Research on Right Turn Parking Detection Method for Large Vehicles in Traffic Scenarios
With the gradual implementation of the new regulation requiring large vehicles to come to a complete stop before making a right turn,a detection method for right-turning parking of large vehicles is proposed to address the ineffi-ciency of the existing regulatory approaches.Firstly,improvements are made to the YOLOv7-tiny detection model by introducing an attention mechanism in the ELAN module to enhance the detection performance of large vehicles.Next,a new method for locating the right turn lanes of large vehicles is designed,which improves the accuracy of positioning under different monitoring perspectives by using adaptive lane detection.Finally,the motion trajectory of large vehicles is transformed into sequential data,and a weighted average median filtering algorithm is employed to effectively reduce the noise in the original data.Simultaneously,a weight factor is introduced in the sliding window loss function to further enhance the robustness of the detection method.Experimental results demonstrate that the improved detection model for large vehicles achieves performance improvements on both self-made datasets and publicly available datasets.The method for locating the right turn lanes of large vehicles exhibits stronger generalization ability,and the coverage rate of detected parking time reaches 97.4％.
detection of large vehicleslane positioningfiltering algorithmloss functionparking time detection
万方数据
维普
