In this research paper, we describe a moving object detection algorithm in video frame sequences based on interframe temporal information and marked-watershed notion in the intra-spatial domain. The algorithm begins with difference image between two adjacent frames. By applying the Canny operator to the difference image and the current video frame, we are able to confine the distance of the edge pixels between the difference and present image in small values to determine the initial edge mask for the object in motion. The horizontal and vertical filling followed by morphological opening and closing operators are applied to the initial edge mask to obtain initial temporal segmentation mask of the moving object, which is processed by morphological techniques to obtain binary marker image of the foreground and background subject to the watershed transformation. The markers are used to modify multi-scale morphological gradient image of current frame. Finally, the watershed algorithm is performed on the modified gradients to locate the non-stationary objects accurately in the spatial domain. Processed video results show the detection accuracy of 98% and 99% for different video sequences involving fast and slow human motion. In this operation, the proposed technique overcomes the shortcoming of over-segmentation of the watershed algorithm and can effectively extract visually distinct, contextually meaningful moving objects, which may appear randomly in the video sequence.