为解决监控视频分辨率不足的问题,在视频流体模型的基础上,提出一种图像超分辨率重建方法。视频流体模型记录了视频对象的整体区域,及区域内各像素的时域对应关系,利用流体区域在不同时刻的像素值进行滤波和拼接,达到去噪、扩展分辨率...为解决监控视频分辨率不足的问题,在视频流体模型的基础上,提出一种图像超分辨率重建方法。视频流体模型记录了视频对象的整体区域,及区域内各像素的时域对应关系,利用流体区域在不同时刻的像素值进行滤波和拼接,达到去噪、扩展分辨率的目的,基于等色线构建视频流体模型,使用视频流体模型实现去噪,以起始帧作为参考图像,并依次在各帧中选择补入流纹,根据补入流纹的相邻流纹计算补入流纹在初始帧的位置,如果所得位置非整数,对参考图像插值拉伸,采用补入流纹中的值代替相关坐标的像素值。实验结果表明,将添加噪声的CIF格式视频重建到2CIF格式,该方法的重建结果比最大后验估计与投影方法、梯度投影等方法的峰值信噪比提高1 d B^4 d B。展开更多
[Objective] The paper is to construct the logistics tracking management system of tropical agricultural products based on supply chain.[Method] With tropical agricultural products in Hainan as study object,based on lo...[Objective] The paper is to construct the logistics tracking management system of tropical agricultural products based on supply chain.[Method] With tropical agricultural products in Hainan as study object,based on logistics supply chain files and electronic tag coding of agricultural products,cold chain temperature and humidity monitoring,vehicle transportation positioning,data exchange of XML Web services and role-based permission dynamic allocation,the multi-level multi-permission and multi-role logistics tracking management system of tropical agricultural products has been established.[Result] The system constructs information exchange platform for various links of logistics supply chain of tropical agricultural products,which realizes the entire quality monitoring and information tracing of agricultural products,thus enhancing the competitiveness of supply chain in company.[Conclusion] The system has good application and extension prospect.展开更多
This paper presents an urban expressway video surveillance and monitoring system for traffic flow measurement and abnormal performance detection. The proposed flow detection module collects traffic flow statistics in ...This paper presents an urban expressway video surveillance and monitoring system for traffic flow measurement and abnormal performance detection. The proposed flow detection module collects traffic flow statistics in real time by leveraging multi-vehicle tracking information. Based on these online statistics, road operating situations can be easily obtained. Using spatiotemporal trajectories, vehicle motion paths are encoded by hidden Markov models. With path division and parameter matching, abnormal performances containing extra low or high speed driving, illegal stopping and turning are detected in real scenes. The traffic surveillance approach is implemented and evaluated on a DM642 DSP-based embedded platform. Experimental results demonstrate that the proposed system is feasible for the detection of vehicle speed, vehicle counts and road efficiency, and it is effective for the monitoring of the aforementioned anomalies with low computational costs.展开更多
Fast-flux is a Domain Name System(DNS)technique used by botnets to organise compromised hosts into a high-availability,loadbalancing network that is similar to Content Delivery Networks(CDNs).Fast-Flux Service Network...Fast-flux is a Domain Name System(DNS)technique used by botnets to organise compromised hosts into a high-availability,loadbalancing network that is similar to Content Delivery Networks(CDNs).Fast-Flux Service Networks(FFSNs)are usually used as proxies of phishing websites and malwares,and hide upstream servers that host actual content.In this paper,by analysing recursive DNS traffic,we develop a fast-flux domain detection method which combines both real-time detection and long-term monitoring.Experimental results demonstrate that our solution can achieve significantly higher detection accuracy values than previous flux-score based algorithms,and is light-weight in terms of resource consumption.We evaluate the performance of the proposed fast-flux detection and tracking solution during a 180-day period of deployment on our university’s DNS servers.Based on the tracking results,we successfully identify the changes in the distribution of FFSN and their roles in recent Internet attacks.展开更多
文摘为解决监控视频分辨率不足的问题,在视频流体模型的基础上,提出一种图像超分辨率重建方法。视频流体模型记录了视频对象的整体区域,及区域内各像素的时域对应关系,利用流体区域在不同时刻的像素值进行滤波和拼接,达到去噪、扩展分辨率的目的,基于等色线构建视频流体模型,使用视频流体模型实现去噪,以起始帧作为参考图像,并依次在各帧中选择补入流纹,根据补入流纹的相邻流纹计算补入流纹在初始帧的位置,如果所得位置非整数,对参考图像插值拉伸,采用补入流纹中的值代替相关坐标的像素值。实验结果表明,将添加噪声的CIF格式视频重建到2CIF格式,该方法的重建结果比最大后验估计与投影方法、梯度投影等方法的峰值信噪比提高1 d B^4 d B。
文摘[Objective] The paper is to construct the logistics tracking management system of tropical agricultural products based on supply chain.[Method] With tropical agricultural products in Hainan as study object,based on logistics supply chain files and electronic tag coding of agricultural products,cold chain temperature and humidity monitoring,vehicle transportation positioning,data exchange of XML Web services and role-based permission dynamic allocation,the multi-level multi-permission and multi-role logistics tracking management system of tropical agricultural products has been established.[Result] The system constructs information exchange platform for various links of logistics supply chain of tropical agricultural products,which realizes the entire quality monitoring and information tracing of agricultural products,thus enhancing the competitiveness of supply chain in company.[Conclusion] The system has good application and extension prospect.
基金The National Key Technology R&D Program of China during the 11th Five-Year Plan Period(No.2009BAG13A04)Jiangsu Transportation Science Research Program(No.08X09)Program of Suzhou Science and Technology(No.SG201076)
文摘This paper presents an urban expressway video surveillance and monitoring system for traffic flow measurement and abnormal performance detection. The proposed flow detection module collects traffic flow statistics in real time by leveraging multi-vehicle tracking information. Based on these online statistics, road operating situations can be easily obtained. Using spatiotemporal trajectories, vehicle motion paths are encoded by hidden Markov models. With path division and parameter matching, abnormal performances containing extra low or high speed driving, illegal stopping and turning are detected in real scenes. The traffic surveillance approach is implemented and evaluated on a DM642 DSP-based embedded platform. Experimental results demonstrate that the proposed system is feasible for the detection of vehicle speed, vehicle counts and road efficiency, and it is effective for the monitoring of the aforementioned anomalies with low computational costs.
基金supported by the National Basic Research Program of China(973 Program)under Grant No.2013CB329603Huawei Innovation Research Program+1 种基金the Opening Project of Key Laboratory of Information Network Security of Ministry of Public Security under Grant No.C11608the National Natural Science Foundation of China under Grant No.61271220
文摘Fast-flux is a Domain Name System(DNS)technique used by botnets to organise compromised hosts into a high-availability,loadbalancing network that is similar to Content Delivery Networks(CDNs).Fast-Flux Service Networks(FFSNs)are usually used as proxies of phishing websites and malwares,and hide upstream servers that host actual content.In this paper,by analysing recursive DNS traffic,we develop a fast-flux domain detection method which combines both real-time detection and long-term monitoring.Experimental results demonstrate that our solution can achieve significantly higher detection accuracy values than previous flux-score based algorithms,and is light-weight in terms of resource consumption.We evaluate the performance of the proposed fast-flux detection and tracking solution during a 180-day period of deployment on our university’s DNS servers.Based on the tracking results,we successfully identify the changes in the distribution of FFSN and their roles in recent Internet attacks.
