本文基于YOLOv5对手扶电梯行人的遮挡进行检测,针对电梯场景中行人遮挡导致的检测难的问题,本文在YOLOv5算法的基础上进行了改进。首先,为了解决因遮挡造成的预测框高度重合问题,本文采用了软非极大值抑制(Soft NMS)算法替代传统的NMS算...本文基于YOLOv5对手扶电梯行人的遮挡进行检测,针对电梯场景中行人遮挡导致的检测难的问题,本文在YOLOv5算法的基础上进行了改进。首先,为了解决因遮挡造成的预测框高度重合问题,本文采用了软非极大值抑制(Soft NMS)算法替代传统的NMS算法,该算法通过先对预测框的得分进行衰减处理,然后再进行过滤,从而减少因遮挡导致的人物漏检的情况。其次,针对遮挡导致行人身体可见区域减小、易被忽略的问题,本文在检测端增加了一个微小目标检测头,专门用于检测因遮挡而只部分可见的行人目标,从而提高了模型对这类目标的检测能力。实验结果表明,通过采用以上两种的改进方法对YOLOv5算法进行改进,在电梯行人遮挡检测中能够取得较好的效果。This article is based on YOLOv5 to detect pedestrian occlusion in escalators. To address the problem of difficulty in detecting pedestrian occlusion in elevator scenes, this article improves the YOLOv5 algorithm. Firstly, in order to solve the problem of high overlap of predicted boxes caused by occlusion, this paper adopts the Soft Non Maximum Suppression (Soft NMS) algorithm instead of the traditional NMS algorithm. This algorithm attenuates the scores of predicted boxes first, and then filters them to reduce the occurrence of missing persons caused by occlusion. Secondly, in response to the problem of occlusion causing a reduction in the visible area of pedestrians and being easily overlooked, this paper adds a small object detection head at the detection end, specifically designed to detect pedestrian targets that are only partially visible due to occlusion, thereby improving the model's detection ability for such targets. The experimental results show that by using the above two improvement methods to improve the YOLOv5 algorithm, good results can be achieved in elevator pedestrian occlusion detection.展开更多
To solve the problems of the low accuracy and poor real-time performance of traditional strip steel surface defect detection meth-ods,which are caused by the characteristics of many kinds,complex shapes,and different ...To solve the problems of the low accuracy and poor real-time performance of traditional strip steel surface defect detection meth-ods,which are caused by the characteristics of many kinds,complex shapes,and different scales of strip surface defects,a strip steel surface defect detection algorithm based on improved Faster R-CNN is proposed.Firstly,the residual convolution module is inserted into the Swin Transformer network module to form the RC-Swin Transformer network module,and the RC-Swin Transformer module is introduced into the backbone network of the traditional Faster R-CNN to enhance the ability of the network to extract the global feature information of the image and adapt to the complex shape of the strip steel surface defect.To improve the attention of the network to defects in the image,a CBAM-BiFPN network module is designed,and then the backbone network is combined with the CBAM-BiFPN network to realize the de-tection and fusion of multi-scale features.The RoI align layer is used instead of the RoI pooling layer to improve the accuracy of defect loca-tion.Finally,Soft NMS is used to achieve non-maximum suppression and remove redundant boxes.In the comparative experiment on the NEU-DET dataset,the improved algorithm improves the mean average precision by 4.2%compared with the Faster R-CNN algorithm,and also improves the average precision by 6.1%and 6.7%for crazing defect and rolled-in scale defect,which are difficult to detect with the Faster R-CNN algorithm.The experiments show that the improvements proposed in the paper effectively improve the detection accuracy of the algorithm and have certain practical value.展开更多
文摘本文基于YOLOv5对手扶电梯行人的遮挡进行检测,针对电梯场景中行人遮挡导致的检测难的问题,本文在YOLOv5算法的基础上进行了改进。首先,为了解决因遮挡造成的预测框高度重合问题,本文采用了软非极大值抑制(Soft NMS)算法替代传统的NMS算法,该算法通过先对预测框的得分进行衰减处理,然后再进行过滤,从而减少因遮挡导致的人物漏检的情况。其次,针对遮挡导致行人身体可见区域减小、易被忽略的问题,本文在检测端增加了一个微小目标检测头,专门用于检测因遮挡而只部分可见的行人目标,从而提高了模型对这类目标的检测能力。实验结果表明,通过采用以上两种的改进方法对YOLOv5算法进行改进,在电梯行人遮挡检测中能够取得较好的效果。This article is based on YOLOv5 to detect pedestrian occlusion in escalators. To address the problem of difficulty in detecting pedestrian occlusion in elevator scenes, this article improves the YOLOv5 algorithm. Firstly, in order to solve the problem of high overlap of predicted boxes caused by occlusion, this paper adopts the Soft Non Maximum Suppression (Soft NMS) algorithm instead of the traditional NMS algorithm. This algorithm attenuates the scores of predicted boxes first, and then filters them to reduce the occurrence of missing persons caused by occlusion. Secondly, in response to the problem of occlusion causing a reduction in the visible area of pedestrians and being easily overlooked, this paper adds a small object detection head at the detection end, specifically designed to detect pedestrian targets that are only partially visible due to occlusion, thereby improving the model's detection ability for such targets. The experimental results show that by using the above two improvement methods to improve the YOLOv5 algorithm, good results can be achieved in elevator pedestrian occlusion detection.
基金supported by the National Natural Science Foundation of China(12002138).
文摘To solve the problems of the low accuracy and poor real-time performance of traditional strip steel surface defect detection meth-ods,which are caused by the characteristics of many kinds,complex shapes,and different scales of strip surface defects,a strip steel surface defect detection algorithm based on improved Faster R-CNN is proposed.Firstly,the residual convolution module is inserted into the Swin Transformer network module to form the RC-Swin Transformer network module,and the RC-Swin Transformer module is introduced into the backbone network of the traditional Faster R-CNN to enhance the ability of the network to extract the global feature information of the image and adapt to the complex shape of the strip steel surface defect.To improve the attention of the network to defects in the image,a CBAM-BiFPN network module is designed,and then the backbone network is combined with the CBAM-BiFPN network to realize the de-tection and fusion of multi-scale features.The RoI align layer is used instead of the RoI pooling layer to improve the accuracy of defect loca-tion.Finally,Soft NMS is used to achieve non-maximum suppression and remove redundant boxes.In the comparative experiment on the NEU-DET dataset,the improved algorithm improves the mean average precision by 4.2%compared with the Faster R-CNN algorithm,and also improves the average precision by 6.1%and 6.7%for crazing defect and rolled-in scale defect,which are difficult to detect with the Faster R-CNN algorithm.The experiments show that the improvements proposed in the paper effectively improve the detection accuracy of the algorithm and have certain practical value.
