scholarly journals Streaming video processing of marine scenes using advanced processor instructions

2021 ◽  
pp. 124-131
Author(s):  
Ш.С. Фахми ◽  
Н.В. Шаталова ◽  
Е.В. Костикова
Keyword(s):  
Video Processing ◽  
Information Quality ◽  
Adaptive Algorithms ◽  
Video Stream ◽  
Surveillance Systems ◽  
Discrete Cosine Transformation ◽  
Smart Cameras ◽  
Processor Core ◽  
Video Information ◽  
High Level

Современные полупроводниковые технологии позволяют перейти к более развитым системам видеонаблюдения, где преобразование и обработка видеоинформации выполняются непосредственно на этапе съемки и формирования видеопотока. Умные камеры расширяют функциональность встроенных видеосенсоров, обеспечивая параллельную высокоуровневую обработку видео. В предлагаемом исследовании проведена разработка адаптивных алгоритмов спектрального преобразования изображений морских сюжетов, позволяющие решить необходимые задачи в реальном времени.Актуальным становится решение задачи использования современных процессорных технологий с использованием последних достижений в архитектуре процессорного ядра, в частности расширенные SSE-инструкции. Рассмотрен математический аппарат реализации адаптивных алгоритмов дискретного косинусного преобразования на базе SSEархитектуры процессорного ядра. Предложенные алгоритмы динамически выполняют предварительный анализ движения и определяют оптимальные размеры видеокубов. Для оценки эффективности предложенных алгоритмов сжатия было использовано множество различных изображений морских судов, полученных с камер и расположенных на беспилотниках с высоты 100-400м. Показаны результаты моделирования предложенных алгоритмов обработки видеоинформации морских сюжетов и определены количественные оценки информационных показателей качества видеосистем кодирования и декодирования изображений. Modern semiconductor technologies allow us to move to more advanced video surveillance systems, where the transformation and processing of video information is performed directly at the stage of shooting and forming a video stream. Smart cameras even extend the functionality of the built-in video sensors, providing parallel high-level video processing. In the proposed study, adaptive algorithms for spectral transformation of images of marine plots were developed, which allow solving the necessary problems in real time. The solution of the problem of using modern processor technologies using the latest achievements in the architecture of the processor core, in particular, advanced SSE instructions, becomes relevant. The mathematical apparatus for implementing adaptive algorithms for discrete cosine transformation based on the SSE architecture of the processor core is considered. Proposed algorithms dynamically perform preliminary motion analysis and determine optimal dimensions of video cubes. To evaluate the effectiveness of the proposed compression algorithms, many different images of naval vessels obtained from cameras and located on drones from a height of 100-400m were used. The results of modeling the proposed algorithms for processing video information of marine scenes are shown and quantitative estimates of information quality indicators of video systems for encoding and decoding images are determined.

scholarly journals Real-time marine vessel surveillance video system

2021 ◽  
pp. 98-105
Author(s):  
Ш.С. Фахми ◽  
С.А. Селиверстов ◽  
Е.В. Костикова ◽  
Р.Р. Муксимова ◽  
В.О. Титов
Keyword(s):  
Video Surveillance ◽  
Video Processing ◽  
Image Sensor ◽  
Surveillance Systems ◽  
Processing Unit ◽  
Desktop Computer ◽  
Smart Cameras ◽  
Video Information ◽  
Observation Systems ◽  
High Level

