Video-based Person Re-identification Based on Distributed Cloud Computing

Person re-identification has been a hot research issues in the field of computer vision.In recent years,with the maturity of the theory,a large number of excellent methods have been proposed.However,large-scale data sets and huge networks make training a time-consuming process.At the same time,the parameters and their values generated during the training process also take up a lot of computer resources.Therefore,we apply distributed cloud computing method to perform person re-identification task.Using distributed data storage method,pedestrian data sets and parameters are stored in cloud nodes.To speed up operational efficiency and increase fault tolerance,we add data redundancy mechanism to copy and store data blocks to different nodes,and we propose a hash loop optimization algorithm to optimize the data distribution process.Moreover,we assign different layers of the re-identification network to different nodes to complete the training in the way of model parallelism.By comparing and analyzing the accuracy and operation speed of the distributed model on the video-based dataset MARS,the results show that our distributed model has a faster training speed.

A public Cloud-based China's Landslide Inventory Database(Cs LID): development, zone, and spatiotemporal analysis for significant historical events, 1949-2011

Landslide inventory plays an important role in recording landslide events and showing their temporal-spatial distribution. This paper describes the development, visualization, and analysis of a China's Landslide Inventory Database(Cs LID) by utilizing Google's public cloud computing platform. Firstly, Cs LID(Landslide Inventory Database) compiles a total of 1221 historical landslide events spanning the years 1949-2011 from relevant data sources. Secondly, the Cs LID is further broken down into six zones for characterizing landslide cause-effect, spatiotemporal distribution, fatalities, and socioeconomic impacts based on the geological environment and terrain. The results show that among all the six zones, zone V, located in Qinba and Southwest Mountainous Area is the most active landslide hotspot with the highest landslide hazard in China. Additionally, the Google public cloud computing platform enables the Cs LID to be easily accessible, visually interactive, and with the capability of allowing new data input to dynamically augment the database. This work developed a cyber-landslide inventory and used it to analyze the landslide temporal-spatial distribution in China.

TIFAflow: Enhancing Traffic Archiving System with Flow Granularity for Forensic Analysis in Network Security

The archiving of Internet traffic is an essential function for retrospective network event analysis and forensic computer communication. The state-of-the-art approach for network monitoring and analysis involves storage and analysis of network flow statistic. However, this approach loses much valuable information within the Internet traffic. With the advancement of commodity hardware, in particular the volume of storage devices and the speed of interconnect technologies used in network adapter cards and multi-core processors, it is now possible to capture 10 Gbps and beyond real-time network traffic using a commodity computer, such as n2disk. Also with the advancement of distributed file system （such as Hadoop, ZFS, etc.） and open cloud computing platform （such as OpenStack, CloudStack, and Eucalyptus, etc.）, it is practical to store such large volume of traffic data and fully in-depth analyse the inside communication within an acceptable latency. In this paper, based on well- known TimeMachine, we present TIFAflow, the design and implementation of a novel system for archiving and querying network flows. Firstly, we enhance the traffic archiving system named TImemachine＋FAstbit （TIFA） with flow granularity, i.e., supply the system with flow table and flow module. Secondly, based on real network traces, we conduct performance comparison experiments of TIFAflow with other implementations such as common database solution, TimeMachine and TIFA system. Finally, based on comparison results, we demonstrate that TIFAflow has a higher performance improvement in storing and querying performance than TimeMachine and TIFA, both in time and space metrics.