×

You are using an outdated browser Internet Explorer. It does not support some functions of the site.

Recommend that you install one of the following browsers: Firefox, Opera or Chrome.

Contacts:

+7 961 270-60-01
ivdon3@bk.ru

  • Study of the operation of computer vision methods in conditions of changing illumination for embedded systems

    The article consider the influence of illumination and distance on the recognition quality for various models of neural networks of embedded systems. The platforms on which the testing was carried out, as well as the models used, are described. The results of the study of the influence of illumination on the quality of recognition are presented.

    Keywords: artificial intelligence, computer vision, embedded systems, pattern recognition, YOLO, Inception, Peoplenet, ESP 32, Sipeed, Jetson, Nvidia, Max

  • Comparative analysis of the effectiveness of software tools for splitting videos into frames using the example of the field of road surface quality assessment

    Roads occupy an important place in the life of almost every person. The quality of the coating is the most significant characteristic of the roadway. To evaluate it, there are many systems, among which there are those that analyze the road surface using video information streams. In turn, the video is divided into frames, and the images are used to directly assess the road quality. Splitting video into frames in such systems works based on special software tools. To understand how effective a particular software is, a detailed analysis is needed. In this article, OpenCV, MoviePy and FFMpeg are selected as software tools for analysis. The research material is a two-minute video of the road surface with a frame rate 29.97 frames/s and mp4 format. The average time to get one frame from a video is used as an efficiency indicator. For each of the three software tools, 5 different experiments were conducted in which the frame size in pixels was consistently increased by 2 times: 40000, 80000, 160000, 320000, 640000. Each program has a linear dependence of O(n) average frame retrieving time on resolution, however, FFMpeg has the lowest absolute time indicators, as well as the lowest growth rate of the function, therefore it is the most effective tool compared to the others (OpenCV, MoviePy).

    Keywords: comparison, analysis, effectiveness, software tool, library, program, video splitting, frame size, resolution, road surface

  • Comparison of the effectiveness of edge detection methods in road surface images depending on size and format

    Road surface quality assessment is one of the most urgent tasks in the world. To solve it, there are many systems that mainly interact with images of the roadway. They work on the basis of both traditional methods (machine learning is not used) and machine learning algorithms. Traditional approaches, for example, include methods for edge detection in images that are the object of this study. However, each of the algorithms has certain features. For example, some of them allow to get a processed version of the original photo faster. The following methods were selected for analysis: "Canny algorithm", "Kirsch operator", "Laplace Operator", "Marr-Hildreth algorithm", "Prewitt operator" and "Sobel Operator". The main indicator of effectiveness in the study is the average time to receive the processed photo. The initial material of the experiment is 10 different images of the road surface in 5 sizes (1000x1000, 894x894, 775x775, 632x632, 447x447) in bmp, jpg, png formats. The study found that the "Kirsch operator", "Laplace Operator" and "Prewitt Operator" and "Sobel operator" have a linear dependence of O(n), the "Canny algorithm" and the "Marr-Hildreth algorithm" have a quadratic character of O(n2). The best results are demonstrated by the "Prewitt Operator" and the "Sobel Operator".

    Keywords: comparison, effectiveness, method, edge detection, image, photo, road surface, dependence, size, format

  • Dependence comparison of the effectiveness of neural networks to improve image resolution on format and size

    Roads have a huge impact on the life of a modern person. One of the key characteristics of the roadway is its quality. There are many systems for assessing the quality of the road surface. Such technologies work better with high-resolution images (HRI), because it is easier to identify any features on them. There are a sufficient number of ways to improve the resolution of photos, including neural networks. However, each neural network has certain characteristics. For example, for some neural networks, it is quite problematic to work with photos of a large initial size. To understand how effective a particular neural network is, a comparative analysis is needed. In this study, the average time to obtain the HRI is taken as the main indicator of effectiveness. EDSR, ESPCN, ESRGAN, FSRCNN and LapSRN were selected as neural networks, each of which increases the width and height of the image by 4 times (the number of pixels increases by 16 times). The source material is 5 photos of 5 different sizes (141x141, 200x200, 245x245, 283x283, 316x316) in png, jpg and bmp formats. ESPCN demonstrates the best performance indicators according to the proposed methodology, the FSRCNN neural network also has good results. Therefore, they are more preferable for solving the problem of improving image resolution.

    Keywords: comparison, dependence, effectiveness, neural network, neuronet, resolution improvement, image, photo, format, size, road surface

  • Dependence сomparative analysis of the effectiveness of image quality improvement approaches on the format and size

    Road surface quality assessment is one of the most popular tasks worldwide. To solve it, there are many systems, mainly interacting with images of the roadway. They work on the basis of both traditional methods (without using machine learning) and machine learning algorithms. To increase the effectiveness of such systems, there are a sufficient number of ways, including improving image quality. However, each of the approaches has certain characteristics. For example, some of them produce an improved version of the original photo faster. The analyzed methods for improving image quality are: noise reduction, histogram equalization, sharpening and smoothing. The main indicator of effectiveness in this study is the average time to obtain an improved image. The source material is 10 different photos of the road surface in 5 sizes (447x447, 632x632, 775x775, 894x894, 1000x1000) in png, jpg, bmp formats. The best performance indicator according to the methodology proposed in the study was demonstrated by the "Histogram equalization" approach, the "Sharpening" method has a comparable result.

    Keywords: comparison, analysis, dependence, effectiveness, approach, quality improvement, image, photo, format, size, road surface

  • Analysis of floating point calculations on microcontrollers

    The article discusses methods for optimizing floating point calculations on microcontroller devices. Hardware and software methods for accelerating calculations are considered. Algorithms of Karatsuba and Schönhage-Strassen for the multiplication operation are given. A method for replacing floating-point calculations with integer calculations is proposed. Describes how to use fixed point instead of floating point. The option of using hash memory and code optimization is considered. The results of measuring calculations on the AVR microcontroller are presented.

