1. 毕业设计（论文）的内容和要求

人群计数，对图像和视频中的人数进行精确估计在公共安全中存在着实际需求,是基于人头标记信息进行身份识别的一种生物识别技术。

用摄像机或摄像头采集含有人脸的图像或视频流，并自动在图像中检测。

主要包括四个组成部分，分别为：人脸图像采集及检测、人脸图像预处理、人脸图像特征提取与检测。

2. 参考文献

[1] B. Liu and N. Vasconcelos. Bayesian model adaptation for crowd counts. In ICCV, 2015. [2] K. Chen, C. C. Loy, S. Gong, and T. Xiang. Feature mining for localised crowd counting. In BMVC, volume 1, page 3,2012. [3] A. B. Chan and N. Vasconcelos. Bayesian poisson regression for crowd counting. In ICCV, pages 545#8211;551. IEEE, 2009. [4] V. Rabaud and S. Belongie. Counting crowded moving objects. In CVPR, volume 1, pages 705#8211;711. IEEE, 2006. [5] D. Ciresan, U. Meier, and J. Schmidhuber. Multi-column deep neural networks for image classification. In CVPR,pages 3642#8211;3649. IEEE, 2012. [6] M. Wang and X. Wang. Automatic adaptation of a generic pedestrian detector to a specific traffic scene. In CVPR, pages 3401#8211;3408. IEEE, 2011. [7] Zhang, H. Li, X. Wang, and X. Yang. Cross-scene crowd counting via deep convolutional neural networks. In CVPR,2015. [8] M.Wang and X. Wang. Automatic adaptation of a generic pedestrian detector to a specific traffic scene. In CVPR, pages 3401#8211;3408. IEEE, 2011 [9] M. Rodriguez, I. Laptev, J. Sivic, and J.-Y. Audibert. Density-aware person detection and tracking in crowds. In ICCV, pages 2423#8211;2430. IEEE, 2011. [10] W. Ge and R. T. Collins. Marked point processes for crowd counting. In CVPR, pages 2913#8211;2920. IEEE, 2009.

3. 毕业设计（论文）进程安排

2018.12.21-2019.1.16 研究调研课题背景，学习相关技术 2019.1.17-2019.3.1 完成开题报告的撰写 2019.3.2-2019.3.20 完成系统整体的设计，选择合适的元器件 2019.3.21-2019.4.13 完成系统的硬件设计，绘制原理图，完成硬件焊接 2019.4.14-2019.5.9 完成软件设计，程序编写，并烧入硬件调试 2019.5.10-2019.6.2 撰写毕业论文 2019.6.3-2019.6.10 查漏补缺，PPT制作，准备答辩