Application of Improved YOLOV3 Algorithm in Ground Object Detection
Ground target detection is widely used in fields such as traffic safety and drone reconnais-sance due to its broad field of view.Due to the large number and small scale of ground targets,the detec-tion accuracy is not high and the recall rate is low.In order to solve the above problems,an improved al-gorithm based on YOLOV3 is proposed.Firstly,the data set is clustered by dimension,and a new anchor box size is designed.The prior data is integrated into the model to enhance the effectiveness of the detec-tion model.Secondly,the original network model is improved and the target prediction frame loss function of YOLOV3 is optimized.The original sum variance loss is replaced by CIoU loss,which improves the stability of the regression of target prediction box.The experimental results show that the recall rate of the improved algorithm is 11.2％higher than that of YOLOV3 algorithm,and the average accuracy rate(map)of the improved algorithm is increased by 3.36％.The improved algorithm effectively improves the recall rate and average accuracy of the detection algorithm,and is better than the original YOLOV3 algo-rithm in the performance of ground target detection.
NETL
NSTL
万方数据
