Motion Estimation (ME) is one of the most intensive computational operations in video compression techniques. Video compression algorithm utilizes numerous standards such as MPEG1, MPEG4 AND H.261, H.264. Compression performance can be increased drastically by efficient motion estimation techniques by which energy is reduced within the residual frames involved in motion compensation. In this paper literature survey of motion estimation especially considering block matching ME (Motion Estimation). In this paper, comparison is made between the already existing block matching algorithms and their limitations in motion estimation along with their applications.

No abstract

Spatiotemporal action recognition is the task of locating and classifying actions in videos. Our project applies this task to analyzing video footage of restaurant workers preparing food, for which potential applications include automated checkout and inventory management. Such videos are quite different from the standardized datasets that researchers are used to, as they involve small objects, rapid actions, and notoriously unbalanced data classes. We explore two approaches -one involving the familiar object detector "You Only Look Once" (YOLO), and another applying a recently proposed analogue for action recognition, "You Only Watch Once" (YOWO). In the first, we design and implement a novel, recurrent modification of YOLO using convolutional LSTMs and explore the various subtleties in the training of such a network. In the second, we study the ability of YOWO's three-dimensional convolutions to capture the spatiotemporal features of our unique dataset, which was generously lent by CMU-based startup Agot.Preprint. Under review.