|
Combined with compressive sensing theory and classical background subtraction method, this paper proposes a CS-based secrecy tracking algorithm, provided with confidential characteristic. This algorithm can track target and protect privacy synchronously, so it has the advantage of privacy protection, which other classical background subtraction algorithms doesn't have. In addition, for the introduction of CS, measurement matrix and the process of projection can be viewed as key and encryption of sensitive areas respectively, which can't be decrypted by the decoder if the key is unknown. Simulation results show that our algorithm can effectively reconstruct real image from the incomplete measurements with the right measurement matrix, and can also have the advantage of computational secure which can be more useful in some secrecy applications. |
|
Keywords:Compressed Sensing; background subtraction; secrecy; mesurement matrix; key; structured-random matrix |
|