    Keywords: floating point calculations, fixed point calculations, microcontroller, AVR, ARM

  • A method for determining the elemental composition of sediment from waste from galvanic production

    The article presents the prerequisites for the relevance of the processing and disposal of galvanic sludge generated from industrial enterprises, which in turn occupies numerous areas of land for storage, which harms the environment. An overview of the methods of processing and disposal of electroplating waste, including physical, chemical and biological processes. Experimental studies of galvanic sludge sediment are presented. The precipitate is a mixture of crystalline CaCO3, SiO2 and an amorphous phase, which is not determined by phase analysis. Modern advanced technologies for the processing and disposal of galvanic sludge are presented.

    Keywords: galvanic sludge waste, automation, control, methods, sediment thermogram

  • Application of machine vision methods on embedded systems

    The article discusses the application of machine vision methods for embedded systems using modern microcontrollers. Machine learning methods that are used in embedded systems to solve recognition problems, as well as neural network models, are described. The use of trained models for solving image recognition problems in embedded systems is proposed. The architectures of YOLOv3 and R-CN neural networks are compared. The Jetson TX2 hardware platform is considered. The results of comparing the calculation speed for different modes of the device are presented.

    Keywords: machine vision, neural networks, artificial intelligence, embedded systems, pattern recognition, YOLO, RCN, Jetson, Tensorflow

  • Method of calculating the application coefficient of the standard control system equipment on the test bench

    The article considers an approach to estimating the application coefficient of standard control system equipment on a test bench. The relevance of the evaluation task at the design stage of the test bench is shown and a description of the method for solving this problem is given. The proposed approaches can be applied both at the stage of creating a test stand and when upgrading an existing positionю.

    Keywords: automatic control system, test bench, analysis of the testing process, experimental testing, standard equipment, centralized control software package, application coefficient of equipment

  • Analysis of the testing time of the control system on the test bench

    The article analyzes the testing time of the control system on the test bench, identifies the components of the testing time, and provides the calculation procedure for a typical test bench. The results obtained can be used to estimate the time of testing control systems at the design stage of test benches.

    Keywords: automatic control system, rocket and space technology, test bench, analysis of the testing process, experimental testing, testing time

  • Improving images of asphalt concrete pavements based on segmentation methods

    To assess the quality of the road surface, there are many systems that work on the basis of specific algorithms, including image segmentation methods. Time complexity and classification accuracy are two key indicators when evaluating the effectiveness of a particular algorithm. In this article, the following image segmentation methods are used as the analyzed methods: k-means clustering, Linear clustering, Adaptive thresholding, Global thresholding. Based on the methods described in the section "Methodology of experiments", the "Global thresholds" method has the best indicators of classification accuracy and time complexity (38.2% - classification accuracy; time complexity is linear (other methods have the same type of complexity, however, GT has much less absolute time indicators).

    Keywords: comparison, method, segmentation, image, photo, road, surface, condition, accuracy, classification, time, complextion

  • Improving the quality of road surface images based on morphological processing techniques

    Road surface quality assessment is one of the most popular tasks around the world. To solve it, there are a large number of systems that work using certain algorithms, including methods of morphological image processing. One of the key criteria for the effectiveness of an algorithm is its time complexity. The following approaches of morphological processing is considered in the article: Dilation, Erosion, Morphological Gradient, Morphological Smoothing. Photos of the road surface of various conditions were used as the material for the study. Based on the proposed methodology of the experiment, it turned out that each of the selected algorithms has a linear time complexity, but the "Dilation" and "Erosion" algorithms have lower absolute time indicators.

    Keywords: comparison, efficiency, morphological technique, processing, image, photo, road, condition, time, complexity

  • On the issue of calculating the design of a prismatic beam with a multi-column truss

    Based on the beginning of the least work, theoretical dependencies were obtained to determine the internal forces in the elements of the combined trussed system. The analysis of the calculation results of a trussed beam with four posts was carried out and the physical side of the phenomenon of bending during the interaction of the main structure of the trussed beam with elements of a multi-post truss was revealed.

    Keywords: truss beam, combined system, multi-column truss, relative eccentricity, potential energy

  • Simulation of the design activity diversification of innovative enterprise

    The results of a study of the nature of the occurrence of fine dust particles in the urban environment (on the example of the city of Volgograd) are presented. The sources of dust release in the form of ground dispersed massifs represented by loess and clayey soils are considered. The results of determining the mode of variability of the parameters of the mechanical composition, physical properties in two directions of dust drift (southeast and north) are shown. Studies of loess and clayey rocks for radon content were carried out. It was revealed that the dispersed soils under consideration are characterized by significant indicators of the effective specific activity of radon. Researches of pollution of a snow cover are carried out. It was found that the snow cover, in addition to technogenic accumulations, contains particles of fine dust. The results of the study will help in the implementation of predictive assessments of possible changes in the environment.

    Keywords: atmospheric pollution, fine dust, urban environment, dispersed rock, wind flow, soil massif, radon content, drift trend of fine earth

  • Methodology for optimizing the process of designing pavements using asphalt granulate

    A methodology for the development of a system of typical environmentally and economically effective road pavement designs is proposed, which allows to optimize the process of designing pavements using asphalt granulate for the design of overhaul of road pavements.redistribution of investments in interests of the organization and development of new production on available floor spaces. The most important organizational economic targets of a diversification of management are presented by innovative activity of the industrial enterprise.

    Keywords: cold deep in-place recycling, pavement, standard design, road, design, construction, asphalt granulate