Aiming at the problem of poor fitting effect of key points of the driver's mouth and eyes during driver fatigue monitoring, a convolutional neural network PFLD-rep based on improved PFLD was proposed. First, the backbone network is structurally re-parameterized, which can not only retain multi-scale parameters but also achieve the calculation speed of a single branch; then introduce the idea of heat map regression to the auxiliary network to improve the spatial expression ability of the network in the mouth and improve fitting. Effect; Add the opening angle of the eyes and mouth to the loss function, and replace the original L2_loss with Wing_loss loss to increase the network's attention to mouth deformation; later, a high-precision comprehensive fatigue judgment criterion will be determined through experiments. The final experimental results show that the IPN value of the PFLD-rep algorithm in the 300W data set reaches 3.68. The algorithm also has a high fitting effect in faces with large deformations, and can be implemented when vehicle-mounted hardware equipment requirements are low. Higher precision monitoring effect.
Aiming at the problem of measuring the height of surrounding obstacles using the monocular fisheye camera of AVM system in parking scenarios, a method of measuring height through inverse perspective transformation and multiple calibration is proposed and verified by simulation experiments. First, the distortion correction of the fish-eye camera and the calculation of the homography transformation matrix are performed to complete the inverse perspective transformation, and the transformation relationship between the original camera image and the vertical plane image is obtained. Secondly, the YOLO-v4 target detection algorithm is used to identify obstacles and return the pixel height of obstacles. Then, according to the calculation formula of monocular camera height measurement and the relationship between pixel distance and object distance established by calibration, the method of measuring obstacle height is determined. Finally, the effectiveness of the method is verified by simulation experiments.
This paper studies the current situation of standards and regulations and test methods of low-speed automatic driving vehicles. Firstly, it introduces the regulations and policies on low-speed automatic driving vehicles formulated by Europe, America and China. Then the application and test status of low-speed automatic driving vehicle are studied. Based on the above discussion, this paper studies the test method for low-speed automatic driving vehicle, and analyzes some test results after the test.
With the rapid development of intelligent driving technology, Lane Keeping Assistance System has been widely used. This paper analyzes the technical characteristics and testing standards of the Lane Keeping Assistance System, researches on the test scenarios and test methods of straight line and curve line, and proposes a reasonable and feasible testing technology scheme. By using auto-driving robot and RT series inertial navigation, the proposed test method and technical scheme are verified.
The related standards of driver condition monitoring have attracted the attention of the industry, since there’re more traffic accidents due to poor driving behaviors. Based on the principles and product status of driver attention monitoring system, and the comparison of the current related test standards, this paper puts forward its test method and scheme. Moreover, the road test of the certain product is conducted, and test methods of driver attention monitoring system are also prospected in this paper.
With the gradual popularization of L2 automatic driving system, there are many products of L2 automatic driving system in the market, and consumers need to understand the quality of L2 automatic driving system more and more. The composition and working principle of the L2 automatic driving system with navigation guidance was described in this article. According to the existing laws and regulations, combined with the special road conditions in China and based on the navigation-guidance test of a vehicle's L2 automatic driving system, a subjective evaluation test method for the open road of the L2 automatic driving system with navigation guidance had been developed, which was suitable for the current technical level
China 's automatic driving main-routes logistics industry is ushering in a new window of development. Enterprises in different fields are closely cooperating in a comprehensive layout, which makes industry ecology is constantly enriched. However, the development problems such as bottleneck of L4 autonomous driving technology, imperfect development system and imperfect laws and regulations are gradually emerging. The application background, application status and development trend of automatic driving main-routes logistics systematically were sorted out in this paper. From the aspects of automatic driving technology, market development system, industry policies and regulations, targeted suggestions for the problems exposed in the development of the industry were proposed. In the future, L3 trucks will continue to promote algorithm iterations. The government and all parties in the industry will improve standards, regulations and supply systems. At the same time, under continuous pressure from foreign brands, automatic driving main-routes logistics in China will continue to develop.
With the continuous development of sensor technology and the increasing requirements of consumers for automobile functions, the blind zone monitoring system is almost standard for middle and high-end models in the market at present. In this paper, a testing method of vehicle-to-vehicle blind spot monitoring system is proposed by using automatic driving robot, inertial navigation combined system and data acquisition device based on the actual road conditions in China. After the actual vehicle test, the test method can accurately read the alarm time and relative distance parameters of the blind spot monitoring system, which verifies the validity and feasibility of the test method, and has reference significance for the automotive inspection industry.
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.