Mr. Viacheslav V. Voronin Profile

Viacheslav V. Voronin

Researcher at Moscow State Univ of Technology "STANKIN"

SPIE Involvement:

Conference Program Committee | Author

Publications (161)

Proceedings Article | 23 November 2024 Poster + Paper

Real-time cognitive algorithm for adapting the actions of multipurpose robotic systems

V. Voronin, I. Khamidullin, E. Semenishchev, M. Zhdanova, N. Gapon, M. Kazaryan

Proceedings Volume 13239, 132391Z (2024) https://doi.org/10.1117/12.3038686

KEYWORDS: Gesture recognition, Sensors, Feature extraction, Histograms of oriented gradient, Detection and tracking algorithms, Robotic systems, Optical flow, Data fusion

Read Abstract +

Proceedings Article | 23 November 2024 Poster + Paper

Depth maps inpainting based on adaptive generative models

N. Gapon, A. Puzerenko, V. Voronin, M. Zhdanova, A. Zelensky, D. Rudoy

Proceedings Volume 13239, 1323920 (2024) https://doi.org/10.1117/12.3038923

KEYWORDS: Depth maps, Gallium nitride, Education and training, Image restoration, RGB color model, Data modeling, Robots, Tunable filters, Network architectures, Visual process modeling

Read Abstract +

Proceedings Article | 23 November 2024 Poster + Paper

Image inpainting by anisotropic gradient estimation

A. Zelensky, N. Gapon, M. Zhdanova, V. Voronin, Y. Ilukhin, I. Khamidullin

Proceedings Volume 13239, 132391X (2024) https://doi.org/10.1117/12.3038592

KEYWORDS: Image restoration, Image processing, Neural networks, Digital image processing, Image segmentation, Electron beam melting, Deep learning

Read Abstract +

Proceedings Article | 23 November 2024 Poster + Paper

Method for recognizing grape disease in bushes from images using neural network technologies

N. Gapon, M. Zhdanova, A. Dvornichenko, D. Rudoy, V. Voronin, O. Safaryan

Proceedings Volume 13239, 1323921 (2024) https://doi.org/10.1117/12.3038925

KEYWORDS: Neurological disorders, Diseases and disorders, Data modeling, Neural networks, Depth maps, Machine learning, Feature extraction, Agriculture, Robotic systems, Education and training

Read Abstract +

Proceedings Article | 23 November 2024 Poster + Paper

Image enhancement via multiscale-exposure image fusion

A. Zelensky, N. Gapon, M. Zhdanova, V. Voronin, Y. Ilukhin, A. Gribkov

Proceedings Volume 13239, 132391Y (2024) https://doi.org/10.1117/12.3038616

KEYWORDS: Image enhancement, Image fusion, Image processing, Image quality, Image analysis, Visualization, Computer simulations, Light sources and illumination, Image visualization, Image restoration

Read Abstract +

Proceedings Article | 20 November 2024 Poster + Paper

Image segmentation based on adaptive quaternion anisotropic gradient for optical inspection applications

A. Zelensky, N. Gapon, M. Zhdanova, V. Voronin, Y. Ilukhin, A. Gribkov

Proceedings Volume 13241, 1324127 (2024) https://doi.org/10.1117/12.3038618

KEYWORDS: Image segmentation, Image enhancement, Image fusion, Image processing algorithms and systems, Optical inspection, Image processing

Read Abstract +

Proceedings Article | 20 June 2024 Poster + Paper

Algorithm for detecting objects and specialized tags in low light conditions and low camera resolution

Evgenii Semenishchev, Marina Zdanova, Andrey Alepko, Viacheslav Voronin

Proceedings Volume 13000, 130000O (2024) https://doi.org/10.1117/12.3023940

KEYWORDS: Cameras, Object detection, Robotic systems, Machine vision, Data processing, Image resolution

