Search

It is very important for autonomous driving vehicles to accurately detect objects such as vehicles and pedestrians on the road in real time. Aiming at the problems of missed detection and poor detection effect of small targets in the autonomous driving scene, this paper proposes an automatic driving target detection algorithm that improves the YOLOv7 algorithm. Firstly, it modifies the modules in the network to expand the receptive field, reduces the size of the receptive field module, and improves the speed of the model and enhances the ability to extract image feature information. Secondly, the paper introduces the BRA attention mechanism at the output of the backbone network to improve the model's ability to small target objects. Finally, it replaces the original CIOU loss function of the algorithm with the EIOU loss function to minimize the difference between the height and width of the predicted frame and the real frame, and speeds up the convergence of the model while achieving better positioning results. The experimental results show that: on the KITTI dataset, when the improved YOLOv7 algorithm performs target detection, its mAP reaches 94.7%, which is 3.1 percentage points higher than the original YOLOv7 algorithm, and it has achieved higher detection accuracy in small target object detection. It effectively improves the model's detection effect on small targets. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Test & Measurement Technology is the property of Publishing Center of North University of China and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Automobile Technology is the property of Automobile Technology Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Rolling Stock (1002-7602) is the property of Rolling Stock Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Automotive Engineer (1674-6546) is the property of Auto Engineering Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Automotive Digest is the property of Automotive Digest Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Automotive Engineer (1674-6546) is the property of Auto Engineering Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Automotive Digest is the property of Automotive Digest Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Coal Science & Technology (0253-2336) is the property of Coal Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Ordnance Equipment Engineering is the property of Chongqing University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Chongqing University of Technology (Natural Science) is the property of Chongqing University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Chongqing University of Technology (Natural Science) is the property of Chongqing University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Shanghai Jiao Tong University (1006-2467) is the property of Journal of Shanghai Jiao Tong University Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of China Sciencepaper is the property of China Sciencepaper and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

To satisfy the actual demand for interpretability and prediction accuracy in judicial practice, we in this paper propose an intelligent sentencing method based on the probabilistic graphical model (PGM). This method is built on the cornerstone of sentencing factors. The parameters are estimated by using the maximum likelihood criterion, and the predicted value is obtained by calculating the mathematical expectation of distribution. Experimental result on dangerous driving shows that the prediction accuracy of the method is better than that based on comparison models, such as decision tree and neural network. Meanwhile, this method has good interpretability as well. [ABSTRACT FROM AUTHOR]

Driver fatigue/drowsiness is one of the important causes of serious traffic accidents and results in so many people deaths or injuries, but also substantial directly and indirectly economic expenses. Therefore, many countries make great effort on how to detect drowsiness during driving. In this paper, we introduce the recent developments of driver fatigue/drowsiness detection technology of world wide and try to classify the existing methods into several kinds according to different features measured, and analyzed. Finally, the challenges faced to fatigue/drowsiness detection technology and the development trend are presented.

A study on distant vision, visual sense and colour vision in 2,218 motor vehicle drivers in Inner Mongolia Region was carried out and the effect of age on vision was analysed. The results showed that vision in drivers diminish with increasing age and the age threshold for visual acuity was 45 years. This paper discusses the normal values of vision in two age groups of pre-and-after the threshold age line, and these results may offer a scientific basis for drawing up occupational examination standards for drivers at their posts or under training.

Unreliable channel links resulted from signal blocks in the vehicular Ad-hoc network( VANET) has caused frequent data lost in the broadcast. As the lost data might contain safety-related information,any data loss in the broadcast can lead to serious crashes and accidents on the vehicle safety driving. To enhance the broadcast reliability in the VANET,this paper proposed a greedy piggyback algorithm( GPA) by exploring the advantage of cooperative piggybacking. All the vehicles in the VANET were allowed to select and piggyback some received messages in each vehicle ’s periodical broadcast,which helped other neighboring vehicles to recover the lost data. To solve the vehicle broadcast island problem,it also proposed another mutual learning algorithm based on GPA( MLPA),and each vehicle could learn some global information from other vehicles’ piggybacking decisions to enhance the broadcast reliability. The simulation results show that GPA and MLPA can dramatically improve the broadcast reliability to 0. 85 and 0. 95 respectively in the VANET,and it also can reduce the network load and broadcast delay. This algorithm can be promoted to other wireless network which has a high request on real time and reliability. [ABSTRACT FROM AUTHOR]

