Abstract
In order to reduce the time spent on class attendance in colleges and universities, an auxiliary sign-in technology based on surveillance cameras was investigated and designed. This paper proposes to use deep learning algorithm to detect and count current number of students and calculate the class attendance rate. Due to the insufficient classroom illumination, densely occluded faces and the blurred image, the system first performs light compensation on the input image, and uses the InceptionV1 convolutional network to generate multiple region proposal for the specific location of the faces, the Long Short-Term Memory is further used to resolve the region proposal to obtain a face frame with maximum confidence. Finally the class attendance statistic is calculated by counting the number of real face frames. Experimental results show that the proposed method significantly improves the detection speed, reducing the computational time from 119 ms to 50 ms per frame on the gtx1060, meanwhile, the detection accuracy is high and robust, which meets the requirements of real-time class attendance detection.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Qi, Y., Liu, F., Jiao, L.: Adaptive reduction immune algorithm for solving large-scale tsp problems. J. Softw. 19(6), 1265–1273 (2008)
Wu, H.: University classroom occupancy statistics system based on surveillance video. Ph.D. dissertation, Shenyang University of Technology (2015)
Shi, Z., Ye, Y., Wu, Y.: Crowd counting method based on ordered spatial pyramid pooling network. Acta Automatica Sinica 42(6), 866–874 (2016)
Liang, R., Liu, X., Ma, X.: High-density population counting method based on surf. J. Comput.-Aided Des. Comput. Graph. 24(12), 1568–1575 (2012)
Jingwei, G.: Research and implementation of Tongji bridge high density population counting method. Ph.D. dissertation, Sun Yat-sen University (2013)
Zhao, M., Zhang, J., Porikli, F., Zhang, C., Zhang, W.: Learning a perspective-embedded deconvolution network for crowd counting. In: IEEE International Conference on Multimedia and Expo, pp. 403–408 (2017)
Marsden, M., Mcguinness, K., Little, S., O’Connor, N.E.: Fully convolutional crowd counting on highly congested scenes, pp. 27–33 (2017)
Walach, E., Wolf, L.: Learning to count with CNN boosting. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 660–676. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_41
Stewart, R., Andriluka, M., Ng, A.Y.: End-to-end people detection in crowded scenes, pp. 2325–2333 (2015)
Lienhart, R., Maydt, J.: An extended set of haar-like features for rapid object detection. In: International Conference on Image Processing, Proceedings, vol. 1, pp. I-900–I-903 (2002)
Freund, Y., Schapire, R.E.: Experiments with a new boosting algorithm. In: Thirteenth International Conference on International Conference on Machine Learning, pp. 148–156 (1996)
Qian, H., Chen, G., Shen, R.: People counting system based on face detection. Comput. Eng. 38(13), 188–191 (2012)
Neubeck, A., Gool, L.V.: Efficient non-maximum suppression. In: International Conference on Pattern Recognition, pp. 850–855 (2006)
Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2
Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6517–6525 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Peng, X., Fang, Z., Gao, Y. (2019). Teaching Assistant and Class Attendance Analysis Using Surveillance Camera. In: Zhai, G., Zhou, J., An, P., Yang, X. (eds) Digital TV and Multimedia Communication. IFTC 2018. Communications in Computer and Information Science, vol 1009. Springer, Singapore. https://doi.org/10.1007/978-981-13-8138-6_35
Download citation
DOI: https://doi.org/10.1007/978-981-13-8138-6_35
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-8137-9
Online ISBN: 978-981-13-8138-6
eBook Packages: Computer ScienceComputer Science (R0)