Read Abstract +

Proceedings Article | 20 June 2024 Poster + Paper

Real-time deep learning-based object recognition in augmented reality

V. Egipko, M. Zhdanova, N. Gapon, V. Voronin, E. Semenishchev

Proceedings Volume 13000, 130000P (2024) https://doi.org/10.1117/12.3024957

KEYWORDS: Augmented reality, Image filtering, Tunable filters, Object recognition, 3D modeling, Neural networks, Image processing, Deep learning

Read Abstract +

Proceedings Article | 18 June 2024 Poster + Paper

Preprocessing and improving image quality for identifying elements simple shape in machine vision system to automated industrial machines

Viacheslav Voronin, Ilia Khamidullin, Evgenii Semenishchev, Marina Zdanova, Andrey Alepko

Proceedings Volume 12998, 129981Y (2024) https://doi.org/10.1117/12.3023939

KEYWORDS: Electronic components, Machine vision, Object detection, Chip manufacturing, Image processing, Data processing

Read Abstract +

Proceedings Article | 7 June 2024 Poster + Paper

Image inpainting based on adaptive generative models

N. Gapon, Artyem Puzerenko, V. Voronin, M. Zhdanova, E. Semenishchev

Proceedings Volume 13051, 130511S (2024) https://doi.org/10.1117/12.3017675

KEYWORDS: Digital watermarking, Image restoration, Image processing, Image quality, Network architectures, Visualization, Image enhancement

Read Abstract +

Proceedings Article | 7 June 2024 Poster + Paper

Thermal image enhancement by artificial multiscale-exposure image fusion

V. Voronin, N. Gapon, M. Zhdanova, E. Semenishchev

Proceedings Volume 13033, 130330V (2024) https://doi.org/10.1117/12.3017678

KEYWORDS: Image enhancement, Image fusion, 3D image enhancement, Image processing, Infrared imaging, 3D image processing, Image quality

Read Abstract +

Proceedings Article | 28 November 2023 Poster + Paper

Real‐time deep learning semantic segmentation for 3-D augmented reality

V. Voronin, E. Semenishchev, A. Zelensky, M. Zhdanova, N. Gapon

Proceedings Volume 12772, 127720L (2023) https://doi.org/10.1117/12.2691152

KEYWORDS: Augmented reality, Image segmentation, Semantics, Neural networks, Video, RGB color model, Object detection, Detection and tracking algorithms, Deep learning

Read Abstract +

Augmented reality is a visualization technology that displays information by adding virtual images to the real world. In many cases, augmented reality requires recognition of the current scene. Extracting foreground objects from a video in real-time on limited hardware, such as a smartphone, is demanding. The augmented reality for the environment must have a model in which it is clear where it is necessary to detect the object or apply a mask. One way to recognize a scene in the current context without prior information is to use semantic segmentation techniques. This article proposes a new neural network architecture for efficient semantic image segmentation in the task of building augmented reality. The developed architecture is based on the combination of Shufflenet V2 and DPC, which provides good performance due to the balance between predictive accuracy and efficiency. First, the ShuffleNet V2 neural network architecture obtains features from RGB images. The resulting feature maps are then passed to one of the Deeplab V3+ Dense Prediction Cell encoders. At the final stage, the features are decoded by bilinear interpolation to create segmentation masks. The augmented reality construction algorithm is based on the ARCore framework and the OpenGL interface for embedded systems. The proposed approach for recognizing scene objects in augmented reality uses semantic segmentation, providing real-time information. The implementation of the algorithm shows that the detected objects can be tracked in 3-D space using visual-inertial odometry without resorting to constantly updating the environment model. The frequency of object detection and semantic mask generation can be reduced, resulting in battery and processing power savings, which is critical for mobile and embedded systems. The semantic information provided by these solutions can be used in autonomous driving, robotics navigation, localization, and scene recognition in conditions of limited resources. In augmented reality, the proposed approach can remove objects from a scene, draw attention to objects, or provide scene recognition to software logic. The experiment results confirmed the high efficiency of the proposed method compared to the state-of-the-art techniques for real‐time 3-D augmented reality construction.