针对金属涂层缺陷图像分割中存在特征提取能力弱和分割精度低的问题,提出了一种改进的U^(2)-Net分割模型。首先,在U型残差块(RSU)中嵌入改进的增大感受野模块(receptive field block light,RFB_l),组成新的特征提取层,增强对细节特征的...针对金属涂层缺陷图像分割中存在特征提取能力弱和分割精度低的问题,提出了一种改进的U^(2)-Net分割模型。首先,在U型残差块(RSU)中嵌入改进的增大感受野模块(receptive field block light,RFB_l),组成新的特征提取层,增强对细节特征的学习能力,解决了网络由于感受野受限造成分割精度低的问题;其次,在U^(2)-Net分割模型的解码阶段引入有效的边缘增强注意力机制(contour enhanced attention,CEA),抑制网络中的冗余特征,获取具有详细位置信息的特征注意力图,增强了边界与背景信息的差异性,从而达到更精确的分割效果。实验结果表明,该模型在两个金属涂层剥落与腐蚀数据集上的平均交并比、准确率、查准率、召回率和F_1-measure分别达到80.36%、96.29%、87.43%、84.61%和86.00%,相比于常用的SegNet、U-Net以及U^(2)-Net分割网络的性能都有较大提升。展开更多
针对传统加油站生产环境下卸油作业检测效率低,违规操作引发的安全问题,提出一种基于改进YOLOv3的加油站卸油检测方法。该方法通过在Darknet-53主干输出后引入RFB(Receptive Field Block)感受野模块,使模型能选择合适的感受野对不同尺...针对传统加油站生产环境下卸油作业检测效率低,违规操作引发的安全问题,提出一种基于改进YOLOv3的加油站卸油检测方法。该方法通过在Darknet-53主干输出后引入RFB(Receptive Field Block)感受野模块,使模型能选择合适的感受野对不同尺度目标进行匹配,提高检测精度;结合CSP(Cross Stage Partial)网络并提出RFB_CSP和RFBS_CSP两种结构,实现两条支路的跨级拼接与通道整合,降低计算成本;用K-means++算法对现场的9类目标重新聚类分析,确定合适的网络anchor参数。实验结果表明,优化后的模型对比原始的YOLOv3模型,其平均精度均值提高了2.3%和2.9%,说明优化后的YOLOv3模型在加油站场景检测具有较高的实用价值。展开更多
Aiming at the problem that the existing models have a poor segmentation effect on imbalanced data sets with small-scale samples,a bilateral U-Net network model with a spatial attention mechanism is designed.The model ...Aiming at the problem that the existing models have a poor segmentation effect on imbalanced data sets with small-scale samples,a bilateral U-Net network model with a spatial attention mechanism is designed.The model uses the lightweight MobileNetV2 as the backbone network for feature hierarchical extraction and proposes an Attentive Pyramid Spatial Attention(APSA)module compared to the Attenuated Spatial Pyramid module,which can increase the receptive field and enhance the information,and finally adds the context fusion prediction branch that fuses high-semantic and low-semantic prediction results,and the model effectively improves the segmentation accuracy of small data sets.The experimental results on the CamVid data set show that compared with some existing semantic segmentation networks,the algorithm has a better segmentation effect and segmentation accuracy,and its mIOU reaches 75.85%.Moreover,to verify the generality of the model and the effectiveness of the APSA module,experiments were conducted on the VOC 2012 data set,and the APSA module improved mIOU by about 12.2%.展开更多
文摘由于低照度图像具有对比度低、细节丢失严重、噪声大等缺点,现有的目标检测算法对低照度图像的检测效果不理想.为此,本文提出一种结合空间感知注意力机制和多尺度特征融合(Spatial-aware Attention Mechanism and Multi-Scale Feature Fusion,SAM-MSFF)的低照度目标检测方法 .该方法首先通过多尺度交互内存金字塔融合多尺度特征,增强低照度图像特征中的有效信息,并设置内存向量存储样本的特征,捕获样本之间的潜在关联性;然后,引入空间感知注意力机制获取特征在空间域的长距离上下文信息和局部信息,从而增强低照度图像中的目标特征,抑制背景信息和噪声的干扰;最后,利用多感受野增强模块扩张特征的感受野,对具有不同感受野的特征进行分组重加权计算,使检测网络根据输入的多尺度信息自适应地调整感受野的大小.在ExDark数据集上进行实验,本文方法的平均精度(mean Average Precision,mAP)达到77.04%,比现有的主流目标检测方法提高2.6%~14.34%.
文摘针对传统加油站生产环境下卸油作业检测效率低,违规操作引发的安全问题,提出一种基于改进YOLOv3的加油站卸油检测方法。该方法通过在Darknet-53主干输出后引入RFB(Receptive Field Block)感受野模块,使模型能选择合适的感受野对不同尺度目标进行匹配,提高检测精度;结合CSP(Cross Stage Partial)网络并提出RFB_CSP和RFBS_CSP两种结构,实现两条支路的跨级拼接与通道整合,降低计算成本;用K-means++算法对现场的9类目标重新聚类分析,确定合适的网络anchor参数。实验结果表明,优化后的模型对比原始的YOLOv3模型,其平均精度均值提高了2.3%和2.9%,说明优化后的YOLOv3模型在加油站场景检测具有较高的实用价值。
基金Ministry of Science and Technology Basic Resources Survey Special Project,Grant/Award Number:2019FY100900High-level Hospital Construction Project,Grant/Award Number:DFJH2019015+2 种基金National Natural Science Foundation of China,Grant/Award Number:61871021Guangdong Natural Science Foundation,Grant/Award Number:2019A1515011676Beijing Key Laboratory of Robotics Bionic and Functional Research。
文摘Aiming at the problem that the existing models have a poor segmentation effect on imbalanced data sets with small-scale samples,a bilateral U-Net network model with a spatial attention mechanism is designed.The model uses the lightweight MobileNetV2 as the backbone network for feature hierarchical extraction and proposes an Attentive Pyramid Spatial Attention(APSA)module compared to the Attenuated Spatial Pyramid module,which can increase the receptive field and enhance the information,and finally adds the context fusion prediction branch that fuses high-semantic and low-semantic prediction results,and the model effectively improves the segmentation accuracy of small data sets.The experimental results on the CamVid data set show that compared with some existing semantic segmentation networks,the algorithm has a better segmentation effect and segmentation accuracy,and its mIOU reaches 75.85%.Moreover,to verify the generality of the model and the effectiveness of the APSA module,experiments were conducted on the VOC 2012 data set,and the APSA module improved mIOU by about 12.2%.
