基于卷积目标检测的3D眼球追踪系统深度估计  

Convolution object detection based depth estimation of 3D eye-tracking system

作　　者：潘新星 汪辉[2] 陈灵[1] 祝永新 杨傲雷[1] Pan Xinxing;Wang Hui;Chen Ling;Zhu Yongxin;Yang Aolei(School of Mechatronic Engineering and Automation,Shanghai University,Shanghai 200072,China;Shanghai Advanced Research Institute,Chinese Academy of Sciences,Shanghai 201210,China)

机构地区：[1]上海大学机电工程与自动化学院,上海200072 [2]中国科学院上海高等研究院,上海201210

出　　处：《仪器仪表学报》2018年第10期241-248,共8页Chinese Journal of Scientific Instrument

基　　金：国家重点研发计划(2017YFA0206104);国家自然科学基金(61703262,61873158);上海市科学技术委员会科研计划项目(16511108701,16YF1403700,18ZR1415100);中国科学院国际合作局对外合作重点项目(184131KYSB20160018);张江高科技园区管理委员会项目(2016-14)资助

摘　　要：随着虚拟现实（VR）技术的发展,作为其核心技术之一的眼球追踪越来越受到人们的重视。在传统3D视线估计技术的基础上,提出一种通过卷积目标检测恢复目标区域深度信息的3D眼球追踪实现方法。基于头戴式眼球追踪设备Pupil的世界摄像头采集到的图像信息,利用TensorFlow卷积目标检测框架实现对目标的识别和宽度测量,通过建立检测出的宽度值和实际测量的距离值之间的函数关系,来达到实时估计深度信息的目的。实验数据表明该方法在采样图像分辨率为1 080p的6组定点测试中的平均相对误差只有1.17%,而且实时处理速度可达15 f/s,能够对实时的深度信息做出较为准确的预测。在眼球追踪技术越来越成熟、眼动仪等设备成本逐渐降低的背景下,该研究为眼球追踪技术的进一步发展和应用打下了坚实的基础。With the development of virtual reality technology, eye-tracking, as one of its core technology, is paid more and more people′s attention. On the basis of conventional 3 D gaze estimation technique, in this paper, a 3 D eye-tracking implementation method is proposed, which recovers the depth information of the object region through convolution object detection. Based on the image information collected by the world camera of the Pupil head wearable eye-tracking device, the TensorFlow convolution object detection framework is used to realize object recognition and its width measurement. Through establishing the function relationship between the detected width value and the distance value of actual measurement, the purpose of estimating the depth information in real time is achieved. The experiment data show that the average relative error is only 1.17% in the six sets of fixed-point tests with the sampled image resolution of 1 080 p and the real-time processing speed reaches 15 frames per second, which can make an accurate prediction of the real-time depth information. Under the background that the eye tracking technology is getting more and more mature and the cost of eye trackers and etc. is decreased gradually, this study lays a solid foundation for the further development and application of eye-tracking technology.

关 键 词：眼球追踪 单目视觉 卷积神经网络 针孔相机 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] TH89[自动化与计算机技术—计算机科学与技术]