ABSTRACT
A monocular multi-pose pedestrian ranging algorithm is proposed for the problem that when existing ranging algorithms perform pedestrian ranging from monocular images, the multi-scale variation caused by the different height, body size, posture and angle of pedestrians usually produces huge deviations in the detection results. Firstly, the key point information of the person in the monocular image is acquired using the human key point extraction algorithm openpose, the key point coordinate information of the shoulder is filtered out, the shoulder width is pre-set, the information is fused using C++ API, then the depth distance between the pedestrian and the camera is measured using the improved pinhole imaging ranging model, and finally the data output is processed using the mean filter. Through experimental validation, the algorithm is finally verified on the collected data set to have a very high accuracy within 12m, with an error within 0.2m, and a high improvement in robustness for multi-attitude and multi-angle pedestrian ranging.
- Zhu Kai, Liu Huafeng, Xia Qingyuan. A review of simultaneous positioning and mapping algorithms based on monocular vision[J]. Computer Application Research, 2018, 35(01): 1-6.Google Scholar
- Zhōu xīn, huángxíyuè, lí yù.. Highway lane keeping and distance measurement based on monocular vision[J].Journal of Image and Graphics,2003(05):110-115.Google Scholar
- Chen Dahai,Mo Lin,Yi Xiangyang.Algorithm for measuring target distance and size in fixed camera image[J].Popular Science and Technology,2011(08):1-5.Google Scholar
- de Queiroz Mendes Raul,Ribeiro Eduardo Godinho,dos Santos Rosa Nicolas,Grassi Valdir. On deep learning techniques to boost monocular depth estimation for autonomous navigation[J]. Robotics and Autonomous Systems,2021,136.Google Scholar
- Huang Tongyuan,Yang Xuejiao,Xiang Guohui,Chen Liao.Study on small target pedestrian detection and ranging based on monocular vision[J].Computer Science,2020,47(11):205-211.Google Scholar
- Zhe Cao, Tomas Simon, Shih-En Wei, and Yaser Sheikh. Realtime multi-person 2d pose estimation using part affinity fields. In CVPR, 2017. 1, 2, 3Google ScholarCross Ref
- Yu-Shiuan Tsai,Li-Heng Hsu,Yi-Zeng Hsieh,Shih-Syun Lin. The Real-Time Depth Estimation for an Occluded Person Based on a Single Image and OpenPose Method[J]. Mathematics,2020,8(8).Google Scholar
- Bi Tianteng, Liu Yue, Weng Dongdong, Wang Yongtian. A review of single image depth estimation based on supervised learning[J].Journal of Computer Aided Design and Graphics,2018,30(08):1383-1393.Google Scholar
- Jiang Jing,Zhang Xuesong.Depth estimation method based on computer vision[J].Application of Optoelectronic Technology,2011,26(01):51-55.Google Scholar
- Jiang Zhenjin,Pei Chengming,Yang Liang.Research on Digital Image Processing Method Based on Camera Ranging[J].Journal of Projectiles, Rockets, Rockets and Guidance,2009,29(06):259-262.Google Scholar
- Zhang Faquan,Lu Liping,Shen Mande,Chen Liangyi,Cui Guangzhao.Research on distance measurement method of monocular vision target[J].Acta Photonica Sinica,2009,38(02):453-456Google Scholar
Index Terms
- Monocular Multi-Pose Pedestrian Ranging Algorithm Based on Key Point Detection
Recommendations
Nighttime Pedestrian Ranging Algorithm Based on Monocular Vision
Abstract Since the traditional computer vision ranging algorithm is imperfect in pertinence and precision, night time monocular vision pedestrian ranging method is proposed for vehicular infrared night vision goggles. Firstly, the method calibrated the ...
Robust pedestrian tracking using improved tracking-learning-detection algorithm
ICVGIP '16: Proceedings of the Tenth Indian Conference on Computer Vision, Graphics and Image ProcessingManual analysis of pedestrians for surveillance of large crowds in real time applications is not practical. Tracking-Learning-Detection suggested by Kalal, Mikolajczyk and Matas [1] is one of the most prominent automatic object tracking system. TLD can ...
Pedestrian detection algorithm based on video sequences and laser point cloud
Pedestrian detection is a critical problem in the field of computer vision. Although most existing algorithms are able to detect pedestrians well in controlled environments, it is often difficult to achieve accurate pedestrian detection from video ...
Comments