在SAR图像机动目标自动识别过程中,因目标预筛选阶段采用次优的异常检测策略而产生大量虚假的感兴趣区域(Region of Interest,ROI),这些虚假ROIs很大程度上降低了目标识别的效率。该文提出一种基于多特征联合的序贯鉴别算法来去除虚假R...在SAR图像机动目标自动识别过程中,因目标预筛选阶段采用次优的异常检测策略而产生大量虚假的感兴趣区域(Region of Interest,ROI),这些虚假ROIs很大程度上降低了目标识别的效率。该文提出一种基于多特征联合的序贯鉴别算法来去除虚假ROIs。该算法首先对ROI切片的目标特征做冗余性、鲁棒性和可分离性的定量分析,以选取互补性强、稳定好的最优特征,并按所选特征鉴别性能的优略进行排序,来构建序贯鉴别的观测矢量,然后利用各鉴别特征的统计模型和设定的虚警概率来计算各特征对应判决阈值,最后联合优选的多个特征进行序贯判决。文中利用X波段的MSTAR数据验证了本文的算法,并与二项式距离鉴别算法做性能比较。展开更多
舌诊是中医望诊的重要手段,同时,温度与人体的健康息息相关。为了研究舌面的脏腑功能定位及舌象温度关系的反映,论文提出了一种红外技术的感兴趣区域(region of interest, ROI)模型研究方法。首先,利用葛立恒扫描法和Bezier曲线对多边形...舌诊是中医望诊的重要手段,同时,温度与人体的健康息息相关。为了研究舌面的脏腑功能定位及舌象温度关系的反映,论文提出了一种红外技术的感兴趣区域(region of interest, ROI)模型研究方法。首先,利用葛立恒扫描法和Bezier曲线对多边形ROI模型进行改进;然后,借助U-Net分割网络将提取出的温度信息进行训练与学习,从而做到批量处理舌体温度信息;最后,利用HSV色彩模型进行3D可视化,达成舌象温度分区的可视化研究。此外,为了验证该方法的准确性,实验还对模型截取出的舌体进行了评价指标验证,准确度可以达到0.991 1,分割效果极佳。研究表明:改进后的红外信息提取技术既能直观地观察到舌体的分区状况,也可以完整保留舌体的信息变化,为中医的数据化提供了完整可行性方案。实现了舌体红外信息数据的提取与中医诊断技术的有机结合。解决了中医一体化望诊的舌体信息完整性及准确性问题。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
In order to more accurately detect the accuracy of word-wheel water meter digits, 2000 water meter pictures were produced, and an improved Faster-RCNN algorithm for detecting water meter digits was proposed. The impro...In order to more accurately detect the accuracy of word-wheel water meter digits, 2000 water meter pictures were produced, and an improved Faster-RCNN algorithm for detecting water meter digits was proposed. The improved Faster-RCNN algorithm uses ResNet50 combined with FPN (Feature Pyramid Network) structure instead of the original ResNet50 as the feature extraction network, which can enhance the accuracy of the model for small-sized digit recognition;the use of ROI Align instead of ROI Pooling can eliminate the error caused by the quantization process of the ROI Pooling twice, so that the candidate region is more accurately mapped to the feature map, and the accuracy of the model is further enhanced. The experiment proves that the improved Faster-RCNN algorithm can reach 91.8% recognition accuracy on the test set of homemade dataset, which meets the accuracy requirements of automatic meter reading technology for water meter digital recognition, which is of great significance for solving the problem of automatic meter reading of mechanical water meters and promoting the intelligent development of water meters.展开更多
