When the rate of the camera moving is too fast, we obtain largely blurred frames.
Nevertheless, noise (e.g., blocking, blurring, frame freezing, packet loss) due to transmission loss or switching peers in the P2P network can sometimes be an important factor influencing overall performance [34].
By using the intensity gradients of the motion blurred LR frame, we suppress the increase of the intensity gradients at smooth regions in the HR frame.
This is because it becomes difficult to accurately estimate the parameters in the prior distribution of the original HR frame from only the motion blurred LR frames.
Therefore, the original HR frame x (i) depends on the parameters β (i), and the motion blurred LR frames y are generated from the original HR frame x (i) and the motion blur kernels k.
Reason why the probability model simultaneously representing x (i), β (i), and k is used Since the proposed method tries to simultaneously perform the SR and the motion blur removal, we must estimate both of the motion blur kernels k and the original HR frame x (i) from only the motion blurred LR frames y.
In the second case, we considered some attacks including time stretching in video, Gaussian noise, adding blur, frame removal in video, cutting some regions in the frame of video, and converting H.264 video into another video format.
In our scheme, we consider time stretching in video, Gaussian noise, adding blur, frame removal in video, cutting some regions in the frame of video, and converting H.264 video into another video format.
Experimental results show that our proposed technique is robust against to H.264 encoder, time stretching in video, Gaussian noise, adding blur, frame removal in video, and cutting some regions in the frame of video.
The proposed method uses the posterior probability for simultaneously estimating the HR frame and the motion blur kernels from the target motion blurred LR frames.
