بررسی روش های شمارش جمعیت در تصاویر
  •   آرشیو : نسخه زمستان 1401
  •   کد پذیرش : 1412
  •   موضوع : مهندسی نرم افزار
  • نویسنده/گان : | سیدمحمدحسین جعفری، حسین فقیه علی آبادی
  •   زبان : فارسی
  •   نوع مقاله : پژوهشی
  •   چکیده مقاله به فارسی : در سال‌های اخیر، نیازهای فوری برای شمارش جمعیت و وسایل نقلیه، تحقیقات در مورد شمارش جمعیت و تخمین تراکم را به شدت ارتقا داده است. تخمین دقیق تعداد اشیا در یک تصویر یک کار چالش برانگیز و در عین حال معنادار است و در بسیاری از کاربردها مانند برنامه ریزی شهری و ایمنی عمومی استفاده شده است. خوشبختانه، توسعه تکنیک‌های جمعیت‌شمار را می‌توان به سایر زمینه‌های مرتبط مانند شمارش وسایل نقلیه و بررسی محیطی، بدون در نظر گرفتن ویژگی‌های آن‌ها، تعمیم داد. با بهره مندی از توسعه سریع یادگیری عمیق، عملکرد شمارش تا حد زیادی بهبود یافته است، و سناریوهای کاربردی بیشتر گسترش یافته اند. ما در این مقاله رویکردهای موجود را در چهار دسته مبتنی بر تشخیص، مبتنی بر رگرسیون، مبتنی بر شبکه عصبی کانولوشن و مبتنی بر ویدئو خلاصه می‌کنیم. ما بیشتر در مورد مجموعه داده ها و معیارها برای جامعه شمارش جمعیت توضیح می دهیم و در مورد کار حل مشکل شمارش بر اساس نمونه های کوچک، روش های حاشیه نویسی مجموعه داده¬ها و غیره بحث می کنیم. در نهایت، چالش‌های مختلف پیش روی جمعیت‌شمار و راه‌حل‌های مربوط به آن‌ها را خلاصه می‌کنیم و مجموعه‌ای از روندهای توسعه را در آینده پیشنهاد می‌کنیم.
  •   لیست منابع : [1] Subburaman VB, Descamps A, Carincotte C (2012) Counting people in the crowd using a generic head detector. In: 2012 IEEE ninth international conference on advanced video and signal-based surveillance.
    [2] Zhu L, Li C, Yang Z, Yuan K, Wang S. Crowd density estimation based on classification activation map and patch density level. Neural Computing and Applications. 2020 May;32(9):5105-16.
    [3] Bhuiyan MR, Abdullah J, Hashim N, Al Farid F, Uddin J, Abdullah N, Samsudin MA. Crowd density estimation using deep learning for hajj pilgrimage video analytics. F1000Research. 2021;10.
    [4] Al Farid F, Hashim N, Abdullah J, Bhuiyan MR, Shahida Mohd Isa WN, Uddin J, Haque MA, Husen MN. A Structured and Methodological Review on Vision-Based Hand Gesture Recognition System. Journal of Imaging. 2022 Jun;8(6):153.
    [5] Dong L, Zhang H, Ji Y, Ding Y. Crowd counting by using multi-level density-based spatial information: A Multi-scale CNN framework. Information Sciences. 2020 Aug 1;528:79-91.
    [6] Liu X, Weijer JVD, Bagdanov AD (2018) Leveraging unlabeled data for crowd counting by learning to rank. In: 2018 IEEE/CVF conference on computer vision and pattern recognition (CVPR)
    [7] iu X, van de Weijer J, Bagdanov AD (2019) Exploiting unla beled data in cnns by self-supervised learning to rank. IEEE Trans Pattern Anal Mach Intell 41:1862–1878
    [8] Jing ZO, Liang HE, Binke HU. An incremental learning algorithm based on support vector machine for multi-scenario crowd counting. 微电子学与计算机. 2022;39(2):75-83.