目前航空货运和客运中锂电池爆炸起火的事故层出不穷,最主要原因在于锂电池内部结构状态发生变化,故锂电池内部结构状态的检测成为机场急需解决的重要问题。因此,本研究提出一种MLP(multi-layer perceptron)特征向量分类方法,该方法首...目前航空货运和客运中锂电池爆炸起火的事故层出不穷,最主要原因在于锂电池内部结构状态发生变化,故锂电池内部结构状态的检测成为机场急需解决的重要问题。因此,本研究提出一种MLP(multi-layer perceptron)特征向量分类方法,该方法首先为锂电池内部结构的识别选择最佳的特征向量和分类器;然后对采集得到的锂电池图像样本进行感兴趣区域(ROI,region of interest)获取、图像裁剪与绘制、特征向量提取和分类器分类处理;最后,根据分类结果找到最佳的特征向量与分类器组合。实验表明:用该方法进行锂电池样本图像分类识别,其结果具有较高的准确率,可以有效降低锂电池在航空运输中的爆炸风险。展开更多
为解决指针式仪表示数读取中识别精度低和算法读取速度慢的问题,提出一种基于戴明回归和感兴趣区域(region of interest, ROI)细化的指针式仪表读数技术.给出了仪表示数读取的算法流程:首先选择ROI,采用基于颜色通道的剪影法和二值化形...为解决指针式仪表示数读取中识别精度低和算法读取速度慢的问题,提出一种基于戴明回归和感兴趣区域(region of interest, ROI)细化的指针式仪表读数技术.给出了仪表示数读取的算法流程:首先选择ROI,采用基于颜色通道的剪影法和二值化形态学操作进行图像预处理;接着运用图像帧差法消除指针的抖动;然后利用ROI细化算法对待识别仪表的指针进行细化;再使用戴明回归法拟合出仪表指针所在直线的方程和斜率;最后根据指针斜率利用角度法计算仪表的实时示数.通过3组试验,测试了该方法的可行性和防抖动能力,比较了戴明回归拟合直线与霍夫直线检测拟合直线的检测精度,还比较了ROI细化算法与全局细化算法的计算速度.结果表明该方法检测的平均误差比霍夫直线检测减小了37.85%,每张图像的平均计算时间比全局细化算法减少了192.717 s,同时具有防抖动能力.展开更多
近年来,异常行为识别算法取得了一定的研究进展,但是针对复杂环境、人体遮挡、动作相似度高等多种挑战,识别算法的适应性、效率、准确性都有待进一步提高。为了解决以上问题,提出了基于特征增强的人体检测与异常行为识别联合算法,首先...近年来,异常行为识别算法取得了一定的研究进展,但是针对复杂环境、人体遮挡、动作相似度高等多种挑战,识别算法的适应性、效率、准确性都有待进一步提高。为了解决以上问题,提出了基于特征增强的人体检测与异常行为识别联合算法,首先将视频序列分别送入人体检测网络和特征加强网络,再采用爱因斯坦求和法将特征加强网络输出的多头卷积注意力特征与人体检测网络输出的热力图特征融合,得到加强融合特征,然后利用检测网络输出的人体目标位置特征信息和ROI Align模块对加强融合特征进行人体ROI(region of interest)区域特征截取,得到人体ROI区域加强融合特征,最后将人体ROI区域加强融合特征送入Transformer时序建模网络模块进行人体行为特征时序建模和识别。所提算法充分利用检测网络中间过程产生的行为主体区域特征,弱化了复杂环境中背景的干扰,同时实现了检测网络的输出特征共享,避免了识别网络的二次特征提取过程,从而提高了网络运行效率,且利用Transformer网络的建模优势,能够充分挖掘人体行为空间特征、时序特征以及之间的跨域特征的优势。实验结果表明:所提算法在提高了网络效率的同时大幅度地提升了网络的识别准确率,达到了预期效果。展开更多
文摘在SAR图像机动目标自动识别过程中,因目标预筛选阶段采用次优的异常检测策略而产生大量虚假的感兴趣区域(Region of Interest,ROI),这些虚假ROIs很大程度上降低了目标识别的效率。该文提出一种基于多特征联合的序贯鉴别算法来去除虚假ROIs。该算法首先对ROI切片的目标特征做冗余性、鲁棒性和可分离性的定量分析,以选取互补性强、稳定好的最优特征,并按所选特征鉴别性能的优略进行排序,来构建序贯鉴别的观测矢量,然后利用各鉴别特征的统计模型和设定的虚警概率来计算各特征对应判决阈值,最后联合优选的多个特征进行序贯判决。文中利用X波段的MSTAR数据验证了本文的算法,并与二项式距离鉴别算法做性能比较。
文摘热轧带钢是钢铁行业的重要产品,其表面缺陷是影响产品质量的重要因素。针对传统缺陷检测算法存在的过程繁琐、精度不足和效率低下等问题,提出一种基于改进更快速区域卷积神经网络(faster region-based convolutional neural network,Faster R-CNN)的检测算法,实现对热轧带钢表面缺陷的高效、高精度检测。首先,采用特征相加的方法对底层细节特征和高层语义特征进行融合;然后,采用精准的感兴趣区域池化(precise region of interest pooling,Precise ROI Pooling)获取固定大小的特征向量,避免特征出现位置偏差;最后,利用均值偏移聚类算法对带钢数据集进行聚类,获得适用于热轧带钢表面缺陷检测的先验框尺寸。实验结果表明,所提算法在热轧带钢表面缺陷检测数据集上的平均精度均值达到了85.34%,检测速度为23.5帧/s,且鲁棒性良好,满足实际的工业检测需求。
文摘舌诊是中医望诊的重要手段,同时,温度与人体的健康息息相关。为了研究舌面的脏腑功能定位及舌象温度关系的反映,论文提出了一种红外技术的感兴趣区域(region of interest, ROI)模型研究方法。首先,利用葛立恒扫描法和Bezier曲线对多边形ROI模型进行改进;然后,借助U-Net分割网络将提取出的温度信息进行训练与学习,从而做到批量处理舌体温度信息;最后,利用HSV色彩模型进行3D可视化,达成舌象温度分区的可视化研究。此外,为了验证该方法的准确性,实验还对模型截取出的舌体进行了评价指标验证,准确度可以达到0.991 1,分割效果极佳。研究表明:改进后的红外信息提取技术既能直观地观察到舌体的分区状况,也可以完整保留舌体的信息变化,为中医的数据化提供了完整可行性方案。实现了舌体红外信息数据的提取与中医诊断技术的有机结合。解决了中医一体化望诊的舌体信息完整性及准确性问题。
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.
