"10.3233\/JIFS-224081_ref3","doi-asserted-by":"crossref","unstructured":"Wang Q. and Breckon T.P. , Crowd counting via segmentation guided attention networks and curriculum loss, IEEE Transactions on Intelligent Transportation Systems, 2022.","DOI":"10.1109\/TITS.2021.3138896"},{"key":"10.3233\/JIFS-224081_ref4","first-page":"1091","article-title":"Csrnet: Dilated convolutional neural networks for understanding the highly congested scenes","author":"Li","year":"2018","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"issue":"8","key":"10.3233\/JIFS-224081_ref5","first-page":"2739","article-title":"Locate, size, and count: accurately resolving people in dense crowds via detection","volume":"43","author":"Sam","year":"2020","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.3233\/JIFS-224081_ref6","doi-asserted-by":"crossref","first-page":"640","DOI":"10.1145\/2964284.2967300","article-title":"Crowdnet: A deep convolutional network for dense crowd counting","author":"Boominathan","year":"2016","journal-title":"Proceedings of the 24th ACM international conference on Multimedia"},{"key":"10.3233\/JIFS-224081_ref7","doi-asserted-by":"crossref","unstructured":"Tang H. , Wang Y. and Chau L.-P. , Tafnet: A three-stream adaptive fusion network for rgb-t crowd counting, arXiv preprint arXiv:2202.08517, 2022.","DOI":"10.1109\/ISCAS48785.2022.9937583"},{"key":"10.3233\/JIFS-224081_ref8","doi-asserted-by":"crossref","first-page":"2382","DOI":"10.1109\/ICPR48806.2021.9413286","article-title":"Encoder-decoder based convolutional neural networks with multi-scale-aware modules for crowd counting","author":"Thanasutives","year":"2021","journal-title":"2020 25th International Conference on Pattern Recognition (ICPR)"},{"key":"10.3233\/JIFS-224081_ref9","first-page":"4510","article-title":"Mobilenetv2: Inverted residuals and linear bottlenecks","author":"Sandler","year":"2018","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"10.3233\/JIFS-224081_ref10","first-page":"1","article-title":"Face mask detection using mobilenetv2 in the era of covid-19 pandemic","author":"Sanjaya","year":"2020","journal-title":"2020 International Conference on Data Analytics for Business and Industry: Way Towards a Sustainable Economy (ICDABI)"},{"key":"10.3233\/JIFS-224081_ref11","first-page":"1","article-title":"Transfer learning with fine-tuned mobilenetv2 for diabetic retinopathy","author":"Patel","year":"2020","journal-title":"2020 international conference for emerging technology (INCET)"},{"key":"10.3233\/JIFS-224081_ref12","first-page":"1","article-title":"Fruit image classification based on mobilenetv2 with transfer learning technique","author":"Xiang","year":"2019","journal-title":"Proceedings of the 3rd International Conference on Computer Science and Application Engineering"},{"key":"10.3233\/JIFS-224081_ref13","first-page":"734","article-title":"Scale aggregation network for accurate and efficient crowd counting","author":"Cao","year":"2018","journal-title":"Proceedings of the European conference on computer vision (ECCV)"},{"key":"10.3233\/JIFS-224081_ref14","first-page":"1","article-title":"A discriminatively trained, multiscale, deformable part model","author":"Felzenszwalb","year":"2008","journal-title":"2008 IEEE conference on computer vision and pattern recognition"},{"key":"10.3233\/JIFS-224081_ref15","unstructured":"Ren S. , He K. , Girshick R. and Sun J. , Faster r-cnn: Towards real-time object detection with region proposal networks, Advances in Neural Information Processing Systems 28 (2015)."},{"key":"10.3233\/JIFS-224081_ref16","first-page":"1440","article-title":"Fast r-cnn","author":"Girshick","year":"2015","journal-title":"Proceedings of the IEEE international conference on computer vision"},{"key":"10.3233\/JIFS-224081_ref17","first-page":"21","article-title":"Ssd: Single shot multibox detector","author":"Liu","year":"2016","journal-title":"European conference on computer vision"},{"key":"10.3233\/JIFS-224081_ref18","unstructured":"Redmon J. and Farhadi A. , Yolov3: An incremental improvement, arXiv preprint arXiv:1804.02767, 2018."},{"key":"10.3233\/JIFS-224081_ref19","first-page":"1","article-title":"Privacy preserving crowd monitoring: Counting people without people models or tracking","author":"Chan","year":"2008","journal-title":"2008 IEEE conference on computer vision and pattern recognition"},{"key":"10.3233\/JIFS-224081_ref20","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1109\/DICTA.2009.22","article-title":"Crowd counting using multiple local features","author":"Ryan","year":"2009","journal-title":"2009 digital image computing: techniques and applications"},{"key":"10.3233\/JIFS-224081_ref21","first-page":"2467","article-title":"Cumulative attribute space for age and crowd density estimation","author":"Chen","year":"2013","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"10.3233\/JIFS-224081_ref22","unstructured":"Lempitsky V. and Zisserman A. , Learning to count objects in images, Advances in Neural Information Processing Systems 23 (2010)."