Анализируется процесс развития систем наблюдения. Раскрываются особенности технологических изменений систем наблюдения 1-го, 2-го и 3-го поколений. Декларируется, что современные полупроводниковые технологии позволяют перейти к более развитым системам видеонаблюдения 3-го поколения, где преобразование и обработка видеоинформации выполняются непосредственно в видеодатчиках на этапе формирования кадров. Умные камеры расширяют функциональность видеосенсора 3-го поколения, обеспечивая бортовую высокоуровневую обработку видео. Рассмотрены эволюция систем наблюдения и архитектура обработки видеоинформации с использованием интеллектуальных видеокамер с высоким динамическим диапазоном. Представлена графическая интерпретация, иллюстрирующая процесс эволюции систем видеонаблюдения от 1-го к 3-му поколению. Проанализированы функции современных систем видеонаблюдения и переход от высокоуровневой обработки видео из систем общего назначения во встраиваемые системы. Рассмотрен состав видеосистемы наблюдения с использованием интеллектуальной видеокамеры, включающий видеодатчик, блок обработки и блок управления связи. Описаны условия в которых морские системы видеонаблюдения используются. Приведены результаты экспериментальных исследований и выполнены оценки производительности. Показаны достигнутые результаты производительности для различных реализаций алгоритма обнаружения морских судов и необходимое время выполнения при обработке одного изображения с полным разрешением на стандартном настольном компьютере Pentium 4 с частотой 2,4 ГГц. с использованием реконфигурируемой системой на кристалле. The process of development of observation systems is analyzed. The features of technological changes in observation systems of the 1st, 2nd and 3rd generations are revealed. It is declared that modern semiconductor technologies make it possible to move to more advanced third-generation video surveillance systems, where the conversion and processing of video information is performed directly in video sensors at the stage of framing. Smart cameras extend the functionality of the 3rd generation image sensor to provide on-board high-level video processing. The evolution of surveillance systems and architecture of video information processing using smart cameras with a high dynamic range are considered. A graphical interpretation is presented that illustrates the evolution of video surveillance systems from the 1st to the 3rd generation. The functions of modern video surveillance systems and the transition from high-level video processing from general-purpose systems to embedded systems are analyzed. The composition of a video surveillance system using an intelligent camera is considered, including a video sensor, a processing unit and a communication control unit. The conditions in which marine video surveillance systems are used are described. The results of experimental studies are presented and performance estimates are performed. Shown are the achieved performance results for various implementations of the ship detection algorithm and the required execution time when processing one full resolution image on a standard Pentium 4 desktop computer running at 2.4 GHz. using a reconfigurable system on a chip.

scholarly journals High-speed algorithm for transmitting video information about emergency situations on transport objects

2021 ◽  
pp. 64-70
Author(s):  
И.Г. Малыгин ◽  
О.А. Королев
Keyword(s):  
Real Time ◽  
High Speed ◽  
High Performance ◽  
Low Complexity ◽  
Transformation Method ◽  
Video Stream ◽  
Surveillance Systems ◽  
Video Information ◽  
Emergency Situations ◽  
Multiplication Operation

Современные интеллектуальные видеосистемы наблюдения стали все больше акцентироваться на передачу в реальном времени высококачественного видео различных важных событий, в том числе чрезвычайных ситуаций. Для высокопроизводительных систем передачи видеоинформации нового поколения необходимы эффективные структурные решения, способные как к высокой скорости передачи, так и к высокой точности вычисления. Такие структуры должны обрабатывать огромные последовательности изображений, при этом каждый видеопоток должен характеризоваться высоким разрешением с минимальным шумом и искажениями, потребляя при этом как можно меньше мощности. Спектральные алгоритмы обработки видеоинформации являются наиболее распространенным способом передачи в реальном времени, в частности дискретное косинусное преобразование. При этом исходное изображение подвергается преобразованию из пространственной в частотную область с целью сжатия путём уменьшения или устранения избыточности визуальных данных. Неявное вычисление преобразования последовательности 8-точечного массива приводит к эффективному сжатию, требующему не более пятикратного выполнения операции умножения. В статье предложены архитектура с низкой структурой сложности и метод преобразования изображений на основе алгебры целых чисел. Modern intelligent video surveillance systems have become increasingly focused on real-time transmission of high-quality video of various important events, including emergencies. For high-performance video information transmission systems of the new generation, efficient structural solutions are needed that are capable of both high transmission speed and high calculation accuracy. Such structures must process huge sequences of images, and each video stream must be characterized by high resolution and with minimal noise and distortion, while consuming as little power as possible. Spectral algorithms for processing video information are the most common method of transmission in real time, in particular the discrete cosine transform. In this case, the original image is transformed from the spatial to the frequency domain in order to compress by reducing or eliminating the redundancy of visual data. Implicitly calculating the sequence transformation of an 8-point array results in efficient compression, requiring no more than five times the multiplication operation. In this paper, we propose an architecture with a low complexity structure and image transformation method based on the algebra of integers

