No abstract

Urgency of the research. Usually, the software that performs NVR functions on a normal PC is suitable only for certain types of cameras. Accordingly, the use of cameras from many manufacturers in the video surveillance system leads to use a large number of different software. This creates inconvenience to the user because for performing necessary functions (viewing, recording video, etc.) on different cameras it is necessary to run various software. Therefore, there is a need of creation software that would support different types of cameras.Target setting. Non-optimal implementation of software architecture that supports devices of different manufacturers can lead to difficulty in understanding of source code, non-optimal use of network resources and so on. Thus, there is a problem of proper construction of the software architecture in order to eliminate these problems.Actual scientific researches and issues analysis. The analysis of publications allows revealing the general tendencies of building video surveillance architectures, among which decreasing networking and storage costs. Reduction of network costs implies the use of special measures to minimize the total size of transmitted media data. This can be achieved through a video surveillance system architecture that eliminates the retransmission of the same information and in general minimizes the exchange of information in the IP network of video surveillance. So, in publications describes the architecture of a video surveillance system, but not software architecture for such systems.Uninvestigated parts of general matters defining. Now there is no open software architecture that support the IP cameras from different manufactures.The research objective. The objective of this paper is to describe the architecture of software that supports IP cameras and NVRs from leading Chinese manufacturers, such as Hikvision, Dahua, UniView, Aevision, as well as devices that operate on universal protocol Onvif.The statement of basic materials. The architecture that works with different types of cameras should be designed accordingly. First of all it is necessary to build architecture at the level of logical components and then at the level of functional components. Software architecture at the level of logical components consists of Screen, VideoPlayer, VideoSchedule, CameraView, Modu-lesContainer and VideoSender components. Software architecture at the level of functional components consists of Screen, Video-Player, VideoSchedule, CameraView, ModulesContainer, VideoSender, FrameSourcer, FrameSaviour and Logginner components. Conclusions. The proposed architecture allows using many types of cameras in single software, which is much more convenient than using many programs for many types of cameras. It minimize network load by using only one video stream from one channel, allows to connect all the channels of devices of supported manufacturers and to use all necessary functions for video surveillance systems of supported IP cameras. It does not lead to the redundancy o...

Urgency of the research. Typically the recognition process includes the following steps: license plate detection, license plate normalization, segmentation of the license plate image into separate symbols and symbols recognition. The effectiveness of license plate recognition depends on each of the indicated recognition stages, but for recognition of the license plates of different formats the key stages are segmentation and recognition stages. Therefore the development of the recognition method of the license plates symbols of different formats is an actual task. Target setting. Different formats of car numbers have different fonts and different arrangement of characters, which complicates the process of recognizing car numbers. Actual scientific researches and issues analysis. General trends that have been identified by the analysis of publications indicate that for character recognition of car numbers used convolutional neural network, fully connected neural networks, correlation analysis, binarization images and histograms of brightness. Uninvestigated parts of general matters defining. All analyzed methods are well suited for recognition of the symbols of wellvisible license plates. This makes difficult to apply such methods in real conditions as the license plates can be dirty or poorly visible. The research objective. The purpose of the article is to describe the method of recognizing car numbers of different formats, which has a high percentage of correct recognition and can be used to recognize car numbers on the video stream from cameras located above the tracks. The statement of basic materials. For recognition of the symbols of license plates it is suggested to use the brightness histogram of the binarized image, for symbols recognition-a specially created neural network with the ability of recognition the alternative parts of the original image of the license plate and for removing the incorrectly recognized symbols-the list of license plates formats. Conclusions. The proposed method successfully copes with the task of license plate recognition with confidence 95-99 %. But as the test results show the method has several drawbacks. First, this method does not easily recognize the "trash" in the image and often confuses it with the symbol 'I'. Second, on the dirty license plates or on false detection this method repeatedly uses alternative recognition which leads to a significant load on the processor.