},{"key":"10.3233\/JIFS-224081_ref23","first-page":"833","article-title":"Cross-scene crowd counting via deep convolutional neural networks","author":"Zhang","year":"2015","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"10.3233\/JIFS-224081_ref24","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1016\/j.neucom.2020.05.056","article-title":"Mobilecount: An efficient encoder-decoder framework for real-time crowd counting","volume":"407","author":"Wang","year":"2020","journal-title":"Neurocomputing"},{"key":"10.3233\/JIFS-224081_ref25","unstructured":"Iandola F.N. , Han S. , Moskewicz M.W. , Ashraf K. , Dally W.J. and Keutzer K. , Squeezenet: Alexnet-level accuracy with 50x fewer parameters and <0.5 mb model size, arXiv preprint arXiv:1602.07360, 2016."},{"key":"10.3233\/JIFS-224081_ref26","unstructured":"Howard A.G. , Zhu M. , Chen B. , Kalenichenko D. , Wang W. , Weyand T. , Andreetto M. and Adam H. , Mobilenets: Efficient convolutional neural networks for mobile vision applications, arXiv preprint arXiv:1704.04861, 2017."},{"key":"10.3233\/JIFS-224081_ref27","first-page":"6848","article-title":"Shufflenet: An extremely efficient convolutional neural network for mobile devices","author":"Zhang","year":"2018","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"10.3233\/JIFS-224081_ref28","first-page":"116","article-title":"Shufflenet v2: Practical guidelines for efficient cnn architecture design","author":"Ma","year":"2018","journal-title":"Proceedings of the European conference on computer vision (ECCV)"},{"key":"10.3233\/JIFS-224081_ref29","first-page":"1580","article-title":"Ghostnet: More features from cheap operations","author":"Han","year":"2020","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"10.3233\/JIFS-224081_ref30","first-page":"1367","article-title":"Computational optimal transport: Complexity by accelerated gradient descent is better than by sinkhorn algorithm","author":"Dvurechensky","year":"2018","journal-title":"International conference on machine learning"},{"key":"10.3233\/JIFS-224081_ref31","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"10.3233\/JIFS-224081_ref32","unstructured":"Simonyan K. and Zisserman A. , Very deep convolutional networks for large-scale image recognition, arXiv preprint arXiv:1409.1556, 2014."},{"key":"10.3233\/JIFS-224081_ref33","first-page":"1595","article-title":"Distribution matching for crowd counting","volume":"33","author":"Wang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.3233\/JIFS-224081_ref34","doi-asserted-by":"crossref","first-page":"610","DOI":"10.1111\/coin.12487","article-title":"and S.Khamuruddeen, An efficient clinical support system for heart disease prediction using TANFIS classifier","author":"Sekar","year":"2022","journal-title":"Computational Intelligence"},{"key":"10.3233\/JIFS-224081_ref35","first-page":"214","article-title":"Wasserstein generative adversarial networks","author":"Arjovsky","year":"2017","journal-title":"International conference on machine learning"},{"issue":"5-6","key":"10.3233\/JIFS-224081_ref36","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1561\/2200000073","article-title":"Computational optimal transport: With applications to data science, in Machine Learning","volume":"11","author":"Peyr\u00e9","year":"2019","journal-title":"Foundations and Trends\u00ae in Machine Learning"},{"issue":"11","key":"10.3233\/JIFS-224081_ref37","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Communications of the ACM"},{"key":"10.3233\/JIFS-224081_ref38","first-page":"1","article-title":"Counting in dense crowds using deep features","author":"Tota","year":"2015","journal-title":"Proc. CRCV"},{"key":"10.3233\/JIFS-224081_ref39","first-page":"833","article-title":"Cross-scene crowd counting via deep convolutional neural networks","author":"Zhang","year":"2015","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"10.3233\/JIFS-224081_ref40","first-page":"532","article-title":"Composition loss for counting, density map estimation and localization in dense crowds","author":"Idrees","year":"2018","journal-title":"Proceedings of the European conference on computer vision (ECCV)"},{"issue":"6","key":"10.3233\/JIFS-224081_ref41","doi-asserted-by":"crossref","first-page":"2141","DOI":"10.1109\/TPAMI.2020.3013269","article-title":"Nwpu-crowd: A large-scale benchmark for crowd counting and localization","volume":"43","author":"Wang","year":"2020","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.3233\/JIFS-224081_ref42","first-page":"5099","article-title":"Context-aware crowd counting","author":"Liu","year":"2019","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"10.3233\/JIFS-224081_ref43","first-page":"2685","article-title":"Learning to count with regression forest and structured labels","author":"Fiaschi","year":"2012","journal-title":"Proceedings of the 21st international conference on pattern recognition (ICPR2012)"},{"key":"10.3233\/JIFS-224081_ref44","unstructured":"Lempitsky V. and Zisserman A. , Learning to count objects in images, Advances in Neural Information Processing Systems 23 (2010)."