Rational Choice of Information Form Converters for Automated Systems in Construction

2020 ◽  
pp. 60-65
Keyword(s):  
Rational Choice ◽  
Construction Industry ◽  
Correct Choice ◽  
Automated System ◽  
Digital Code ◽  
Automated Control ◽  
Sigma Delta ◽  
Processor Core ◽  
Building Monitoring ◽  
High Level

In automated control systems for technical processes, the conversion of a continuous signal into a digital code and vice versa from a digital code to a continuous (analog) value is widely used. For direct type converters often used the term ADC, the reverse - DAC. The characteristics of the converters often dramatically affect the parameters of the entire automated system. The importance of the correct choice of ADCs and DACs has especially increased recently in connection with the mass introduction of microcontrollers MC. Indeed, in addition to the ADC and DAC, it is necessary to place the processor core in the microcontroller's crystal, I/O interfaces and many other elements necessary for the functioning of the MC. The use of information converters in the construction industry imposes additional requirements on converters: for example, in building monitoring systems, precision ADCs with extremely high accuracy are often required (while performance may be low), in other applications it is necessary to provide the necessary parameters at a high level of industrial interference, etc. This article explores issues related to the rational choice of ADCs and DACs, taking into account current trends in the IT field and the specifics of work in the construction industry. Sigma-Delta converters are noted as the most promising models of direct type converters.

scholarly journals Devising a conceptual method for generating cryptocompression codograms of images without loss of information quality

2021 ◽  
Vol 4 (2(112)) ◽  
pp. 6-17
Author(s):  
Vladimir Barannik ◽  
Serhii Sidchenko ◽  
Dmitriy Barannik ◽  
Sergii Shulgin ◽  
Valeriy Barannik ◽  
...  
Keyword(s):  
Information Quality ◽  
Dynamic Range ◽  
Video Data ◽  
Service Component ◽  
Loss Of Information ◽  
Video Information ◽  
Information Components ◽  
Service Data ◽  
Processing Steps ◽  
Better Than

Along with the widespread use of digital images, an urgent scientific and applied issue arose regarding the need to reduce the volume of video information provided it is confidential and reliable. To resolve this issue, cryptocompression coding methods could be used. However, there is no method that summarizes all processing steps. This paper reports the development of a conceptual method for the cryptocompression coding of images on a differentiated basis without loss of information quality. It involves a three-stage technology for the generation of cryptocompression codograms. The first two cascades provide for the generation of code structures for information components while ensuring their confidentiality and key elements as a service component. On the third cascade of processing, it is proposed to manage the confidentiality of the service component. The code values for the information components of nondeterministic length are derived out on the basis of a non-deterministic number of elements of the source video data in a reduced dynamic range. The generation of service data is proposed to be organized in blocks of initial images with a dimension of 16×16 elements. The method ensures a decrease in the volume of source images during the generation of cryptocompression codograms, by 1.14–1.58 times (12–37 %), depending on the degree of their saturation. This is 12.7‒23.4 % better than TIFF technology and is 9.6‒17.9 % better than PNG technology. The volume of the service component of cryptocompression codograms is 1.563 % of the volume of the source video data or no more than 2.5 % of the total code stream. That reduces the amount of data for encryption by up to 40 times compared to TIFF and PNG technologies. The devised method does not introduce errors into the data in the coding process and refers to methods without loss of information quality.

