A New Vehicle Detection Framework Based on Feature-Guided in the Road Scene

Vehicle detection plays a crucial role in the field of autonomous driving technology.However,directly applying deep learning-based object detection algorithms to complex road scene images often leads to subpar performance and slow inference speeds in vehicle detection.Achieving a balance between accuracy and detection speed is crucial for real-time object detection in real-world road scenes.This paper proposes a high-precision and fast vehicle detector called the feature-guided bidirectional pyramid network(FBPN).Firstly,to tackle challenges like vehicle occlusion and significant background interference,the efficient feature filtering module(EFFM)is introduced into the deep network,which amplifies the disparities between the features of the vehicle and the background.Secondly,the proposed global attention localization module(GALM)in the model neck effectively perceives the detailed position information of the target,improving both the accuracy and inference speed of themodel.Finally,the detection accuracy of small-scale vehicles is further enhanced through the utilization of a four-layer feature pyramid structure.Experimental results show that FBPN achieves an average precision of 60.8% and 97.8% on the BDD100K and KITTI datasets,respectively,with inference speeds reaching 344.83 frames/s and 357.14 frames/s.FBPN demonstrates its effectiveness and superiority by striking a balance between detection accuracy and inference speed,outperforming several state-of-the-art methods.

Research on Obstacle Avoidance Method of Intelligent Car Based on Optimized Fuzzy Control Algorithm

In order to realize the accurate obstacle avoidance function of intelligent car, we propose an intelligent car obstacle avoidance system based on optimized fuzzy control algorithm. Firstly, the kinematics model of intelligent car obstacle avoidance is established, and an efficient environment information collection system composed of multiple sensors is designed to realize the comprehensive collection of obstacle information. Then, the optimized fuzzy control system is adopted to improve the position control accuracy and obstacle avoidance ability. Through the physical debugging and joint simulation of the intelligent car fuzzy controller in the MATLAB and Simulink environment, the simulation results show that the control method can make the collision-free path planned by the intelligent car from the initial state to the obstacle avoidance smoother, and at the same time, the obstacle avoidance of the intelligent car. The actual running distance is reduced by about 16%, which can ensure the practicability of the obstacle avoidance system, provide a new guarantee for the safe operation of the car, and also provide a new idea for the development of the unmanned car.