},{"key":"10.3233\/JIFS-224081_ref45","first-page":"615","article-title":"Towards perspective-free object counting with deep learning","author":"Onoro-Rubio","year":"2016","journal-title":"European conference on computer vision"},{"key":"10.3233\/JIFS-224081_ref46","first-page":"1125","article-title":"Image-to-image translation with conditional adversarial networks","author":"Isola","year":"2017","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"10.3233\/JIFS-224081_ref47","first-page":"423","article-title":"Extremely overlapping vehicle counting","author":"Guerrero-G\u00f3mez-Olmedo","year":"2015","journal-title":"Iberian Conference on Pattern Recognition and Image Analysis"},{"key":"10.3233\/JIFS-224081_ref48","first-page":"4145","article-title":"Drone-based object counting by spatially regularized regional proposal network","author":"Hsieh","year":"2017","journal-title":"Proceedings of the IEEE international conference on computer vision"},{"key":"10.3233\/JIFS-224081_ref49","first-page":"2547","article-title":"Multi-source multi-scale counting in extremely dense crowd images","author":"Idrees","year":"2013","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"10.3233\/JIFS-224081_ref50","first-page":"2150178","article-title":"Multi-feature analysis for automated brain stroke classification using weighted Gaussian na\u00efve Bayes classifier","author":"Sekar","year":"2021","journal-title":"Journal of Circuits, Systems and Computers"},{"key":"10.3233\/JIFS-224081_ref51","doi-asserted-by":"crossref","first-page":"2328","DOI":"10.1109\/ICASSP40776.2020.9053780","article-title":"A real-time deep network for crowd counting","author":"Shi","year":"2020","journal-title":"ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"},{"key":"10.3233\/JIFS-224081_ref52","first-page":"2164","article-title":"Weighing counts: Sequential crowd counting by reinforcement learning","author":"Liu","year":"2020","journal-title":"Computer Vision\u2013ECCV 2020"},{"key":"10.3233\/JIFS-224081_ref53","first-page":"2382","article-title":"Encoder-decoder based convolutional neural networks with multi-scale-aware modules for crowd counting","author":"Thanasutives","year":"2021","journal-title":"25th international conference on pattern recognition ICPR"},{"key":"10.3233\/JIFS-224081_ref54","doi-asserted-by":"crossref","first-page":"15233","DOI":"10.1109\/TITS.2021.3138896","article-title":"Crowd counting via segmentation guided attention networks and curriculum loss","author":"Wang","year":"2022","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.3233\/JIFS-224081_ref55","doi-asserted-by":"crossref","first-page":"2576","DOI":"10.1609\/aaai.v35i3.16360","article-title":"To choose or to fuse? scale selection for crowd counting","author":"Song","year":"2021","journal-title":"Proceedings of the AAAI conference on artificial intelligence"},{"key":"10.3233\/JIFS-224081_ref56","first-page":"3486","article-title":"Pcc net: Perspective crowd counting via spatial convolutional network","author":"Gao","year":"2019","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.3233\/JIFS-224081_ref57","doi-asserted-by":"crossref","first-page":"3299","DOI":"10.1109\/ISCAS48785.2022.9937583","article-title":"Tafnet: A three-stream adaptive fusion network for rgb-t crowd counting","author":"Tang","year":"2022","journal-title":"2022 IEEE International Symposium on Circuits and Systems (ISCAS)"},{"key":"10.3233\/JIFS-224081_ref58","first-page":"779","article-title":"You only look once: Unified, real-time object detection","author":"Redmon","year":"2016","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"10.3233\/JIFS-224081_ref59","unstructured":"Ren S. , Wang Y. , He K. Girshick R. and Sun J. , Faster r-cnn: Towards real-time object detection with region proposal networks, Advances in Neural Information Processing Systems (2015)."},{"key":"10.3233\/JIFS-224081_ref60","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1007\/978-3-319-46487-9_48","article-title":"A large contextual dataset for classification, detection and counting of cars with deep learning,ECCV:14th European Conference","author":"Mundhenk","year":"2016","journal-title":"Computer Vision\u2013ECCV 2016:14th European Conference"},{"key":"10.3233\/JIFS-224081_ref61","first-page":"4145","article-title":"Drone-based object counting by spatially regularized regional proposal network","author":"Hsieh","year":"2017","journal-title":"Proceedings of the IEEE international conference on computer vision"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-224081","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T09:20:22Z","timestamp":1769678422000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-224081"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,1]]},"references-count":61,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.3233\/jifs-224081","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,1]]}}}