Fall behavior is closely related to high mortality in the elderly,so fall detection becomes an important and urgent research area.However,the existing fall detection methods are difficult to be applied in daily life d...Fall behavior is closely related to high mortality in the elderly,so fall detection becomes an important and urgent research area.However,the existing fall detection methods are difficult to be applied in daily life due to a large amount of calculation and poor detection accuracy.To solve the above problems,this paper proposes a dense spatial-temporal graph convolutional network based on lightweight OpenPose.Lightweight OpenPose uses MobileNet as a feature extraction network,and the prediction layer uses bottleneck-asymmetric structure,thus reducing the amount of the network.The bottleneck-asymmetrical structure compresses the number of input channels of feature maps by 1×1 convolution and replaces the 7×7 convolution structure with the asymmetric structure of 1×7 convolution,7×1 convolution,and 7×7 convolution in parallel.The spatial-temporal graph convolutional network divides the multi-layer convolution into dense blocks,and the convolutional layers in each dense block are connected,thus improving the feature transitivity,enhancing the network’s ability to extract features,thus improving the detection accuracy.Two representative datasets,Multiple Cameras Fall dataset(MCF),and Nanyang Technological University Red Green Blue+Depth Action Recognition dataset(NTU RGB+D),are selected for our experiments,among which NTU RGB+D has two evaluation benchmarks.The results show that the proposed model is superior to the current fall detection models.The accuracy of this network on the MCF dataset is 96.3%,and the accuracies on the two evaluation benchmarks of the NTU RGB+D dataset are 85.6%and 93.5%,respectively.展开更多
In this paper, a new idea that combines Quasi-Accurate Detection of gross errors (QUAD) with discontinuous deformation positive analysis, is brought forward to divide the regional active blocks. The method can improve...In this paper, a new idea that combines Quasi-Accurate Detection of gross errors (QUAD) with discontinuous deformation positive analysis, is brought forward to divide the regional active blocks. The method can improve the demarcation of active blocks for areas lacking with observation data and offer a new train of through for the complete study of the regional deformation of active blocks. In addition, using the Sichuan-Yunnan area as example, the practice process of the method is introduced briefly.展开更多
电子评标过程中,由于目前的辅助招评标系统在智能化程度方面有所欠缺,在评标效率、准确率等方面仍有提升进步的区间。例如,在获取招投标文件图片信息中,现有的辅助招评标系统识别效果较差。为解决现有问题,提出了一种通过使用光学字符识...电子评标过程中,由于目前的辅助招评标系统在智能化程度方面有所欠缺,在评标效率、准确率等方面仍有提升进步的区间。例如,在获取招投标文件图片信息中,现有的辅助招评标系统识别效果较差。为解决现有问题,提出了一种通过使用光学字符识别(Optical Character Recognition,OCR)技术获取招投标文件内容,并对上传图片进行灰度值、图像预处理。该方法可大幅度增强系统智能辅助招评标功能,使用公章检测算法判断招投标文件中公章使用情况,划分标书文字块,从而缩短评标时间,减轻评审标书的工作强度,解决了评标过程中的评审不公正、评标效率低等问题,使招投标项目的评标更加公平、公正、公开。展开更多
基金supported,in part,by the National Nature Science Foundation of China under Grant Numbers 62272236,62376128in part,by the Natural Science Foundation of Jiangsu Province under Grant Numbers BK20201136,BK20191401.
文摘Fall behavior is closely related to high mortality in the elderly,so fall detection becomes an important and urgent research area.However,the existing fall detection methods are difficult to be applied in daily life due to a large amount of calculation and poor detection accuracy.To solve the above problems,this paper proposes a dense spatial-temporal graph convolutional network based on lightweight OpenPose.Lightweight OpenPose uses MobileNet as a feature extraction network,and the prediction layer uses bottleneck-asymmetric structure,thus reducing the amount of the network.The bottleneck-asymmetrical structure compresses the number of input channels of feature maps by 1×1 convolution and replaces the 7×7 convolution structure with the asymmetric structure of 1×7 convolution,7×1 convolution,and 7×7 convolution in parallel.The spatial-temporal graph convolutional network divides the multi-layer convolution into dense blocks,and the convolutional layers in each dense block are connected,thus improving the feature transitivity,enhancing the network’s ability to extract features,thus improving the detection accuracy.Two representative datasets,Multiple Cameras Fall dataset(MCF),and Nanyang Technological University Red Green Blue+Depth Action Recognition dataset(NTU RGB+D),are selected for our experiments,among which NTU RGB+D has two evaluation benchmarks.The results show that the proposed model is superior to the current fall detection models.The accuracy of this network on the MCF dataset is 96.3%,and the accuracies on the two evaluation benchmarks of the NTU RGB+D dataset are 85.6%and 93.5%,respectively.
基金This research was sponsored by the Joint EarthquakeScience Foundation (603002) and 104011)the sub-project of the 10th"Five-Year"Key Research Program ofCEA,entitled"Variation patterns of tectonic deformation and strain accumulation state in the key areas on the Chinesecontinent".
文摘In this paper, a new idea that combines Quasi-Accurate Detection of gross errors (QUAD) with discontinuous deformation positive analysis, is brought forward to divide the regional active blocks. The method can improve the demarcation of active blocks for areas lacking with observation data and offer a new train of through for the complete study of the regional deformation of active blocks. In addition, using the Sichuan-Yunnan area as example, the practice process of the method is introduced briefly.
文摘电子评标过程中,由于目前的辅助招评标系统在智能化程度方面有所欠缺,在评标效率、准确率等方面仍有提升进步的区间。例如,在获取招投标文件图片信息中,现有的辅助招评标系统识别效果较差。为解决现有问题,提出了一种通过使用光学字符识别(Optical Character Recognition,OCR)技术获取招投标文件内容,并对上传图片进行灰度值、图像预处理。该方法可大幅度增强系统智能辅助招评标功能,使用公章检测算法判断招投标文件中公章使用情况,划分标书文字块,从而缩短评标时间,减轻评审标书的工作强度,解决了评标过程中的评审不公正、评标效率低等问题,使招投标项目的评标更加公平、公正、公开。
