With the development of computer neural network and machine vision, human posture detection has become an important research field in machine vision. In this paper, the Openpose human posture recognition algorithm is used to extract the posture characteristic information of traffic police, and the gesture posture of traffic police in traffic command is calculated by the key point information of the human body, so as to judge the gesture instructions of traffic police. Openpose pose recognition algorithm can deal with human body pose recognition in different scenes well.
Road traffic sign recognition includes two parts: traffic sign recognition and lane line recognition. Based on the Hilens deep learning platform provided by Huawei cloud, this paper simulates the whole traffic scene and realizes the function of traffic sign recognition. In the aspect of detection and recognition of landmarks and vehicles, based on yolov3, this paper uses two kinds of backbone networks, Darknet53 and Resnet18, adds interference data features, and uses soft NMS, which improves the robustness and accuracy of the algorithm. The experimental results show that the detection accuracy of traffic signs in this paper can reach 97.09%. In the aspect of lane line detection, aiming at the problem of low accuracy of Hough transform, this paper optimizes it combined with least square method to improve its recognition efficiency.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.