Automatic Surveillance: Vision Detection Using Gaussian Processes Analysis

The importance of Video Surveillance is increasing significantly everyday as organizations seek to safe guard their physical, information and capital assets. With the same vigour, the necessity to observe large number of people on roads, tourist spots, traffic lights, etc. is increasing to seek and pull more and more useful information. These demands calls for Smart Video Surveillance, analogous to traditional analog human-force-consuming approaches. This report is focussed to study such various technologies and ideas for implementation in Video Surveillance System. A lot of human resources is used for tracking and surveillance.

[4] Sayyed Mohammad Hosseini (2016) et. al. present that In this paper a new method for detection of camera tampering is proposed. Some examples for camera tampering are: shaking the camera, movement of the camera, occlusion, and rotation of the camera. The tampering may be intentional or unintentional. In the proposed algorithm, in addition to detection of the exact nature of tampering, the exact amount of tampering also can be detected (i.e. the amount and direction of movement). This will help operator in diction making for management in surveillance system. The proposed algorithm detect the shaking using current and previous frames, as well as by constructing a total background based on all frames and building a temporary background based on last 10 frames. The proposed method employs the SURF feature detector to find interest points in both of two backgrounds and compare and match them using MSAC algorithm. The transformation matrix can be obtained to detect the camera movement; camera image zoom and camera rotate. Finally, using the method sobel edge detection the camera occlusion and defocus can be detected. The method also detect the sudden shut downs in camera or images loss. Another feature of the

Interactive video monitoring allows you to see what is going on inside your home. The video integrates seamlessly with the security system. When an alarm is triggered or motion detection is seen by the camera it records video. The video is sent to you

Human detection in video is complicated due several factors such as variable appearance of people, camera positions, and wide range of person poses, illumination variation, brightness, backgrounds, contrast level and human occlusions [ ]. Different people perform the same action differently and the same person performs the same action differently at different times. Due to huge diversity of human body size, appearance, shape and human actions to perform automatically recognize actions are very challenging [12]. Steps for processing a video are video segmentation, motion detection, background modeling, foreground segmentation, object classification, motion tracking, activity recognition, and camera handoff and data fusion [].

We will use the skin color detection technique as it can detect different skin colors under cluttered background .The segmentation considered as an open issue problem itself. The color space used in a specific application plays an essential role in the success of segmentation process,

In this paper, we've got proposed a technique that detects tampering involving facial regions via evaluating the dissimilarity among the brightness distributions. We have considered two cases of tampered images; images with three face and pictures with two faces. For images with three faces, distance comparison between histograms of three faces is carried out for detecting tampered face. For images with two faces, the distance between two faces is checked against a threshold to detect if the image is tampered. Both bin-by-bin procedures and move-bin measures are calculated as distance

Owing to the imperfections of image acquisition systems, the images acquired are subject to various defects that will affect the subsequent processing. Although these defects can sometimes be corrected by adjusting the acquisition hardware, for example by increasing the number of images captured for the same scene and adopting higher quality instruments, such hardware-based solutions are time-consuming and costly. Therefore it is preferable to correct the images, after they have been acquired and digitized, by using computer programs, which are fast and relatively low-cost. For example, to remove noise, smooth filters (including linear and median filters) can be applied; to enhance contrast in low-contrast images, the image histograms can

With the increasing danger of crime, video surveillance attracts much more attention and it has been adopted in different

Nowadays digital cameras which is used to capture images and videos are storing it directly in digital form. But this digital data ie. images or videos are corrupted by various types of noises. It may cause due to some disturbances or may be impulse noise. To suppress noise and improve the image performances we use image processing schemes. In this paper they uses Kalman filter to remove the impulse noise. The Kalman filter is digital signal processing based filter. It estimates three states past, present and future of a system.[10] To remove noise from video sequences they utilize both temporal and spatial information. In the temporal domain, by collecting neighbouring frames based on similarities of all images, to remove noise from a video tracking sequence they given a low-rank matrix recovery phenomena. [11]

The project Smart CCTV camera surveillance system is to enhance the CCTV camera based security systems, which presently exist in different places. The Project Security System by using CCTV Camera is designed using wireless technology. The use of a surveillance system for image detection is becoming more important. An embedded surveillance system is frequently used in the home, office or factory for image processing of the surveillance system and also for traffic moni-toring but this configuration requires a high performance core, which works against some advantages of embedded systems, such as low power consumption and low cost. Some designs propose the use of different sensors to track the sequence of the human body movement. Other researchers construct an external signal to trigger the embedded surveillance system by means of a PIR sensor, which

The basic flow of algorithm is as show in Fig 3 As our aim is to do real time state of mind, detection of human so input image directly taken from webcam video. Therefore, we take few second video as input then extracting the frames from that video. After that number of frames, we apply some basic function on that image to improve the image quality. Colour image more complex for processing so that we convert tis colour image to the grey scale image.

Saliency detection is considered as a preferential allocation of computational resources. Saliency algorithms formulate on detecting the salient object from an individual image. The salient object is separated from the background using a set of novel features, including center surround histogram, color spatial

The captured input image has number plate covered by vehicle body, so by this step only number plate area is detected and extracted from whole body of vehicle. The number plate extraction phase influence the accuracy of ANPR system because all further step depend on the accurate extraction of number plate area. The input to this stage is vehicle image and output is a portion of image containing the exact number plate. Number plate can be distinguished by its features. Instead of processing every pixel, the system processes only the pixels that have these features. The features are derived from number plate format and the characters constituting the plate. Number plate color, rectangular shape of number plate boundary, the color change between the plate background and characters on it etc. can be used for detection and extraction of number plate area. The extraction of Indian number plate is difficult as compared to the foreign number plate because in India there is no standard followed for the aspect ratio of plate. This factor makes the detection and extraction of number plate very difficult. The various methods used for number plate extraction are as follows:-

The method of feature extraction is based on the spatial distribution of the black and white pixels in the image space. We are assuming that the difference of distribution of pixels for each digit are sufficient enough to classify them.

Segmenting or dividing a digital image into region of interests or meaningful structures in general plays a momentous role in quite a few image processing tasks. Image analysis, image visualization, object representation are some of them. The prime objective of segmenting a digital image is to change its representation so that it looks more expressive for image analysis. During the course of action in image segmentation, each and every pixel of the image segmentation is assigned a label or value. The pixels that share the same value also share homogeneous traits. The examples can include color, texture, intensity or some other features. Image segmentation can be defined as the technique to divide the an image f (x, y) into a non empty subset f1, f2, ...., fn which is continuous and disconnected. This step contributes in feature extraction. There are quite a few applications where image segmentation plays a pivotal role. These applications vary from image filtering, face recognition, medical imaging