    [9] De Sanctis M, Di Domenico S, Fioravanti D, Abellán EB, Rossi T, Cianca E. RF-Based Device-Free Counting of People Waiting in Line: A Modular Approach. IEEE Transactions on Vehicular Technology. 2022 Jun 13;71(10):10471-84.
    [10] Wang H, Zhang K, Su Z, Lu J, Xiong Z. Graph clustering‐based crowd counting with very limited labelled samples. Electronics Letters. 2020 Jul;56(14):709-12.
    [11] Xu J, Bo C, Wang D. A novel multi-target multi-camera tracking approach based on feature grouping. Computers & Electrical Engineering. 2021 Jun 1;92:107153.
    [12] Liu X, Yang J, Ding W, Wang T, Wang Z, Xiong J. Adaptive mixture regression network with local counting map for crowd counting. InEuropean Conference on Computer Vision 2020 Aug 23 (pp. 241-257). Springer, Cham.
    [13] Zhou D, He Q. Cascaded multi-task learning of head segmentation and density regression for rgbd crowd counting. IEEE Access. 2020 May 29;8:101616-27.
    [14] Sindagi VA, Yasarla R, Babu DS, Babu RV, Patel VM. Learning to count in the crowd from limited labeled data. InEuropean Conference on Computer Vision 2020 Aug 23 (pp. 212-229). Springer, Cham.
    [15] Rodriguez M, Laptev I, Sivic J et al (2011) Density-aware person detection and tracking in crowds. In: IEEE international conference on computer vision, ICCV 2011, Barcelona, Spain, Novem ber 6–13, 2011
    [16] Li J, Huang L, Liu C (2011) Robust people counting in video surveillance: dataset and system. In: 2011 8th IEEE international conference on advanced video and signal based surveillance (AVSS). pp 54–59
    [17] Pham VQ, Kozakaya T, Yamaguchi O et al (2015) Count forest: co-voting uncertain number of targets using random forest for crowd density estimation. In: International conference on computer vision (ICCV 2015)
    [18] Min F, Pei X, Li X et al (2015) Fast crowd density estimation with convolutional neural networks. Eng Appl Artif Intell 43:81–88
    [19] Zhang L, Shi M, Chen Q. Crowd counting via scale-adaptive convolutional neural network. In2018 IEEE Winter Conference on Applications of Computer Vision (WACV) 2018 Mar 12 (pp. 1113-1121). IEEE.
    [20] Shen Z, Xu Y, Ni B et al (2018) Crowd counting via adversarial cross-scale consistency pursuit. IEEE CVF Conf Comput Vis Pattern Recognit 2018:5245–5254
    [21] Liu J, Gao C, Meng D et al (2017) Decidenet: counting varing density crowds through attention guided detection and density estimation. IEEE CVF Conf Comput Vis Pattern Recognit 2018:5197–5206
    [22] Shi M, Yang Z, Xu C et al (2018) Revisiting perspective information for efcient crowd counting. IEEE CVF Conf Comput Vis Pattern Recognit CVPR 2019:7271–7280
    [23] Huang S, Zhou H, Liu Y, Chen R. High-resolution crowd density maps generation with multi-scale fusion conditional GAN. IEEE Access. 2020 Jun 8;8:108072-87.
    [24] Yang J, Zhou Y, Kung S-Y (2018) Multi-scale generative adversarial networks for crowd counting. In: 2018 24th international conference on pattern recognition (ICPR).
    [25] Wang L, Li Y, Xue X (2019) Coda: counting objects via scaleaware adversarial density adaption. IEEE Int Conf Multimed Expo (ICME) 2019:193–198
    [26] Shen Z, Xu Y, Ni B et al (2018) Crowd counting via adversarial cross-scale consistency pursuit. IEEE CVF Conf Comput Vis Pattern Recognit 2018:5245–5254
    [27] Olmschenk G, Hao T, Zhu Z (2018) Crowd counting with minimal data using generative adversarial networks for multiple target regression. In: 2018 IEEE winter conference on applications of computer vision (WACV(
    [28] Sindagi VA, Patel VM. Generating high-quality crowd density maps using contextual pyramid cnns. InProceedings of the IEEE international conference on computer vision 2017 (pp. 1861-1870).
