By comparing multiple target detection algorithms, combined with the particularity of the airport scene, finally an algorithm based on YOLOv5 was selected for airport multi-target detection.. After tuning the parameters according to the loss function and the mean average precision in training, a target detection model adapted to the airport scene is obtained. The data was collected from a high-definition camera at Chengdu Shuangliu Airport, and about 3000 highdefinition pictures were obtained by intercepting video frames. Then the experiment use "LabelImg" software to annotate the data to get the VOC data set. Experimental results show that the average accuracy of the algorithm can reach 85.77%, and it can effectively detect aircraft on the airport scene.
Multi-target Detection in Airport Scene Based on Yolov5
2021-10-20
1107597 byte
Conference paper
Electronic Resource
English
Multi-scale Small Target Detection for Indoor Mobile Rescue Vehicles Based on Improved YOLOv5
Springer Verlag | 2024
|Multi-scale Small Target Detection for Indoor Mobile Rescue Vehicles Based on Improved YOLOv5
Springer Verlag | 2024
|