文摘In order to more accurately detect the accuracy of word-wheel water meter digits, 2000 water meter pictures were produced, and an improved Faster-RCNN algorithm for detecting water meter digits was proposed. The improved Faster-RCNN algorithm uses ResNet50 combined with FPN (Feature Pyramid Network) structure instead of the original ResNet50 as the feature extraction network, which can enhance the accuracy of the model for small-sized digit recognition;the use of ROI Align instead of ROI Pooling can eliminate the error caused by the quantization process of the ROI Pooling twice, so that the candidate region is more accurately mapped to the feature map, and the accuracy of the model is further enhanced. The experiment proves that the improved Faster-RCNN algorithm can reach 91.8% recognition accuracy on the test set of homemade dataset, which meets the accuracy requirements of automatic meter reading technology for water meter digital recognition, which is of great significance for solving the problem of automatic meter reading of mechanical water meters and promoting the intelligent development of water meters.
文摘目前航空货运和客运中锂电池爆炸起火的事故层出不穷,最主要原因在于锂电池内部结构状态发生变化,故锂电池内部结构状态的检测成为机场急需解决的重要问题。因此,本研究提出一种MLP(multi-layer perceptron)特征向量分类方法,该方法首先为锂电池内部结构的识别选择最佳的特征向量和分类器;然后对采集得到的锂电池图像样本进行感兴趣区域(ROI,region of interest)获取、图像裁剪与绘制、特征向量提取和分类器分类处理;最后,根据分类结果找到最佳的特征向量与分类器组合。实验表明:用该方法进行锂电池样本图像分类识别,其结果具有较高的准确率,可以有效降低锂电池在航空运输中的爆炸风险。
文摘为解决指针式仪表示数读取中识别精度低和算法读取速度慢的问题,提出一种基于戴明回归和感兴趣区域(region of interest, ROI)细化的指针式仪表读数技术.给出了仪表示数读取的算法流程:首先选择ROI,采用基于颜色通道的剪影法和二值化形态学操作进行图像预处理;接着运用图像帧差法消除指针的抖动;然后利用ROI细化算法对待识别仪表的指针进行细化;再使用戴明回归法拟合出仪表指针所在直线的方程和斜率;最后根据指针斜率利用角度法计算仪表的实时示数.通过3组试验,测试了该方法的可行性和防抖动能力,比较了戴明回归拟合直线与霍夫直线检测拟合直线的检测精度,还比较了ROI细化算法与全局细化算法的计算速度.结果表明该方法检测的平均误差比霍夫直线检测减小了37.85%,每张图像的平均计算时间比全局细化算法减少了192.717 s,同时具有防抖动能力.
文摘近年来,异常行为识别算法取得了一定的研究进展,但是针对复杂环境、人体遮挡、动作相似度高等多种挑战,识别算法的适应性、效率、准确性都有待进一步提高。为了解决以上问题,提出了基于特征增强的人体检测与异常行为识别联合算法,首先将视频序列分别送入人体检测网络和特征加强网络,再采用爱因斯坦求和法将特征加强网络输出的多头卷积注意力特征与人体检测网络输出的热力图特征融合,得到加强融合特征,然后利用检测网络输出的人体目标位置特征信息和ROI Align模块对加强融合特征进行人体ROI(region of interest)区域特征截取,得到人体ROI区域加强融合特征,最后将人体ROI区域加强融合特征送入Transformer时序建模网络模块进行人体行为特征时序建模和识别。所提算法充分利用检测网络中间过程产生的行为主体区域特征,弱化了复杂环境中背景的干扰,同时实现了检测网络的输出特征共享,避免了识别网络的二次特征提取过程,从而提高了网络运行效率,且利用Transformer网络的建模优势,能够充分挖掘人体行为空间特征、时序特征以及之间的跨域特征的优势。实验结果表明:所提算法在提高了网络效率的同时大幅度地提升了网络的识别准确率,达到了预期效果。