Parallel-Pipelined Video Processing in Multicore Heterogeneous Systems on Chip

2021 ◽  
Vol 26 (2) ◽  
pp. 172-183
Author(s):  
E.S. Yanakova ◽  
◽  
G.T. Macharadze ◽  
L.G. Gagarina ◽  
A.A. Shvachko ◽  
...  
Keyword(s):  
Video Processing ◽  
High Efficiency ◽  
Heterogeneous Systems ◽  
Video Data ◽  
System Level ◽  
Video Information ◽  
Systems On Chip ◽  
The Face ◽  
Parallel Pipelined ◽  
On Chip

A turn from homogeneous to heterogeneous architectures permits to achieve the advantages of the efficiency, size, weight and power consumption, which is especially important for the built-in solutions. However, the development of the parallel software for heterogeneous computer systems is rather complex task due to the requirements of high efficiency, easy programming and the process of scaling. In the paper the efficiency of parallel-pipelined processing of video information in multiprocessor heterogeneous systems on a chip (SoC) such as DSP, GPU, ISP, VDP, VPU and others, has been investigated. A typical scheme of parallel-pipelined processing of video data using various accelerators has been presented. The scheme of the parallel-pipelined video data on heterogeneous SoC 1892VM248 has been developed. The methods of efficient parallel-pipelined processing of video data in heterogeneous computers (SoC), consisting of the operating system level, programming technologies level and the application level, have been proposed. A comparative analysis of the most common programming technologies, such as OpenCL, OpenMP, MPI, OpenAMP, has been performed. The analysis has shown that depend-ing on the device finite purpose two programming paradigms should be applied: based on OpenCL technology (for built-in system) and MPI technology (for inter-cell and inter processor interaction). The results obtained of the parallel-pipelined processing within the framework of the face recognition have confirmed the effectiveness of the chosen solutions.

Collective Event Detection by a Distributed Low-Cost Smart Camera Network

2019 ◽  
pp. 918-937
Author(s):  
Jhih-Yuan Hwang ◽  
Wei-Po Lee
Keyword(s):  
Event Detection ◽  
Low Cost ◽  
Event Recognition ◽  
Surveillance Systems ◽  
Collective Decision Making ◽  
Video Streams ◽  
Smart Cameras ◽  
Encoding Scheme ◽  
Human Behaviors ◽  
Indirect Encoding

The current surveillance systems must identify the continuous human behaviors to detect various events from video streams. To enhance the performance of event recognition, in this chapter, we propose a distributed low-cost smart cameras system, together with a machine learning technique to detect abnormal events through analyzing the sequential behaviors of a group of people. Our system mainly includes a simple but efficient strategy to organize the behavior sequence, a new indirect encoding scheme to represent a group of people with relatively few features, and a multi-camera collaboration strategy to perform collective decision making for event recognition. Experiments have been conducted and the results confirm the reliability and stability of the proposed system in event recognition.

Business Applications of Deep Learning

2020 ◽  
pp. 942-964
Author(s):  
Armando Vieira
Keyword(s):  
Deep Learning ◽  
Language Processing ◽  
Video Processing ◽  
Autonomous Vehicles ◽  
Video Annotation ◽  
Business Applications ◽  
Personal Assistants ◽  
Efficient Learning ◽  
High Level ◽  
Almost All

Deep Learning (DL) took Artificial Intelligence (AI) by storm and has infiltrated into business at an unprecedented rate. Access to vast amounts of data extensive computational power and a new wave of efficient learning algorithms, helped Artificial Neural Networks to achieve state-of-the-art results in almost all AI challenges. DL is the cornerstone technology behind products for image recognition and video annotation, voice recognition, personal assistants, automated translation and autonomous vehicles. DL works similarly to the brain by extracting high-level, complex abstractions from data in a hierarchical and discriminative or generative way. The implications of DL supported AI in business is tremendous, shaking to the foundations many industries. In this chapter, I present the most significant algorithms and applications, including Natural Language Processing (NLP), image and video processing and finance.

