Automotive Cockpit Oblivion Detection Based on Improved YOLOv5s
Aimed at the low detection accuracy,slow speed and poor detection of amnesia in current automobile cockpits,an im-proved YOLOv5s automotive cockpit oblivion detection method forgetting is proposed.The detection method uses YOLOv5s as a basic network and improves on this basis.Firstly,the SE attention module is added to a backbone network to strengthen the model's atten-tion to the channel information and improve the target detection performance.Secondly,the space pyramid pool module is improved,and the original SPPF module is improved to the SPPCSPC module,which makes the network pay more attention to the characteristics of the target to be detected.Finally,the GSConv layer is simultaneously introduced to alleviate the detects of depth wise separable convolution(DSC)and fully utilize the advantages of the DSC to achieve significant results in detecting small targets.It ensures the semantic information,balances the accuracy of the model,and improves the detection speed.Experimental results show that com-pared with the original YOLOv5s network,the average mean average precision(mAP)of the improved network is increased by 2％,and the detection accuracy by 3.5％.The improved network has a good improvement effect,which shows the effectiveness of the method.
万方数据
维普
