"Вестник МГСУ"

Comprehensive distributed safety, control, and monitoring systems applied by companies and organizations of different ownership structure play a substantial role in the present-day society.
Video surveillance elements that ensure image processing and decision making in automated or automatic modes are the essential components of new systems. This paper covers the modeling of video surveillance systems installed in buildings, and the algorithm, or pattern, of video camera placement with due account for nearly all characteristics of buildings, detection and recognition facilities, and cameras themselves. This algorithm will be subsequently implemented as a user application.
The project contemplates a comprehensive approach to the automatic placement of cameras that take account of their mutual positioning and compatibility of tasks.
The project objective is to develop the principal elements of the algorithm of recognition of a moving object to be detected by several cameras. The image obtained by different cameras will be processed. Parameters of motion are to be identified to develop a table of possible options of routes. The implementation of the recognition algorithm represents an independent research project to be covered by a different article. This project consists in the assessment of the degree of complexity of an algorithm of camera placement designated for identification of cases of inaccurate algorithm implementation, as well as in the formulation of supplementary requirements and input data by means of intercrossing sectors covered by neighbouring cameras. The project also contemplates identification of potential problems in the course of development of a physical security and monitoring system at the stage of the project design development and testing.
The camera placement algorithm has been implemented as a software application that has already been pilot tested on buildings and inside premises that have irregular dimensions. The algorithm has an operating pattern that may be used to develop an automated system of video surveillance and control for any building. The constituent elements of the system will be interconnected with account for their peculiarities and technical specifications

In modern integrated monitoring systems and systems of automated control of technological processes there are several essential algorithms and procedures for obtaining primary information about an object and its behavior. The primary information is characteristics of static and moving objects: distance, speed, position in space etc. In order to obtain such information in the present work we proposed to use photos and video detectors that could provide the system with high-quality images of the object with high resolution. In the modern systems of video monitoring and automated control there are several ways of obtaining primary data on the behaviour and state of the studied objects: a multisensor approach (stereovision), building an image perspective, the use of fixed cameras and additional lighting of the object, and a special calibration of photo or video detector.In the present paper the authors develop a method of determining the distances to objects by analyzing a series of images using depth evaluation using defocusing. This method is based on the physical effect of the dependence of the determined distance to the object on the image from the focal length or aperture of the lens. When focusing the photodetector on the object at a certain distance, the other objects both closer and farther than a focal point, form a spot of blur depending on the distance to them in terms of images. Image blur of an object can be of different nature, it may be caused by the motion of the object or the detector, by the nature of the image boundaries of the object, by the object’s aggregate state, as well as by different settings of the photo-detector (focal length, shutter speed and aperture).When calculating the diameter of the blur spot it is assumed that blur at the point occurs equally in all directions. For more precise estimates of the geometrical parameters determination of the behavior and state of the object under study a statistical approach is used to determine the individual parameters and estimate their accuracy. A statistical approach is used to evaluate the deviation of the dependence of distance from the blur from different types of standard functions (logarithmic, exponential, linear). In the statistical approach the evaluation method of least squares and the method of least modules are included, as well as the Bayesian estimation, for which it is necessary to minimize the risks under different loss functions (quadratic, rectangular, linear) with known probability density (we consider normal, lognormal, Laplace, uniform distribution). As a result of the research it was established that the error variance of a function, the parameters of which are estimated using the least squares method, will be less than the error variance of the method of least modules, that is, the evaluation method of least squares is more stable. Also the errors’ estimation when using the method of least squares is unbiased, whereas the mathematical expectation when using the method of least modules is not zero, which indicates the displacement of error estimations. Therefore it is advisable to use the least squares method in the determination of the parameters of the function.In order to smooth out the possible outliers we use the Kalman filter to process the results of the initial observations and evaluation analysis, the method of least squares and the method of least three standard modules for the functions after applying the filter with different coefficients.

The second important problem to be resolved to the algorithm and its software, that comprises an automatic design of a complex closed circuit television system, represents object recognition, by virtue of which an image is transmitted by the video camera. Since imaging of almost any object is dependent on many factors, including its orientation in respect of the camera, lighting conditions, parameters of the registering system, static and dynamic parameters of the object itself, it is quite difficult to formalize the image and represent it in the form of a certain mathematical model. Therefore, methods of computer-aided visualization depend substantially on the problems to be solved. They can be rarely generalized. The majority of these methods are non-linear; therefore, there is a need to increase the computing power and complexity of algorithms to be able to process the image. This paper covers the research of visual object recognition and implementation of the algorithm in the view of the software application that operates in the real-time mode

The recent decade has been the time of the rapid development of communication infrastructure, but very often the structures erected in the middle of the last century are used as a basis for new transmission units and antennas, which are considerably worn out. In this regard the control problems of the infrastructure facilities such as towers and masts are often emerging. Such tasks may be associated with the test required when installing additional equipment and modules, as well as during the scheduled inspection and certification of individual objects in accordance with the legal documents. Timely detection of critical deformations will to a large extent prevent the occurrence of accidents and disasters. For accurate detection of deformations load cells on the basis of the piezoelectric effect and fiber-optic sensors based on Bragg gratings are most commonly used, but in such distributed information measurement systems there are significant drawbacks, which narrow the scope of their possible application. Among the main disadvantages there are: high cost of initial installation and configuration, and the subsequent operation of such systems. Traditional measuring sensors require power, separate line of measurement information signal, as well as lines for supplying control signals. A significant limitation is that any sensor detects deformation or other parameters of the design only for its whole base, thus, active sensors should be installed in structures, in which an altered state was detected by visual inspection or by other means. The emergence of video and photo-detectors with high resolution and other settings to get a high-quality image of the object made it possible to establish the systems for infrastructure objects’ monitoring with the characteristics acceptable for practice. At the heart of such systems there are not only detectors with high sensitivity, but also the algorithms for the objects’ recognition, determination of their geometrical parameters by analyzing a series of images. This is the issue and the subject of this work, which developed the computational algorithms to detect external defects. At the stage of preliminary image processing there is the delineation of characteristic points in the image and the calculation of the optical flow in the area of these points. When determining the defect position, the characteristic points of the image are determined using the detector of Harris-Laplace, which are located in the central part of the image. The characteristic points outside the frame are considered to be background. There is an identification of the changes in characteristic points in the frame in relation to the background by using a pyramidal iterative scheme. In the second stage servo frame focuses on a specific point with the greatest change in relation to the background in the current time. The algorithm for object detection and determination of its parameters includes three procedures: detection procedure start; the procedure of the next image processing; stop procedure for determining the parameters of the object. The method described here can be used to create information-measuring system of monitoring based on the use of photodetectors with high-definition and recognition of defects (color differences and differences in the form compared to the background). Since almost each examination of a building or structure begins with a visual examination and determination of the most probable places of occurrence and presence of the defects, the proposed method can be combined with this stage and it will simplify the process of diagnosing, screening for the development of projects on reconstruction and placement of additional equipment on the existing infrastructure.