Motion Detection for Intelligent Video Surveillance System: A Survey Vaibhavi S. Bharwad Department of Information Technology SVM Institute of Technology Bharuch 392-001, Gujarat, India vaibhavibharwad@gmail.com Kruti J. Dangarwala Department of Computer Engineering / IT SVM Institute of Technology Bharuch 392-001, Gujarat, India krutidangarwala@gmail.com Abstract: Motion detection is a main task for video Surveillance system. In video surveillance, motion detection refers to the capability of the surveillance system to detect motion. Video surveillance is the procedure of finding a moving object or various objects over a period utilizing camera. Video Surveillance is a term given to monitor the behavior of any kind through videos. It requires person to monitor the CCTV and huge volume of memory to record it. One of the major challenges involved is the huge volume of video storage and retrieval of the same on demand. In order to avoid the depletion of human resources and to detect the suspicious behaviors that threaten safety and security, Intelligent Video Surveillance system (IVS) is required Because of key feature of video surveillance, it has a various uses like human-computer associations, security and surveillance, video communication, traffic control, open territories, for example, airports, underground stations, mass events, and so on. This paper present classification of different method which are used for motion detection and survey on different previously proposed system for motion detection. Keywords- Video Surveillance, Moving Object Detection, Motion detection, Kalman filters and Gaussian mixture models. I. INTRODUCTION Motion detection in real time application is an important challenging task in video surveillance systems. A video is a collection of static images or frames and associated audio data. A frame is a single picture or still shot, that is shown as part of a larger video. Motion detection in video acts as a first step for next processing such as tracking, classification of the detected moving object [2]. A field of computer vision is integration and automation of various representations and processes used in vision perception, which includes different techniques that are themselves important, such as statistical decision theory(statistical pattern classification applied to video, general patterns, or otherwise) and image processing (encoding, transmitting and transforming images )[6]. Surveillance is one of the primary applications in Computer vision or evolving information, for the most part of people groups with the end goal of securing. Surveillance applied in electronic equipment such as CCTV cameras, are installed in many places such as airports, parking lots, railway stations and banks [5]. In the past, the video imagery has been mostly utilized as a scientific instrument after an occasion. To take advantage of the video in real-time, a human must monitor the system continuously in order to alert security officers if there is an emergency. Besides, one individual can just watch more or less four cameras at once with great exactness. Hence, this requires classy human resources for real-time video surveillance using recent technology. Motion detection has become a central topic of discussion in field of computer vision because of its extensive variety of uses like video surveillance, monitoring of security at airport, law enforcement, video compression, automatic target identification, marine surveillance and human activity recognition. Several methods have been proposed so forth for object detection, out of which Background Subtraction, Frame differencing, Temporal Differencing and Optical Flow are extensively used traditional methods. Intelligent video surveillance is a well-established commercial technology. Intelligent video surveillance detecting only the moving footage of the human objects [5]. The surveillance system utilizes Network Video Recorder (NVR) and IP cameras. It utilizes scientific calculations to detect moving things in an image. Intelligent video surveillance Solutions permits the user to monitor and secure zones with the security cameras. Processing in an intelligent video surveillance system are: motion detection and recognition, tracking, behavioral analysis and retrieval. These stages include the points of machine vision, pattern analysis, artificial intelligence and data management. The conventional video surveillance frameworks have disadvantage in that a man ought to monitor the closed circuit televisions (CCTV). Henceforth, the requirements for the intelligent video surveillance systems which can monitor and respond to situations in real time have improved due to the high-cost and low-efficiency of the existing ones. In addition, the video surveillance systems using IP cameras have been common and NVR enables a person to keep watching anywhere [5]. Vaibhavi S Bharwad et al, International Journal of Computer Science & Communication Networks,Vol 5(5),267-269 267 ISSN:2249-5789