Geometric Characteristics Of Objects Research Articles

Improving 3D Vulnerable Road User Detection With Point Augmentation

Point clouds have been a popular representation to describe 3D environments for autonomous driving applications. Despite accurate depth information, sparsity of pointsresults in difficulties in extracting sufficient features from vulnerable objects of small sizes. One solution is leveraging self-attention networks to build long-range connections between similar objects. Another method is using generative models to estimate the complete shape of objects. Both approaches introduce large memory consumption and extra complexity to the models while the geometric characteristics of objects are overlooked. To overcome this problem, this paper proposes Point Augmentation (PA)- RCNN, focusing on small object detection by generating efficient complementary features without trainable parameters. Specifically, 3D points are sampled with the guidance of object proposals and encoded through the 3D grid-based feature aggregation to produce localised 3D voxel properties. Such voxel attributes are fed to the pooling module with the aid of fictional points, which are transformed from sampled points considering geometric symmetry. Experimental results on Waymo Open Dataset and KITTI dataset show a superior advantage in the detection of distant and small objects in comparison with existing state-ofthe- art methods.

Influence of heat treatment methods on the color characteristics of meat

The production of food products with a sufficient amount of functional ingredients is an urgent task for the modern food industry, since the health of every person and nation is largely determined by the diet. An important role in the formation of the range of functional food products is assigned to the development of new recipes and technologies for meat products. In this work, horse meat was used as raw meat. When developing a horse meat product, different methods of heat treatment of the main raw materials were used: the traditional method - frying and stewing, cooking in a combi oven, sous-vide technology. A comparative analysis of heat treatment of meat has been carried out. Investigations were carried out using digital image processing methods to compare the color change of meat samples during cooking by the above methods. The ability to select a fragment of an image for a more detailed study with the output of statistical information about the number of pixels by secondary or tertiary colors has been implemented. The geometric characteristics of objects are determined - area, perimeter, height, width, as well as color characteristics for the selected color components. Using the method of digital image processing, the processes occurring during heat treatment have been established, which makes it possible to regulate and correct the technology of cooking meat products, analyze the geometric and color characteristics of finished products. A program and method for determining the color characteristics of the meat samples under study have been developed.

Landmark Extraction via Composite Features of Voronoi Diagram

Landmark extraction is a hotspot of spatial cognition and spatial knowledge organization research. Saliency measurement model is a most important method of landmark extraction, of which the principle is the weighted evaluation of the appearance, structure and semantics of objects. Considering the spatial distribution and geometric characteristics of objects, and it is difficult to extract landmarks with more consistent features, making it a complex process. From the viewpoint of composite features in Voronoi domain, a landmark extraction method is proposed to explore the geometric feature reflection of landmark from individual to its neighborhoods, based on the height of Voronoi element, Voronoi k-order neighborhood crevice and Voronoi k-order neighborhood visibility. Comparative experiments show that: (1) Compared with the landmark extracted by the existing methods with the results of traditional saliency measurement model, which verifies the effectiveness of this method; (2) As for the characteristics of ground property, the geometric features contained in Voronoi diagram can effectively represent the landmarks, reducing the complexity for feature selection of landmarks.

ІДЕНТИФІКАЦІЯ ОБ’ЄКТІВ МАШИНОБУДУВАННЯ ЗА КІЛЬКОМА КІЛЬКІСНИМИ ОЗНАКАМИ ОДНОЧАСНО

Показано, що діагностика об'єктів машинобудування передбачає обґрунтування розширення застосовуваних фізичних ефектів, орієнтованих, в першу чергу, на неруйнівного контролю параметрів продукції машинобудування. На підставі досліджень, які показують перспективність експериментальних і теоретичних доказів, доведена доцільність пошуку підтвердження інформативності частотних спектрів резонансних акустичних сигналів досліджуваних об'єктів, порушених широкосмуговими резонаторами рівній амплітуди в акустичному діапазоні. Надані прикладі застосування широкосмугових випромінювачів наноамплітудних впливів на досліджувані об'єкти з метою акустичної спектроскопії для створення їх ідентифікаційних моделей. Для практичного використання експериментальних результатів для ідентифікації розмірних і фізико-механічних характеристик станів діагностованих об'єктів авторами застосовані нейромережні моделі. Такі моделі служать практичним цілям діагностики станів об'єктів на основі частотних спектрів власних резонансних коливань. Доведено, якщо діагностика об'єкта проводиться щодо опорного сигналу у вигляді широкосмугового впливу постійної амплітуди, то такий підхід дозволяє нормувати вихідні діагностичні сигнали щодо опорного сигналу. представлені ідентифікаційні моделі, побудовані на нейромережному базисі, показали реальну можливість їх використання для створення системи діагностики об'єктів за кількома кількісними ознаками. Причому, кількість таких ознак, які можна контролювати одночасно, практично, не обмежена. Авторами роботи проведені додаткові дослідження, які показали можливість одночасного контролю не тільки геометричних характеристик об'єктів, а й їх фізико-механічних характеристик, включаючи показники напруженого стану, твердості і т.ін..

Identification of saline-alkali soil based on target decomposition of full-polarization radar data

The potential of C-band polarimetric synthetic aperture radar data for the discrimination of saline-alkali soils in the western Jilin Province, China, is shown. This area is one of the three saline-alkali landscapes in the world; the presence of saline-alkali soils severely restricts the development of local farming and limits the land use. It is extremely important to identify saline-alkali landscapes accurately and effectively. Radar remote sensing is one of the most promising approaches for saline-alkali soil identification due to the sensitivity of radar data to the dielectric and geometric characteristics of objects, its weather-independent imaging capability, and its potential to acquire subsurface information, independent of the frequency band. Full polarimetric radar data from the RADARSAT-2 satellite were used. We focused on target decomposition theory and the statistical classification approach using a Wishart distribution to identify saline-alkali soils. The precise validation of the classification results is based on 129 ground sampling points. The results indicate that the polarimetric classifications using the H-α¯ method performed poorly, with Kappa values of approximately 0.29. The classification method based on Freeman-Durden decomposition showed better results, with Kappa values of approximately 0.54 and an overall accuracy of 68.22%. The best result was achieved using an input of anisotropy, with Kappa values of approximately 0.62 and an overall accuracy of 74.42%. The validity of the anisotropy approach implies that the scattering randomness of saline-alkali soil is very strong, which reflects the complex scattering characteristics of saline-alkali landscapes. Further study of the scattering characteristics of saline-alkali soil is necessary.