Surveillance systems paradigm envisions the pervasive interconnection and cooperation of interactive devices over the Internet\ninfrastructure. Nevertheless, dissemination and processing of surveillance video amid the Internet of Things (IoT) applications\nbecome a susceptible issue due to the large volume and the significant information of these data. Moreover, surveillance devices on\nIoT have very limited resources such as memory and storage. The actual security methods are not quite appropriate for surveillance\nIoT systems. Thus, a particular cryptosystem technique is required for surveillance data security. In this paper, we\npropose an efficient cryptosystem to secure IoT-based surveillance systems. The proposed cryptosystem framework contains three\nparts. First, a lightweight automatic summarization technique based on a fast histogram-clustering approach is used to extract the\nkeyframes from the surveillance video. Then, we employ a discrete cosine transform (DCT) technique to compress the extracted\ndata size. Finally, the proposed framework performs an efficient image encryption algorithm by employing a discrete fractional\nrandom transform (DFRT). The testing results and analysis confirm the features of the proposed cryptosystem on surveillance\nsystems. The proposed framework is fast and ensures secure and efficient real-time processing by minimizing the transmission\ncost and storage.
Loading....