基于改进YOLOv5m的室内停车位检测

Indoor Parking Space Detection Based on Improved YOLOv5m

针对现有检测算法在室内停车场景下对目标停车位检测精度不足、检测效率较低的情况,在现有的YO-LOv5m中增加了小目标检测层以增强对小目标样本的检测,并在此基础上引入一种坐标注意力机制来减少冗余信息输入,提升检测精度。同时建立包含8100张地下车位图像的大型室内停车场标注数据集,并在此数据集上进行实验。该方法的平均检测精度(mAP)为98.214%,准确率为97.254%,召回率为96.548%。结果显示该算法大大提高了模型精度、停车位检测性能以及模型检测的实时性,在室内停车场景的停车位检测上具有可行性。

Aiming at the situation that the existing detection algorithm has insufficient detection accuracy and low detection efficiency of target parking space under the indoor parking lot scene,a small target detection layer is added to the existing YOLOv5m to enhance the detection of small target samples,and a coordinate attention mechanism is introduced on this basis to reduce redundant information input and improve de-tection accuracy.At the same time,a large-scale indoor parking lot labeling dataset containing 8100 underground parking space images is es-tablished,and experiments are carried out on this dataset,the mean average precision(mAP)of the method is 98.214%,the accuracy rate is 97.254%,and the recall rate is 96.548%,the results show that the algorithm greatly improves the accuracy of the model,the performance of parking space detection and the real-time detection of the model,and is feasible in the detection of parking spaces in indoor parking lots.