The hardware and software of modern integrated security systems are capable of solving problems of any complexity at various industrial, social and domestic facilities. Very important tools of security systems are video surveillance systems, and the requirements for the functional capabilities of the segment are steadily growing.
Integrated Security Systems
A single platform of integrated security systems includes modules for fire-fighting equipment, access control and management, video surveillance or CCTV. Until recently, the functions of the latter have been limited to video monitoring and recording the situation at the facility and the adjacent territory, archiving and storing data. Classic video systems have a number of significant drawbacks:
- Human factor. Ineffective operator work when broadcasting a large amount of information.
- Impossibility of surgical intervention, untimely analysis.
- Significant time costs for searching and identifying events.
The development of digital technology has led to the creation of “smart” automated systems.
Strength in intelligence
The basic principle of an intelligent video surveillance system is video analytics - a technology based on methods and algorithms for pattern recognition and image processing, automated data collection as a result of video stream analysis. Such equipment without human intervention is capable of detecting and tracking in real time the set targets (car, group of people), potentially dangerous situations (smoke, fire, unauthorized interference with the operation of video cameras), programmed events and promptly issue an alarm. By filtering the video data of no interest, the load on communication channels and the archive database is significantly reduced.
The most popular video analytics tool is a face recognition system. Depending on the functions performed and the tasks set, certain requirements are imposed on the equipment.
Firmware
For the effective operation of the system, several types of IP video cameras with various operational characteristics are used. Detection of an object in the controlled territory is fixed by panoramic cameras with a resolution of 1 megapixel and a focal length of 1 mm and scanning devices are pointing at it. These are more advanced cameras (from 2Mp, from 2 mm) that produce recognition by simple techniques (3-4 parameters). To identify the object using cameras with good image quality, sufficient for the application of complex algorithms (from 5 megapixels, 8-12 mm).
The most popular face recognition software Face Intellect (developed by House Control), Face director (Synesis) and VOCORD FaceControl (VOCORD) show:
- High probability of object identification (up to 99%).
- Support for a wide range of camera angles.
- The ability to distinguish persons even in a dense pedestrian mass.
- Variability in the preparation of analytical reports.
Pattern Recognition Basics
Any biometric recognition system is based on identifying the correspondence of the readout physiological characteristics of the personality to a specific predetermined pattern.
Scanning takes place in real time. The IP camera transmits the video stream to the terminal, and the face recognition system determines the correspondence of the image to the photos stored in the database. There are two main methods. The first is based on static principles: according to the results of processing biometric parameters, an electronic sample is created in the form of a unique number corresponding to a specific person. The second method models the “human” approach and is characterized by self-learning and robustness. Identification of a person by video image takes into account age-related changes and other factors (the presence of a hat, beard or mustache, glasses). This technology allows you to work even with old photographs and, if necessary, with x-rays.
Face Search Algorithm
The most common face detection technique is using Haar cascades (sets of masks).
The mask is a rectangular window with a different combination of white and black segments.
The mechanism of the program is as follows: the video frame is covered with a set of masks, and according to the results of the convolution (counting pixels that fall into the white and black sectors), the difference is compared, compared with a certain threshold value.
To improve the work of the classifier, positive (frames where people’s faces are present) and negative (without such) training samples are created. In the first case, the convolution result is higher than the threshold value, in the second case, lower. The face detector with an allowable error determines the sum of the convolutions of all cascades and, when the threshold is exceeded, signals the presence of persons in the frame.
Recognition technology
After detection and localization at the preliminary stage, the brightness and geometric alignment of the image occurs. Further actions — feature calculation and identification — can be carried out by various methods.
When scanning a face full face in a room with excellent illumination, good results are demonstrated by algorithms that work with two-dimensional images. By analyzing the unique points and the distances between them, the face recognition system determines the fact of identification by the coefficients of difference between the "live" image and the registered template.
Three-dimensional technologies are resistant to changes in luminous flux, the permissible deviation from the front angle is up to 45 degrees. Here, not only points and lines are analyzed, but also surface properties (curvature, profile), the metric of the distances between them. For the operation of such algorithms, a maximum video quality of up to 200 frames / s is required. The system is based on stereo video cameras with a matrix of 5 megapixels, high optical resolution and minimized synchronization error. In addition, they are connected by a special clocking cable for transmitting clock pulses.
The state of the modern systems market
The first biometric control systems, due to their high cost, were developed only for state military facilities and only in the mid-90s became available to commercial organizations. The rapid development of technology and microprocessor technology has allowed to increase the accuracy of systems and expand their scope. The leading positions in the market of our country belong to American and Western European manufacturers of security systems. The leader in sales is equipment of ZN Vision Technologies and Visionics corporations. The most promising among domestic developers are research and products of Vokord, NTechLab, Soling, VisionLabs LLC and the MDGs, which, among other things, are also engaged in adapting foreign complexes to Russian conditions.
Computer face control
The most extensive area of ​​contactless identification is the fight against terrorism and crime. The image of the face of the offender is stored in the database. In crowded places (airports, train stations, shopping malls, sports facilities), the human flow is being monitored in real time to identify wanted persons.
The next area is access control control systems: a sample of a photo image on an electronic pass is compared with a model obtained as a result of processing data from video cameras. The procedure takes place instantly, without requiring any additional action from undergoing (as opposed to retinal scanning or fingerprinting).
Another rapidly growing industry is marketing. An interactive billboard, having scanned a person’s face, determines his gender and age, visualizes only the advertisement that will be potentially interesting to the client.
Trends and development prospects
Face recognition systems in the banking sector are in great demand.
Following the results of last year, the management of Post Bank, after installing 50,000 smart cameras in their offices, managed to save millions of rubles by preventing fraud in the lending and payment segments. Experts say that by 2021 the necessary infrastructure network will be created and any operations at ATMs will become possible only after biometric identification of the client’s face.
In the next decade, high technology will open a network of self-service stores: the buyer walks in front of the windows, selects the goods he likes and leaves. The system of recognition of faces and images will determine the identity of the buyer, purchase and write off the necessary amount from his account.
Work is underway to create systems for recognizing the psycho-emotional state. Analysis of human emotions will be in demand in multimedia areas: animation, cinema, the industry of creating computer games.