A method for providing a mechanism for gesture recognition may include causing down-sampling of image data received to generate down-sampled image blocks for a plurality of image frames, causing extraction of a plurality of features from the down-sampled image blocks, determining a moving status of the down-sampled image blocks based on changes in values of respective features in consecutive frames, and determining a direction of motion of an object in the image data based on movement of a first border and a second border of a projection histogram determined based on the moving status of respective down-sampled image blocks. A corresponding apparatus and computer program product are also provided.