Rimmert B. Wittebrood

Tackling occlusion in scan rate conversion systems

We present a motion compensated frame rate up-conversion algorithm which aims at reducing the interpolation artefacts in occlusion areas. This algorithm uses motion vectors estimated between two successive frames, and uses the same 2 frames for the up-conversion.

Feature point selection for object-based motion estimation on a programmable device

Recently, we reported on a recursive algorithm enabling real-time object-based motion estimation (OME) for standard definition video on a digital signal processor (DSP). The algorithm approximates the motion of objects in the image with parametric motion models and creates a segmentation mask by assigning the best matching model to image parts on a block-by-block basis. A parameter estimation module determines the parameters of the motion models on a small fraction of the pictorial data called feature points. In this paper, we propose a new, computationally very efficient, feature point selection method that improves the convergence of the motion parameter estimation process.

Real-time recursive motion segmentation of video data

Segmentation is a hot topic for video compression and interpolation. We introduce a recursive algorithm that enables real-time motion segmentation of standard definition video on a DSP. The evaluation of the separate optimization steps is included.

Second generation DSP software for picture rate conversion

Great progress has been made in motion estimation (ME). This has led to a high-quality second-generation scan-rate conversion (SRC) algorithm which runs on a commercially available programmable platform. The new system has a higher quality of motion estimation/compensation and de-interlacing than the first generation. The paper presents the new algorithm, and highlights the advances in performance.

Efficient image segmentation and its application to motion estimation

In this paper, a new concept is introduced for economy image segmentation applicable in an earlier designed object based motion estimation algorithm. The image segmentation is based on simple features, like average grayscale within a segment, and uses spatial-temporal predictions in order to economize the segmentation procedure. Focus is on the segmentation process and the robust application of a non-perfect segmentation mask in the object based motion estimator. In this application, the new image segmentation method helps to improve the motion segmentation, while reducing the operations count. The paper describes both the object-based motion estimation and the block-based image segmentation. Experimental results are described in order to proof the validity of the concept.

Machine learning deconvolution filter kernels for image restoration

In this paper, we propose a novel algorithm to recover a sharp image from its corrupted form by deconvolution. The algorithm learns the deconvolution process. This is achieved by learning the deconvolution filter kernels for the set of learnt basic pixel patterns. The algorithm consists of the offline learning and online filtering stages. In the one-time offline learning stage, the algorithm learns the dictionary of various local characteristics of the pixel patch as the basic pixel patterns from a huge number of natural images in the training database. Later, the deconvolution filter coefficients for each pixel pattern is optimized by using the source and the corrupted image pairs in the training database. In the online stage, the algorithm only needs to find the nearest matching pixel pattern in the dictionary for each pixel and filter it using the filter optimized for the corresponding pixel pattern. Experimental results on natural images show that our method achieves the state-of-art result on an image deblurring. The proposed approach can be applied to recover a sharp image for applications such as camera, HD/UHD TV, document scanning systems etc.