I.J. Information Technology and Computer Science, 2016, 8, 13-22 Published Online August 2016 in MECS (http://www.mecs-press.org/) DOI: 10.5815/ijitcs.2016.08.02 Copyright © 2016 MECS I.J. Information Technology and Computer Science, 2016, 8, 13-22 IP Camera Based Video Surveillance Using Object’s Boundary Specification Natalia Chaudhry Department of Computer Sciences, Kinnaird College for Women Lahore, Pakistan E-mail: nataliawr123@gma il.co m Kh. M. Umar Suleman Faculty of IT, University of Central Punjab, Pakistan E-mail: umar.suleman@ucp.edu.pk Abstract —The ability to detect and track object of interest from sequence of frames is a critical and vital problem of many vision systems developed as yet. This paper presents a smart surveillance system that tracks objects of interest in a sequence of frames in their own defined respective boundaries. The objects of interest are registered or saved within the system. We have proposed a unique tracking algorithm using combination of SURF feature matching, Kalman filtering and template matching approach. Moreover, an efficient technique is proposed that is used to refine registered object image, extract object of interest and remove extraneous image area from it. The system will track registered objects in their respective boundaries using real time video generated through two IP cameras positioned in front of each other. Index Terms—SURF feature matching, template matching, Kalman filtering, track, IP cameras. I. INT RODUCT ION Various network based video surveillance software are proposed in industry. There are many benefits offered by IP solutions. Beyond all such advantages, the use of coax cables has been eliminated. Network technology allows IP cameras to be administered and viewed, even though the operators are located far away. Video surveillance system finds events of interest in various aspects. Many video surveillance systems have been introduced so far. One of them is NUUO surveillance system. It allows setting up the software to detect when defined objects are removed from areas being monitored by surveillance system. Apart from this, system for tracking a moving object, license plate recognition, face recognition and tracking, finding pedestrian in infrared videos, system for monitoring and alerting based on animal behavior and a system for detection of abnormal motion in video stream have also been introduced. The ability to detect and track object of interest from sequence of frames is a critical and vital problem of many vision systems developed so far. The above mentioned systems notify the user merely on detecting motion and other activity. Each object of interest in a scene has common tracking criteria. This paper introduces a video surveillance system that allows tracking of registered objects. The process of cropping out and saving object of interest from the given frame is referred to as registration of that object of interest. The proposed surveillance system will allow monitoring of different registered objects under a certain boundary that is defined and personalized for each object by the user and it notifies the user about theft of object only if it is found missing for predefined duration in its own defined boundary. This boundary is known as virtual fence for that object. If the object is flipped then the registered image of the object will not match with the current image of the object. Our video surveillance system caters this using an efficient algorithm known as auto-registration. In it, registered object image is modified and updated with object's current image to ensure correct object detection for monitoring in future. Rest of the paper is organized as: Section 2 contains description of work done related to video surveillance. Section 3 describes the architecture of the system. Section 4 contains the description of each module involved in a system. Section 5 contains experiments and results. Section 6 concludes the paper. Section 7 contains future recommendations. II. RELATED WORK Various surveillance systems have been developed to date. Vital task in each of these video surveillance systems includes object detection and tracking. Some of the video surveillance system projects are surveyed as follows. M. Sivarathinabala et al, [1] had proposed an intelligent video surveillance system. Human activity is recognized through image classification using HMM model. The system generates notification alarm when it detects abnormal activity through motion and event detection. H. Shengluan et al, [2] presented a tracking system that hinders the error that arises due to occlusion. This is done through estimations and predictions in Kalman filtering approach. It merely tracks the objects. Y. T. Hwang et al, [3] also presents a tracking system that is based on feature points. Object segmentation is eliminated to lessen the complexity. Feature points are detected and then matched to achieve matching. This matching is followed by tracking. C. Tuscano et al, [4] worked on a project of