|
|
|
| A Classroom Population Statistics Algorithm Based on Human Contour Features |
| YANG Lu |
| Xi‘an Aeronautical Polytechnic Institute, Xi’an, Shaanxi 710089, China |
|
|
|
|
Abstract According to the application scenarios of automatic counting of classrooms, the image processing algorithms based on human contour features and motion detection are studied. The differences in classroom video images, threshold processing, edge extraction, morphological operations, sensitive area identification, human contour feature extraction, etc. The processing steps are used to achieve the result of counting the people number of classroom. At the same time, the layout calculation method of the camera is given in combination with the layout of different classrooms, so as to obtain more effective algorithm effects.The experimental results show that the accuracy of the algorithm is 95.4% in a classroom of 40 people by reasonably arranging the camera positions, which can effectively assist the resource allocation of self-study room.
|
|
Received: 04 September 2019
Published: 18 February 2021
|
|
|
|
|
|
［1］李继秀, 李啸天, 刘子仪. 基于SSD卷积神经网络的公交车下车人数统计［J］. 计算机系统应用, 2019, 28(3): 51-58.
Li J X, Li X T, Liu Z Y. Statistics on Number of People Getting off Bus Based on SSD Convolutional Neural Network［J］. Computer Systems & Applications, 2019, 28(3): 51-58.
［2］Collins R T, Lipton A J, Kanade T, et al. A system for video surveillance and monitoring VASM final report［R］. Pittsburgh: CMU-Rl-TR-00-1 Robotie Institute Carnegie Mellon University, 2000.
［3］Zhao T, Nevatia R. Bayesian Human Segmentation in Crowded Situation［C］//IEEE Conf on Computer Vision and Pattern Recognition. Kauai, Hawaii, 2001.
［4］张烨, 周晓晶, 杨晓童. 基于单目视频的人体运动测量系统［J］. 计量学报, 2019, 40(3): 367-372.
Zhang Y, Zhou X J, Yang X T. Human Motion Measurement System Based on Monocular Videos［J］. Acta Metrologica Sinica, 2019, 40(3): 367-372.
［5］郭晶晶, 许萌, 孔令爱. 基于改进HOG特征的人数统计算法［J］. 信息技术与信息化, 2019, (3): 81-84.
Guo J J, Xu M, Kong L A. The Population Statistics Algorithm Based on Improved HOG Feature［J］. Information Technology and Informatization, 2019, (3): 81-84.
［6］王洪斌, 于菲, 李一骏, 等. 分块特征匹配与局部差分结合的运动目标检测［J］. 计量学报, 2015, 36(4): 352-355.
Wang H B, Yu F, Li Y J, et al. Detection of Moving Object by Combining Block Features Matching and Local Differential［J］. Acta Metrologica Sinica, 2015, 36(4): 352-355.
［7］Wei G, Ai H Z, Lao S H. Adaptive Contour Features in oriented granular space for human detection and segmentation［C］// IEEE Conference on Computer Vision & Pattern Recognition. 2009.
［8］Zhao K, Deng J J, Cheng D Q. Real-time moving pedestrian detection using contour features［J］. Multimedia Tools and Applications, 2018, 77(1):30891-30910.
［9］Cao J, Victor O C, Gilbert O M, et al. A fast background subtraction method using kernel density estimation for people counting［C］// International Conference on Modelling. 2018.
［10］Hernandez J, Morita H, Nakanomiytake M, et al. Movement Detection and Tracking Using Video Frames［C］// 14th Iberoamerican Conference on Pattern Recognition, CIARP 2009. Guadalajara, Jalisco, Mexico, 2009.
［11］朱明旱, 罗大庸, 曹倩霞. 帧间差分与背景差分相融合的运动目标检测算法［J］. 计算机测量与控制, 2005, 13(3): 215-217.
Zhu M H, Luo D Y , Cao Q X. Moving Objects Detection Algorithm Based on Two Consecutive Frames Subtraction and Background Subtraction［J］. Computer Measurement & Control, 2005, 13(3) : 215-217.
［12］刘威, 段成伟, 遇冰, 等. 基于后验HOG特征的多姿态行人检测［J］. 电子学报, 2015, 43(2): 217-224.
Liu W, Duan C W, Yu B, et al. Multi-Pose Pedestrian Detection Based on Posterior HOG Feature［J］. Acta Electronica Sinica, 2015, 43(2): 217-224.
［13］薛震,于莲芝,胡婵娟. 基于图像序列的运动目标检测识别关键技术研究［J］. 计量学报, 2020, 41(12): 1475-1481.
Xue Z, Yu L Z, Hu C J. Research on Key Techniques of Moving Target Detection and Recognition Based on Image Sequence［J］. Acta Metrologica Sinica, 2020, 41(12): 1475-1481. |
|
|
|
2021, Vol. 42 
