KEYWORDS: Image processing, Image filtering, Tunable filters, Video, Matrices, Video compression, Digital filtering, Video processing, Televisions, Digital image processing
In the article describe the methods of increasing the contrast of images in video information systems, the main compression of the video stream is provided by eliminating inter-frame redundancy using motion compensation methods for image fragments of adjacent frames. However, the use of motion compensation methods requires the formation of additional data (metadata) containing information about the types of image blocks used, the coordinates of their movement, etc. At the same time, in order to increase the compression of the video stream without compromising its quality, a higher accuracy of motion compensation is required, which leads to an increase in the number of blocks and, accordingly, to an increase in the volume of metadata that reduces the effectiveness of motion compensation. This is the main problem of compressing streaming video without degrading the quality of images. In addition, the higher accuracy of positioning blocks with motion compensation dramatically reduces the speed of image processing, which is not always feasible in real-time systems.
In recent years, the integration of machine learning algorithms has significantly advanced the field of computer vision, particularly in the domain of object detection and tracking in video images. This article explores the application of machine learning techniques to enhance the accuracy and efficiency of object detection and tracking systems. The article begins by providing an overview of the challenges associated with traditional methods of object detection and tracking, highlighting the limitations in handling complex scenarios and diverse object types. Subsequently, it delves into the methodology of employing machine learning algorithms, emphasizing their adaptability and capability to discern patterns and features crucial for accurate object recognition. Various machine learning models, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), are discussed in detail, elucidating their roles in extracting meaningful representations from video frames. The training process is explored, encompassing the use of labeled datasets to enable the algorithms to generalize and make informed predictions in real-world scenarios. Furthermore, the article investigates the integration of deep learning techniques, exploring the advantages of transfer learning and fine-tuning pre-trained models to optimize performance. The role of neural networks in handling object occlusion, scale variations, and pose changes is emphasized, showcasing the adaptability of machine learning algorithms to dynamic and unpredictable environments. The practical implementation of these algorithms in object detection and tracking systems is presented, highlighting real-world applications across industries such as surveillance, autonomous vehicles, and industrial automation. The article concludes by discussing ongoing research and potential future developments, addressing the evolving landscape of machine learning in computer vision and its implications for advancing object detection and tracking capabilities in video images.
This article presents an algorithm for determining reference brightness correction coefficients to improve image quality. The algorithm utilizes a combination of statistical analysis and image processing techniques to identify and correct brightness discrepancies in digital images. By establishing a robust and efficient method for calculating these coefficients, the algorithm aims to enhance the overall visual fidelity of images across various applications, such as photography, medical imaging, and remote sensing. The proposed algorithm demonstrates its effectiveness through experimental results and comparisons with existing methods, highlighting its potential for practical implementation in image processing workflows. In the world, the filtering of digital images by the convolution method with a pulse characteristic in the spectral region scientific research is being conducted to improve the quality level of digital television images, methods for modeling filtration processes and highly efficient control systems in a number of priority areas, including: on the formation of mathematical models of filtration processes, improving the methods of wavelet, Fourier, Haar, Walsh-Hadamard, Karhunen-Loev in increasing the clarity and brightness of images based on linear and nonlinear differential equations; creation of methods for eliminating additive, pulsed and adaptive-Gaussian types of noise in images using additive and adaptive filtering; methods of algorithms and software for introducing intra-frame and interframe image transformations; methods of adaptive brightness system control using the Chebyshev matrix series; methods of gradient, static and Laplace methods for image segmentation and dividing it into contours; formation of criteria and conditions for evaluating image quality. Conducting scientific research in the above research areas confirms the relevance of the topic of this article.
In the world, scientific research is being conducted to improve the quality level of digital television images, methods for modeling filtration processes and highly efficient control systems in a number of priority areas, including: on the formation of mathematical models of filtration processes, improving the methods of wavelet, Fourier, Haar, Walsh -Hadamard, Karhunen -Loev in increasing the clarity and brightness of images based on linear and nonlinear differential equations; creation of methods for eliminating additive, pulsed and adaptive-Gaussian types of noise in images using additive and adaptive filtering; methods of algorithms and software for introducing intra-frame and inter-frame image transformations; methods of adaptive brightness system control using the Chebyshev matrix series; methods of gradient, static and Laplace methods for image segmentation and dividing it into contours; formation of criteria and conditions for evaluating image quality. Conducting scientific research in the above research areas confirms the relevance of the topic of this article.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.