ViPar: High-Level Design Space Exploration for Parallel Video Processing Architectures

2019 ◽  
Vol 2019 ◽  
pp. 1-19
Author(s):  
Karim M. A. Ali ◽  
Rabie Ben Atitallah ◽  
Abdessamad Ait El Cadi ◽  
Nizar Fakhfakh ◽  
Jean-Luc Dekeyser
Keyword(s):  
Power Consumption ◽  
Video Processing ◽  
Execution Time ◽  
Design Space Exploration ◽  
Hardware Implementation ◽  
Space Exploration ◽  
Absolute Difference ◽  
Architectural Model ◽  
Processing Architectures ◽  
High Level

Embedded video applications are now involved in sophisticated transportation systems like autonomous vehicles and driver assistance systems. As silicon capacity increases, the design productivity gap grows up for the current available design tools. Hence, high-level synthesis (HLS) tools emerged in order to reduce that gap by shifting the design efforts to higher abstraction levels. In this paper, we present ViPar as a tool for exploring different video processing architectures at higher design level. First, we proposed a parametrizable parallel architectural model dedicated for video applications. Second, targeting this architectural model, we developed ViPar tool with two main features: (1) An empirical model was introduced to estimate the power consumption based on hardware utilization and operating frequency. In addition to that, we derived the equations for estimating the hardware utilization and execution time for each design point during the space exploration process. (2) By defining the main characteristics of the parallel video architecture like parallelism level, the number of input/output ports, the pixel distribution pattern, and so on, ViPar tool can automatically generate the dedicated architecture for hardware implementation. In the experimental validation, we used ViPar tool to generate automatically an efficient hardware implementation for a Multiwindow Sum of Absolute Difference stereo matching algorithm on Xilinx Zynq ZC706 board. We succeeded to increase the design productivity by converging rapidly to the appropriate designs that fit with our system constraints in terms of power consumption, hardware utilization, and frame execution time.

scholarly journals A Face Image Virtualization Mechanism for Privacy Intrusion Prevention in Healthcare Video Surveillance Systems

Symmetry ◽  
2020 ◽  
Vol 12 (6) ◽  
pp. 891 ◽  
Author(s):  
Jinsu Kim ◽  
Namje Park
Keyword(s):  
Video Surveillance ◽  
Visual Information ◽  
Face Image ◽  
Video Data ◽  
Surveillance Systems ◽  
Image Information ◽  
Video Information ◽  
Face Area ◽  
Blockchain Technology ◽  
Wide Range

Closed-circuit television (CCTV) and video surveillance systems (VSSs) are becoming increasingly more common each year to help prevent incidents/accidents and ensure the security of public places and facilities. The increased presence of VSS is also increasing the number of per capita exposures to CCTV cameras. To help protect the privacy of the exposed objects, attention is being drawn to technologies that utilize intelligent video surveillance systems (IVSSs). IVSSs execute a wide range of surveillance duties—from simple identification of objects in the recorded video data, to understanding and identifying the behavioral patterns of objects and the situations at the incident/accident scenes, as well as the processing of video information to protect the privacy of the recorded objects against leakage. Besides, the recorded privacy information is encrypted and recorded using blockchain technology to prevent forgery of the image. The technology herein proposed (the “proposed mechanism”) is implemented to a VSS, where the mechanism converts the original visual information recorded on a VSS into a similarly constructed image information, so that the original information can be protected against leakage. The face area extracted from the image information is recorded in a separate database, allowing the creation of a restored image that is in perfect symmetry with the original image for images with virtualized face areas. Specifically, the main section of this study proposes an image modification mechanism that inserts a virtual face image that closely matches a predetermined similarity and uses a blockchain as the storage area.

Sign in / Sign up

Export Citation Format

Share Document