This paper is devoted to the construction of a visual-inertial odometry system for an unmanned vehicle using both binocular cameras and inertial sensors as an information source, which would be able to simultaneously determine the vehicle's own position and the relative position of other road users. To ensure accurate and continuous localization, it is proposed to use an inertial navigation system and two types of image keypoints. Deep learning models are used to accurately and reliably track keypoints. To achieve efficient and reliable matching of objects between two frames, a multi-level data association mechanism is proposed that takes into account possible errors of various system components. The experimental results demonstrate the feasibility and application potential of the proposed system.

Keywords: multi-object visual-inertial odometry, localization, data association, tracking of 3D dynamic objects

This paper is devoted to the construction of a robust visual-inertial odometry system for an unmanned vehicle using binocular cameras and inertial sensors as information sources.The system is based on a modified structure of the VINS-FUSION system. Two types of feature points and matching methods are used to better balance the quantity and quality of tracking points. To filter out incorrect matches of key points, it is proposed to use several different methods. Semantic and geometric information are combined to quickly remove dynamic objects. Keypoints of static objects are used to complement the tracking points. A multi-layer optimization mechanism is proposed to fully utilize all point matchings and improve the accuracy of motion estimation. The experimental results demonstrate the effectiveness of the system.

Keywords: robust visual-inertial odometry, localization, road scene, multi-level optimization mechanism

The paper presents a method of detecting distortions in the archival photo documents by texture analysis based on local binary patternss. The proposed approach consists of the following stages: pre-treatment and detection of scratches. Pre-treatment is used to reduce the effects of noise and small defects in the image. To recognize the class of defects using a support vector machine. The effectiveness of the new approach on several examples in the detection of defects.

Keywords: digital image processing, detection of defects, archival photographs, local binary patterns

  This paper is devoted to development of gas sensors air control. It is shown that copper oxides are the promising materials for high sensitive sensors. The CuOx film material was syntheses by means of citrate sol-gel technique. The sensors fabricated on the basis of CuOx film material were sensitive to ammonia gas in the range of 25-150 ppm. Working temperature was determined as 180 °C. Such sensors can be used for work area air control of industrial enterprises.

Keywords: gas-sensitive element, atmospheric air, sensors, copper oxides

Combined method which allows analyzing parameters of the nanoscale atomic and electronic structure of materials relying on three different methods (x-ray absorption spectroscopy (XAFS), x-ray diffraction (XRD) and Raman spectroscopy) was developed. The method was applied for the study of nickel oxide nanoparticles, which serve as an efficient catalyst for the artificial photosynthesis process. 

Keywords: solar energy, artificial photosynthesis, NiO, Raman, x-ray diffraction, XAFS

Keywords: nanotechnology, nanomaterials, energy, new materials, nanodevices, manage properties, bioelectronics.

Keywords: