Mr. Vladimir V. Kniaz Profile

Vladimir V. Kniaz

at GosNIIAS

SPIE Involvement:

Author

Publications (10)

Proceedings Article | 20 June 2021 Presentation + Paper

Deep learning for 3D scene reconstruction and segmentation from stereo images

Vladimir Kniaz, Vladimir Knyaz, Evgeny Ippolitov, Mikhail Novikov, Lev Grodzitsky, Petr Moshkantsev

Proceedings Volume 11785, 117850I (2021) https://doi.org/10.1117/12.2592648

KEYWORDS: 3D modeling, Image segmentation, 3D image processing, 3D image reconstruction, Visual process modeling, Systems modeling, 3D metrology, Performance modeling, Clouds, Neural networks

Read Abstract +

Proceedings Article | 21 September 2020 Presentation + Paper

Object recognition for UAV navigation in complex environment

V. Knyaz, V. Kniaz

Proceedings Volume 11533, 115330P (2020) https://doi.org/10.1117/12.2574078

KEYWORDS: 3D modeling, Unmanned aerial vehicles, Image segmentation, Object recognition, 3D image processing, Neural networks, Motion models, Data modeling, Data processing, Computing systems

Read Abstract +

Impressive progress in technical characteristics of modern unmanned aerial vehicles (UAV) provides new opportunities for their exploiting in different applications and missions which were impossible earlier. The growing applicability of UAVs is based on high performance of modern computers and latest advances in sensor data processing techniques. Recent decades modern convolutional neural network (CNN) models have demonstrated the state of the art performance in many computer vision problems seemed to be solved properly only by a human. The study is aimed at developing a deep learning techniques for UAV autonomous navigation in complex environment in obstacle avoidance mode. Such kind of navigation is required for cargo delivery or rescue mission in urban, industrial or forestry environment when global geo-positioning system can be unavailable. For navigating in complex environment UAV have to recognize objects of observed scene and to estimate distance for possible obstacle. The proposed technique to solve these tasks exploits deep learning approach for image segmentation and depth map estimation using an image of the observed scene. The convolutional neural network model is developed capable to predict depth map of the observed scene along with scene segmentation according the predefined object classes. The proposed neural network architecture is based on generative adversarial model with generative part translating an input color image into an output voxel model. The aim of the discriminative part is to estimate how close the output to real data and to penalize false output. Both generative and discriminative parts are trained simultaneously on the specially prepared dataset. Evaluation on the testing part of the prepared dataset has demonstrated the ability of the developed neural network model to perform segmentation of unobserved complex scenes containing several objects and estimating depth map for this scene. The proposed neural network architecture provides high generalization ability for new scenes.

Proceedings Article | 13 April 2020 Presentation + Paper

GANcoder: robust feature point matching using conditional adversarial auto-encoder

Vladimir Kniaz, Vladimir Mizginov, Lev Grodzitsky, Artyom Bordodymov

Proceedings Volume 11353, 1135309 (2020) https://doi.org/10.1117/12.2556065

KEYWORDS: 3D modeling, 3D image processing, Sensors, Data modeling, 3D image reconstruction, Reconstruction algorithms, Convolutional neural networks, Detection and tracking algorithms

Read Abstract +

Objects without prominent textures pose challenges for an automatic 3D model reconstruction and feature point matching. Such objects are common in many industrial applications such as metal defect detection, archeological applications of photogrammetry, and 3D object reconstruction from infrared imagery. Most of the common feature point descriptors fail to match local patches in featureless regions of an object. Various kind of textures requires different feature descriptors for high-quality image matching. Hence, automatic low-textured 3D object reconstruction using Structure from Motion (SfM) methods is challenging. Nevertheless, such reconstruction is possible with the aid of a human operator. Deep learning-based descriptors have outperformed most of common feature point descriptors recently. This paper is focused on the development of a new conditional generative adversarial auto-encoder (GANcoder) based on the deep learning. We use a coder-decoder architecture with four convolutional and four deconvolutional layers as a staring point for our research. Our main contribution is a generative adversarial framework GANcoder for training the auto-encoder on the textureless data. Traditional training approaches using an L1 norm tend to converge to the mean image on the low-textured images. In contrast, we use an adversarial discriminator to provided an additional loss function that is focused on distinguishing real images from the training dataset from the auto-encoder reconstruction. We collected a large GANPatches dataset of feature points from nearly textureless objects to train and evaluate our model and baselines. The dataset includes 16k pairs of image patches. We performed qualitative evaluation of our GANcoder and baselines for two tasks. Firstly, we compare the matching score of the our GANcoder and baselines. Secondly, we evaluate the accuracy of 3D reconstruction of low-textured objects using an SfM pipeline with stereo-matching provided by our GANcoder. The results of the evaluation are encouraging and demonstrate that our model achieves and surpasses the state of the art in the feature matching on low-textured objects.

Proceedings Article | 7 October 2019 Presentation + Paper

Deep learning for dense labeling of hydrographic regions in very high resolution imagery

Vladimir Kniaz

Proceedings Volume 11155, 111550W (2019) https://doi.org/10.1117/12.2533161

KEYWORDS: Image segmentation, Satellite imaging, Earth observing sensors, Satellites, Image resolution, Multispectral imaging, Roads, Buildings, Vegetation, Data modeling

Read Abstract +

Automatic dense labeling of multispectral satellite images facilitates faster map update process. Water objects are essential elements of a geographic map. While modern dense labeling methods perform robust segmentation of such objects like roads, buildings, and vegetation, dense labeling of hydrographic regions remains a challenging problem. Water objects change their surface albedo, color, and reflection in different weather and different seasons. Moreover, rivers and lakes can change their boundaries after floods or droughts. Robust documentation of such seasonal changes is an essential task in the field of analysis of satellite imagery. Due to the high variance in water object appearance, their segmentation is usually performed manually by a human operator. Recent advances in machine learning have made possible robust segmentation of static objects such as buildings and roads. To the best of our knowledge, there is little research in the modern literature regarding dense labeling of water regions. This paper is focused on the development of a deep-learning-based method for dense labeling of hydrographic in aerial and satellite imagery. We use the GeoGAN framework and MobileNetV2 as the starting point for our research. The GeoGAN framework uses an aerial image as an input to generate pixel-level annotations of five object classes: building, low vegetation, high vegetation, road, and car. The GeoGAN framework leverages two deep learning approaches to ensure robust labeling: a generator with skip connections and Generative Adversarial Networks. A generator with skip connections performs image→label translation using feed-forward connections between convolutional and deconvolutional layers of the same depth. A GAN framework consists of two competing networks: a generator and a discriminator. The adversarial loss improves the quality of the resulting dense labeling. We made the following contributions to the GeoGAN framework: (1) new MobileNetV2-based generator, (2) adversarial loss function. We term the resulting framework as HydroGAN. We evaluate our HydroGAN model using a new HydroViews dataset focused on dense labeling of areas that are subject to severe flooding during the spring season. The evaluation results are encouraging and demonstrate that our HydroGAN model competes with the state-of-the-art models for dense labeling of aerial and satellite imagery. The evaluation demonstrates that our model can generalize from the training data to previously unseen samples. The developed HydroGAN model is capable of performing dense labeling of water objects in different seasons. We made our model publicly available.

Proceedings Article | 12 July 2019 Presentation + Paper

FringeMatchNet: effective stereo matching onboard of mobile structured light 3D scanner

Vladimir Kniaz

Proceedings Volume 11058, 1105815 (2019) https://doi.org/10.1117/12.2525871

KEYWORDS: 3D modeling, Structured light, 3D scanning, Cameras, Laser scanners, Scanners, Projection systems, 3D acquisition, 3D image processing, Data modeling, Convolutional neural networks

Read Abstract +

Proceedings Article | 9 October 2018 Presentation + Paper

Conditional GANs for semantic segmentation of multispectral satellite images

Vladimir Kniaz

Proceedings Volume 10789, 107890R (2018) https://doi.org/10.1117/12.2325601

KEYWORDS: Machine learning, RGB color model, Image segmentation, Earth observing sensors, Satellite imaging, Satellites, Data modeling, Multispectral imaging, Convolutional neural networks, Remote sensing

Read Abstract +

Proceedings Article | 24 May 2018 Presentation + Paper

Optical flow-based filtering for effective presentation of the enhanced vision on a HUD

Vladimir Kniaz

Proceedings Volume 10679, 106790O (2018) https://doi.org/10.1117/12.2306670

KEYWORDS: Video, Optical flow, Heads up displays, Video acceleration, Algorithm development, Video processing, 3D modeling, Image segmentation, Enhanced vision, Infrared sensors, Convolutional neural networks

Read Abstract +

Proceedings Article | 26 June 2017 Paper

A photogrammetric technique for generation of an accurate multispectral optical flow dataset

V. Kniaz

Proceedings Volume 10332, 103320G (2017) https://doi.org/10.1117/12.2269956

KEYWORDS: Optical flow, Visualization, Infrared imaging, Infrared radiation, Cameras, Detection and tracking algorithms, Image fusion, Algorithm development, Robotics, Imaging systems, Laser scanners, Visible radiation, Optical testing, 3D modeling

Read Abstract +

Proceedings Article | 29 April 2016 Paper

Real-time optical flow estimation on a GPU for a skied-steered mobile robot

V. Kniaz

Proceedings Volume 9897, 989706 (2016) https://doi.org/10.1117/12.2227556

KEYWORDS: Optical flow, Computing systems, Image processing, Mobile robots, Visualization, Video processing, Computer simulations, Video acceleration, Video, Fourier transforms, Algorithm development, Cameras, Image segmentation, Motion models, 3D modeling, Imaging systems, Motion estimation

Read Abstract +

Proceedings Article | 21 June 2015 Paper

Fast instantaneous center of rotation estimation algorithm for a skied-steered robot

V. Kniaz

Proceedings Volume 9528, 95280L (2015) https://doi.org/10.1117/12.2184834

KEYWORDS: Optical flow, Motion models, Algorithm development, Cameras, Visualization, Mobile robots, Optical character recognition, Motion estimation, Data modeling, Machine vision

Read Abstract +

Showing 5 of 10 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years