In action recognition, the dynamic image (DI) approach is recently proposed to code a video signal to a still image. Since DI descriptor is strongly dependent on first frames, it cannot extract dynamics that do not occur in the first frames or even long dynamics. On the other hand, most of the video frames are not informative for the task of action recognition. Therefore, the authors' intuition is that the process of representing a video using all frames is inefficient. Thus, in this study, they proposed to remove the existing redundancy inside the frames and extract some processed informative images based on the information theory which are called key frames. The proposed method is capable enough to extract sufficient frames regardless of the duration and the position of frames in the entire video. Motivated by this method and DI, they proposed a novel key frames dynamic image (KFDI) approach. Experimental results on popular UCF11, Olympic Sports, and J‐HMDB datasets show the superiority of the proposed KFDI approach compared to the DI in capturing long dynamics of videos for action recognition. Their experiments show KFDI improves the accuracy 2–6%compared to DI.

In this paper, we introduce a likelihood model for tracking the location of object in multiple view systems. Our proposed model transforms conventional nonlinear Euclidean estimation model to an estimation model based on the manifold tangent subspace. In this paper, we show that by decomposition of input noise into two parts and description of model by exponential map, real observations in the Euclidean geometry can be transformed to the manifold tangent subspace. Moreover, by obtained tangent subspace likelihood function, we propose two iterative and noniterative maximum likelihood estimation approaches which numerical results show their good performance.

In this study, the authors propose a distributed form of Kalman filter for non‐linear dynamics as a generalised Kalman consensus filter (GKCF) and prove its stability, analytically. More specifically, the authors obtain the sufficient condition for asymptotical convergence using Lyapunov analysis. For this purpose, the authors propose four lemmas and show that Kalman consensus filter (KCF) in a linear system is a special case of the authors’ proposed GKCF.

Conventional methods for block‐based compressive sensing consider an equal number of samples for all blocks. However, the sparsity order of blocks in natural images could be different and, therefore, a various number of samples could be required for their reconstruction. In this study, the authors propose an adaptive block‐based compressive sensing scheme, which collects a different number of samples from each block. The authors show that by adapting the sampling rate, in addition to reducing the whole required number of measurements, the reconstruction performance would be improved, simultaneously. Simulation results verify the effectiveness of the proposed scheme, especially for multi‐level pixel value images like Mondrian test image.

This paper proposes a new method for digital video watermarking in compressed domain. Both the embedding and extracting phases are performed after entropy decoding. Consequently, fully decompressing the compressed video is not necessary making this scheme an appropriate choice for real-time application. Furthermore, taking the structural information into account leads to presenting a robust watermarking scheme along with less quality degradation. To select suitable coefficients for embedding the watermark, three different aspects, imperceptibility, security, and bit rate increase, have been considered. These performance factors are adjusted by defining three priority matrices. In addition, a content based key is proposed in order to overcome the collusion attack. The flexibility of our method to provide desired characteristic can be expressed as another advantage.

In this paper, a new blind and readable H.264 compressed domain watermarking scheme is proposed in which the embedding/extracting is performed using the syntactic elements of the compressed bit stream. As a result, it is not necessary to fully decode a compressed video stream both in the embedding and extracting processes. The method also presents an inexpensive spatiotemporal analysis that selects the appropriate submacroblocks for embedding, increasing watermark robustness while reducing its impact on visual quality. Meanwhile, the proposed method prevents bit-rate increase and restricts it within an acceptable limit by selecting appropriate quantized residuals for watermark insertion. Regarding watermarking demands such as imperceptibility, bit-rate control, and appropriate level of security, a priority matrix is defined which can be adjusted based on the application requirements. The resulted flexibility expands the usability of the proposed method.

A new approach for image recovery using the anisotropic diffusion equation is developed which is based on the first derivative of the signal in time embedded in family of images with different scales. The diffusion coefficient is determined as a function of the gradient of the signal convolved with a symmetric exponential filter. A new discrete realization is developed for the simultaneous removal of noise and preservation of edges.