In a traffic system with HOV lanes, considering two modes of driving alone and carpooling, we proposed three kinds of travel cost functions for potential commuters such as carpoolers in HOV lanes, driving alone users and carpoolers in general purpose lanes. Assume that all commuters will experience a random travel time with discrete distribution during their trip, this paper compared the commuters' equilibrium choices of travel mode and travel route under the framework of cumulative prospect theory and expected utility theory. In addition, the sensitivity analysis on the proportion of driving alone users, the individual preference such as the reference point were conducted. The resultant observations show that the individuals' risk preference and reference dependence definitely affect the commuters' choices on the travel mode and travel route. When the proportion of driving alone users exceeds a critical value, the carpooling users will be better than driving alone users since they have higher cumulative prospect value. However, this critical value will be slightly overestimated under the framework of expected utility theory. [ABSTRACT FROM AUTHOR]

In real world driving drivers have to determine a desired trajectory within the pavement width they can use before following it. Therefore, the model for desired trajectory decision is an indispensable part of the driver model. In this context, we provide a full method used to deicide desired trajectory for complex mountainous highways. The strategy for deciding desired trajectory is uselecting the trajectory point on the pre-view cross section". Then the four objective functions corresponding to minimum trajectory length, minimum trajectory curvature, minimum trajectory curvature changing and lane keeping were presented according to the typical driving pattern on real roads. After that the four constraint conditions of driving within the pavement, obstacle avoiding, lateral driving stability and bend passing ability were presented. The next, the receding horizon algorithm used to determine the desired trajectory for complex highways was designed according to the decision process of a real driver. Examples of trajectory determination on two mountainous roads and a racing track were given in the end of the paper, the results show that the simulated trajectories coincide with the ones we wanted and the ones we observed on real roads, so the reliability of presented models was validated. [ABSTRACT FROM AUTHOR]

In view of the problem of power batteries being frequently charged and discharged at large power in hybrid electric vehicle, the battery/ultra-capacitor hybrid energy storage system (B/UC HESS ) is adopted, which takes advantage of the high power characteristics of ultra-capacitor to improve the performance of storage system. In this paper, two schemes of B/UC HESS are studied: direct battery/ultra-capacitor parallel connection and active battery/ultra-capacitor parallel connection, in which the latter uses DC-DC convertor with zero current transition soft switching as interface to connect battery and ultra-capacitor. The dynamic model for the DC-DC convertor and the models for battery and ultra-capacitor are set up with Matlab simulink and a simulation is conducted with AVL Cruise. The results indicate that the direct parallel scheme doesn't take full use of the capability of ultra-capacitor, while with the active parallel scheme the peak current of battery lowers in pure electric driving and regenerative braking conditions, the variation range of battery end voltage reduces, with an energy efficiency 14. 92 % higher than that of sole battery energy storage system. In addition, its dynamic response performance also improves due to the use of fuzzy PID control algorithm. [ABSTRACT FROM AUTHOR]

Combining with the practical application of driving environment, this paper proposed a vehicle detection method based on improved DBSCAN clustering algorithm using a laser scanner. First, the vehicle and sensor coordinate conversion model was built to fuse the data from the laser scanner and the camera. Then the DBSCAN algorithm was improved to cluster the laser scanner data points and remove the noises at the same time. Based on the models of vehicle shape features, the preceding vehicles could be detected using shape matching. Finally, the result of the detection was projected onto the video image. The tests on running vehicle show that the proposed method can detect the vehicles efficiently in real traffic environment. [ABSTRACT FROM AUTHOR]

Copyright of China Sciencepaper is the property of China Sciencepaper and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The various control strategies of left-turn vehicle in intersection couldn't be evaluated on field, this paper proposed the model of left-turn vehicle trajectory in intersection, then modeled respectively two main types of left-turn vehicle collision a-voidance behavior. It developed an intersection microscopic traffic simulation system by using C# language to simulate and analyzed the collision avoidance behavior. The results show that a reasonable set of collision avoidance behavior in different traffic demands can effectively reduce the average delay time, start-stop times and other indicators of vehicle. The system is suitable for the simulation and evaluation of different traffic control strategies. [ABSTRACT FROM AUTHOR]