Security is one of the most key concern of people in current world. Advanced surveillance systems are now being used widely for detecting suspicious act in real time. But it also comprises the shortcomings of having a huge memory along with smart encryption system. To alienate these computationally heavy workflows, a smart intruder alert system has been developed which senses motion in real time. Motion detection is attained with a new approach which incorporates PIR sensors with ARM cortexA53 microprocessor. The sensor is used more effectively with GSM modem through efficient communication between them with the help of both coding and required customization. SMS and calls are initiated from GSM based on the data obtained from sensor. The method used in this research provides computationally faster processing and detection comparing with the other systems which is explained in detail in this paper.

A Smart Intruder Alert System Based on Microprocessor and Motion Detection

Nowadays, the human behavior analysis by computer vision techniques has been an interesting issue for researchers. Automatic recognition of actions in video allows automation of many otherwise manually intensive tasks such as video surveillance. Video surveillance system especially for elderly care and their behavior analysis has an important role to take care of aged, impatient or bedridden persons. In this paper, we propose a high accuracy human action classification and recognition method using hidden Markov model classifier. In our approach, first, we use star skeleton feature extraction method to extract extremities of human body silhouette to produce feature vectors as inputs of hidden Markov model classifier. Then, hidden Markov model, which is learned and used in our proposed surveillance system, classifies the investigated behaviors and detects abnormal actions with high accuracy in comparison by other abnormal detection reported in previous works. The accuracy about 94% resulted from confusion matrix approve the efficiency of the proposed method when compared with its counterparts for abnormal action detection.

/pdf/recognition-and-classification-of-human-behavior-in-plj3jke43f.pdf

Recognition and Classification of Human Behavior in Intelligent Surveillance Systems using Hidden Markov Model

In computer vision application object tracking is a challenging problem. Illumination and occlusion are major constraints observed in object tracking. We are focusing on object tracking with partial or full occlusion. Object tracking is done using features like colors and contours. We have proposed a robust Color-based algorithm to track the object and handle occlusion in real time domain. In our algorithm, HSV color model is used and HSV range of the color object to be tracked is selected. Required object area is identified and contour is formed accordingly to track the object. Proposed algorithm is implemented on ARM Cortex-A7 using Open Source Computer Vision (OpenCV) and Linux-embedded platform. The experiment is done using generated real life database and standard unusual crowd activity database. Results showed run time performance, efficiency and accuracy in real time environment.

A real-time color-based object tracking and occlusion handling using ARM cortex-A7

This survey describes the current state-of-the-art in the development of automated visual surveillance systems so as to provide researchers in the field with a summary of progress achieved to date and to identify areas where further research is needed. The ability to recognise objects and humans, to describe their actions and interactions from information acquired by sensors is essential for automated visual surveillance. The increasing need for intelligent visual surveillance in commercial, law enforcement and military applications makes automated visual surveillance systems one of the main current application domains in computer vision. The emphasis of this review is on discussion of the creation of intelligent distributed automated surveillance systems. The survey concludes with a discussion of possible future directions.

Intelligent distributed surveillance systems: a review : Intelligent distributed surveillance systems

In this paper, we present a straightforward numerical algorithm for visual image sequential motion detection based on half quadratic minimization method. As for the standard visual image sequences with RGB color representation, an intuitive way is to convert it to grayscale image to achieve an approximate motion detection with relatively low computational load. Instead, we propose a sequential processing scheme for more accurate detection by utilizing the motion detection algorithm separately and then performing fusion on a higher level. In this way, we extend the motion detection technique for grayscale images to be capable of dealing with visual videos. Experiment results show that the proposed algorithm can provide more robust motion detection performance and be successfully utilized in practical visual surveillance applications.

Visual Image Sequential Motion Detection via Half Quadratic Minimization Method

Surveillance is the monitoring of the behavior, activities, or other changing information, usually of people for the purpose of influencing, managing, directing, or protecting them. As security is becoming the primary concern of society and hence having a security system is becoming a big requirement. Video surveillance plays a vital role in security systems. This paper describes the ability to recognise objects and humans, to describe their actions and interactions from information acquired by sensors using absolute difference motion detection technique. Real-time implementation is achieved by using a Global System for Mobile Communication (GSM) modem for SMS (Short Message Service) notification. The ablity of tracking and recognition of the visual device was implemented using OpenCVTM for displaying an output. The detected objects motion is being captured and stored in HDD.

Shraddha G. Mhatre

Papers

Visual surveillance using absolute difference motion detection