No abstract

In this thesis, a moving object detection algorithm under dynamic scene is proposed, which is based on ORB feature. Firstly, we extract feature points and match them by using ORB. We then obtain global motion compensation image by parameters of transformation matrix based on the RANSAC method. Finally, we use the inter-frame difference method to achieve the detection of moving targets. The high speed and accuracy of ORB feature point matching method, as well as the effectiveness of the RANSAC method for removing outliers ensure accurate calculation of parameters of affine transformation model. Combined with inter-frame difference method, foreground objects can be detected entirely. Experiment results show that the algorithm can accurately detect moving objects, and to some extent, it can solve the issue of real-time detection.

No abstract

cloud computing is used over network of host servers on Internet to store, process, share and manage rather than local server or personal computer. And there is rapid increase of organization opting for outsourcing data to remote cloud service provider. Customers should pay for the cps storage infrastructure to store and retrieve unlimited amount of data by paying in the measures of gigabytes/month. For more scalability, availability and durability. User might even want their data to get replicated on multiple server across different data centers. More of the copies, more the customer is asked to pay. So, the customers need to have a strong belief that the cps will store all the data copies that are agreed upon in the contract and all the copies should be synchronized with the modifications that has been done by the customers. In this paper, we are trying to propose a map-based provable multi copy dynamic data possession (MB-PMDDP) scheme that has the respective features: The customers will have an proof that the services provider is not cheating by storing only fewer copies The customers will be supported with block-level operation,i.e. block-level modification ,insertion, deletion and append. Only authorized users can access the file copies stored by the cps. The proposed MB-PMDDP is an extension of dynamic single copy schemes. This analysis will be validated on experimental results on a commercial cloud platform and also provide security against clouding serves and identify the corrupted copies by addition modification in the proposed scheme.

No abstract