    [29] Shang C, Ai H, Bai B. End-to-end crowd counting via joint learning local and global count. In2016 IEEE International Conference on Image Processing (ICIP) 2016 Sep 25 (pp. 1215-1219). IEEE.
    [30] Liu W, Salzmann M, Fua P (2018) Context-aware crowd count ing. IEEE CVF Conf Comput Vis Pattern Recognit CVPR 2019:5094–5103
    [31] Liu L, Wang H, Li G, Ouyang W, Lin L. Crowd counting using deep recurrent spatial-aware network. arXiv preprint arXiv:1807.00601. 2018 Jul 2.
    [32] Xiong H, Lu H, Liu C et al (2019) From open set to closed set: counting objects by spatial divide-and-conquer. IEEE CVF Int Conf Comput Vis (ICCV) 2019:8361–8370
    [33] Liu X, Yang J, Ding W (2020) Adaptive mixture regression network with local counting map for crowd counting. arXiv :2005.05776
    [34] Ranjan V, Le H, Hoai M. Iterative crowd counting. InProceedings of the European Conference on Computer Vision (ECCV) 2018 (pp. 270-285).
    [35] Xiong F, Shi X, Yeung D-Y (2017) Spatiotemporal modeling for crowd counting in videos. IEEE Int Conf Comput Vis ICCV 2017:5161–5169
    [36] ang Y, Zhan B, Cai W et al (2019) Locality-constrained spatial transformer network for video crowd counting. IEEE Int Conf Multimed Expo ICME 2019:814–819
    [37] Wu X, Xu B, Zheng Y et al (2019) Video crowd counting via dynamic temporal modeling. arXiv:1907.02198
    [38] Zou Z, Shao H, Qu X et al (2019) Enhanced 3d convolutional networks for crowd counting. arXiv:1908.04121
    [39] Zheng H, Lin Z, Cen J et al (2019) Cross-line pedestrian count ing based on spatially-consistent two-stage local crowd density estimation and accumulation. IEEE Trans Circuits Syst Video Technology 29(3):787–799
    [40] He G, Ma Z, Huang B et al (2019) Dynamic region division for adaptive learning pedestrian counting. IEEE Int Conf Mul timed Expo ICME 2019:1120–1125
    [41] Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv:1804.02767
    [42] https://svip-lab.github.io/dataset/campus_dataset.html
    [43] http://www.ee.cuhk.edu.hk/~xgwang/expo.html
    [44] http://iot.ee.surrey.ac.uk:8080/datasets.html
    [45] https://www.crcv.ucf.edu/data/ucf-qnrf/
    [46] https://www.crcv.ucf.edu/data/ucf-cc-50/
    [47] https://grail.cs.washington.edu/projects/bal/venice.html
    [48] http://www.crowd-counting.com/
    [49] Lempitsky V, Zisserman A. Learning to count objects in images. Advances in neural information processing systems. 2010;23.
    [50] Oghaz MM, Khadka AR, Argyriou V et al (2019) Content-aware density map for crowd counting and density estimation. arXiv :1906.07258
    [51] Olmschenk G, Tang H, Zhu Z (2019) Improving dense crowd counting convolutional neural networks using inverse k-nearest neighbor maps and multiscale upsampling.arXiv:1902.05379
    [52] Liu X, Weijer JVD, Bagdanov AD (2018) Leveraging unlabeled data for crowd counting by learning to rank. In: 2018 IEEE/CVF conference on computer vision and pattern recognition (CVPR)
  •   کلمات کلیدی به فارسی : شمارش جمعیت- تصاویر-یادگیری عمیق- شبکه عصبی کانولوشن.
  •   چکیده مقاله به انگلیسی :
  •   کلمات کلیدی به انگلیسی :
  •  صفحات : 1-14
  •   دانلود فایل ( 869.86 KB )