吴靖,赵尔敦,林卓成,秦文清.基于注意力与特征融合的工程机械目标检测方法[J].包装工程,2022,43(15):61-67.
WU Jing,ZHAO Er-dun,LIN Zhuo-cheng,QIN Wen-qing.Object Detection Method of Construction Machinery Based on Attentionand Feature Fusion[J].Packaging Engineering,2022,43(15):61-67. |
| 基于注意力与特征融合的工程机械目标检测方法 |
| Object Detection Method of Construction Machinery Based on Attentionand Feature Fusion |
| |
| DOI：10.19554/j.cnki.1001-3563.2022.15.007 |
| 中文关键词: 目标检测 Faster R–CNN 注意力机制 特征融合 |
| 英文关键词: object detection Faster R-CNN attention mechanism feature fusion |
| 基金项目: |
|
| 摘要点击次数: |
| 全文下载次数: |
| 中文摘要: |
| 目的 针对施工环境中工程机械目标大小不一、相互遮挡、工作形态各异等问题，提出一种基于注意力与特征融合的目标检测方法(AT–FFRCNN)。方法 在主干网络中采用ResNet50和特征路径聚合网络PFPN，融合不同尺度的特征信息，在区域建议网络(RPN)和全连接层引入注意力机制，提高目标识别的能力，在损失函数中使用广义交并比(GIoU)，提高目标框的准确性。结果 实验表明，文中提出方法检测准确率比其他方法有较大提高，检测平均准确率(mAP)达到90%以上。结论 能够较好地完成工程机械目标的检测任务。 |
| 英文摘要: |
| The work aims to propose an object detection method based on attention and feature fusion (AT-FFRCNN) aiming at the problems of different size, mutual occlusion and different working forms of construction machinery objects in the construction environment.ResNet50 and feature path aggregation network PFPN were used in the backbone network to fuse feature information of different scales, and an attention mechanism was introduced into the region proposal network (RPN) and fully connected layer to improve the ability of target recognition, and generalized intersection over union (GIoU) was used in the loss function to improve the accuracy of the object box.Experiments indicated that the detection accuracy of the proposed method was greatly improved compared with other methods, and the average detection accuracy (mAP) reached more than 90%. The proposed method can complete the detection task of the construction machinery better. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
渝公网安备 50010702501716号