International Journal of Computer Applications (0975 - 8887) Volume 122 - No.13, July 2015 Review of Human Motion Detection based on Background Subtraction Techniques Arwa Darwish Alzughaibi -Taibah University Department of Computer Science and Information, Community College Madinah, Kingdom of Saudi Arabia -University of Technology Sydney Faculty of Engineering and Information Technology Hanadi Ahmed Hakami University of Technology Sydney Faculty of Engineering and Information Technology Zenon Chaczko University of Technology Sydney Faculty of Engineering and Information Technology ABSTRACT For the majority of computer vision applications, the ability to identify and detect objects in motion has become a crucial necessity. Background subtraction, also referred to as foreground detection is an innovation used with image processing and computer vision fields when trying to detect an object in motion within videos from static cameras. This is done by deducting the present image from the image in the background or background module. There has been comprehensive research done in this field as an effort to precisely obtain the region for the use of further processing (e.g. object recognition). This paper provides a review of the human motion detection methods focusing on background subtraction technique. Keywords Motion detection methods, Background subtraction method, Moving object detection 1. INTRODUCTION The general means by which objects in motion are detected within videos from fixed cameras is referred to as foreground detection or background subtraction. This is broadly used as a way to recognize the actions of humans, object tracking, monitoring traffic, computer vision application, and also human computer interaction. For this mechanism, objects in motion, also referred to as the foreground, are required to be disjoined from the static information. This static information is referred as the background, and the background subtraction approach is the process frequently used for this [2] . The image, which is located in the background, ought to be an illustration of the setting with immobile objects, and should be updated regularly in order to adjust to the changing geometry settings and luminance conditions. The notion of background subtraction has been developed to mean more than its actual meaning with challenging models. As a matter of fact, this process has greatly developed into a common and popular method for detecting motion. This innovation utilizes the contrast between the background and current image to determine the region of motion. It also has the ability to supply data which includes information with regards to the object. The easiest method is by using the following equation for the application of differences between the background and current frame. |I (x, y, t) - I (x, y, t - 1)| >Th (1) Where the previous frame, also known as the background frame, is I(x,y,t-1) and deducted from the present or current frame, I(x,y,t). The threshold (Th) is then applied to the complete difference in order to receive the foreground mask. The main parameter in the thresholding method is the preferred threshold value. This can be selected to be either automatic or manual. The justification of this method is the detection of the foreground or objects in motion from the compression between the background frame and input video frame. Nonetheless, any system which detects motion established on background deduction considers the following: —Background deduction should separate the important objects upon initial appearance in a setting. —A suitable pixel-level criterion needs to be established. A pixel that meets the satisfaction of this criterion is considered background and is disregarded. —The model of the background should adhere to light within the setting and the progressive and immediate changes within the background. —Background models need to consider the differences in spatial scales. —The shadow regions that are protruded by the objects in the foreground are detected as objects in motion. —Numerous objects shifting within a setting for short and long intervals. 1