scholarly journals Situational Awareness and Problems of Its Formation in the Tasks of UAV Behavior Control

2021 ◽  
Vol 11 (24) ◽  
pp. 11611
Author(s):  
Dmitry M. Igonin ◽  
Pavel A. Kolganov ◽  
Yury V. Tiumentsev
Keyword(s):  
Visual Information ◽  
Situational Awareness ◽  
Landing Site ◽  
Semantic Segmentation ◽  
Group Behavior ◽  
Information Support ◽  
Primary Sources ◽  
Behavior Control ◽  
Critical Elements ◽  
Segmentation Of Images

Situational awareness formation is one of the most critical elements in solving the problem of UAV behavior control. It aims to provide information support for UAV behavior control according to its objectives and tasks to be completed. We consider the UAV to be a type of controlled dynamic system. The article shows the place of UAVs in the hierarchy of dynamic systems. We introduce the concepts of UAV behavior and activity and formulate requirements for algorithms for controlling UAV behavior. We propose the concept of situational awareness as applied to the problem of behavior control of highly autonomous UAVs (HA-UAVs) and analyze the levels and types of this situational awareness. We show the specifics of situational awareness formation for UAVs and analyze its differences from situational awareness for manned aviation and remotely piloted UAVs. We propose the concept of situational awareness as applied to the problem of UAV behavior control and analyze the levels and types of this situational awareness. We highlight and discuss in more detail two crucial elements of situational awareness for HA-UAVs. The first of them is related to the analysis and prediction of the behavior of objects in the vicinity of the HA-UAV. The general considerations involved in solving this problem, including the problem of analyzing the group behavior of such objects, are discussed. As an illustrative example, the solution to the problem of tracking an aircraft maneuvering in the vicinity of a HA-UAV is given. The second element of situational awareness is related to the processing of visual information, which is one of the primary sources of situational awareness formation required for the operation of the HA-UAV control system. As an example here, we consider solving the problem of semantic segmentation of images processed when selecting a landing site for the HA-UAV in unfamiliar terrain. Both of these problems are solved using machine learning methods and tools. In the field of situational awareness for HA-UAVs, there are several problems that need to be solved. We formulate some of these problems and briefly describe them.

scholarly journals Weakly-Supervised Recommended Traversable Area Segmentation Using Automatically Labeled Images for Autonomous Driving in Pedestrian Environment with No Edges

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 437
Author(s):  
Yuya Onozuka ◽  
Ryosuke Matsumi ◽  
Motoki Shino
Keyword(s):  
Visual Information ◽  
Data Augmentation ◽  
Semantic Segmentation ◽  
Autonomous Driving ◽  
Weighting Method ◽  
Personal Mobility ◽  
Human Understanding ◽  
Autonomous Mobility ◽  
Weakly Supervised ◽  
Traffic Rules

Detection of traversable areas is essential to navigation of autonomous personal mobility systems in unknown pedestrian environments. However, traffic rules may recommend or require driving in specified areas, such as sidewalks, in environments where roadways and sidewalks coexist. Therefore, it is necessary for such autonomous mobility systems to estimate the areas that are mechanically traversable and recommended by traffic rules and to navigate based on this estimation. In this paper, we propose a method for weakly-supervised recommended traversable area segmentation in environments with no edges using automatically labeled images based on paths selected by humans. This approach is based on the idea that a human-selected driving path more accurately reflects both mechanical traversability and human understanding of traffic rules and visual information. In addition, we propose a data augmentation method and a loss weighting method for detecting the appropriate recommended traversable area from a single human-selected path. Evaluation of the results showed that the proposed learning methods are effective for recommended traversable area detection and found that weakly-supervised semantic segmentation using human-selected path information is useful for recommended area detection in environments with no edges.

scholarly journals A comparison between two semantic deep learning frameworks for the autosomal dominant polycystic kidney disease segmentation based on magnetic resonance images

2019 ◽  
Vol 19 (S9) ◽  
Author(s):  
Vitoantonio Bevilacqua ◽  
Antonio Brunetti ◽  
Giacomo Donato Cascarano ◽  
Andrea Guerriero ◽  
Francesco Pesce ◽  
...  
Keyword(s):  
Deep Learning ◽  
Magnetic Resonance ◽  
Kidney Disease ◽  
Autosomal Dominant ◽  
Automatic Segmentation ◽  
Semantic Segmentation ◽  
Magnetic Resonance Images ◽  
Polycystic Kidney ◽  
Autosomal Dominant Polycystic Kidney ◽  
Segmentation Of Images

Abstract Background The automatic segmentation of kidneys in medical images is not a trivial task when the subjects undergoing the medical examination are affected by Autosomal Dominant Polycystic Kidney Disease (ADPKD). Several works dealing with the segmentation of Computed Tomography images from pathological subjects were proposed, showing high invasiveness of the examination or requiring interaction by the user for performing the segmentation of the images. In this work, we propose a fully-automated approach for the segmentation of Magnetic Resonance images, both reducing the invasiveness of the acquisition device and not requiring any interaction by the users for the segmentation of the images. Methods Two different approaches are proposed based on Deep Learning architectures using Convolutional Neural Networks (CNN) for the semantic segmentation of images, without needing to extract any hand-crafted features. In details, the first approach performs the automatic segmentation of images without any procedure for pre-processing the input. Conversely, the second approach performs a two-steps classification strategy: a first CNN automatically detects Regions Of Interest (ROIs); a subsequent classifier performs the semantic segmentation on the ROIs previously extracted. Results Results show that even though the detection of ROIs shows an overall high number of false positives, the subsequent semantic segmentation on the extracted ROIs allows achieving high performance in terms of mean Accuracy. However, the segmentation of the entire images input to the network remains the most accurate and reliable approach showing better performance than the previous approach. Conclusion The obtained results show that both the investigated approaches are reliable for the semantic segmentation of polycystic kidneys since both the strategies reach an Accuracy higher than 85%. Also, both the investigated methodologies show performances comparable and consistent with other approaches found in literature working on images from different sources, reducing both the invasiveness of the analyses and the interaction needed by the users for performing the segmentation task.

scholarly journals Scene-Aware Deep Networks for Semantic Segmentation of Images

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 69184-69193 ◽  
Author(s):  
Zhike Yi ◽  
Tao Chang ◽  
Shuai Li ◽  
Ruijun Liu ◽  
Jing Zhang ◽  
...  
Keyword(s):  
Semantic Segmentation ◽  
Deep Networks ◽  
Segmentation Of Images

scholarly journals Non-Intrusive Load Disaggregation by Convolutional Neural Network and Multilabel Classification

2020 ◽  
Vol 10 (4) ◽  
pp. 1454 ◽  
Author(s):  
Luca Massidda ◽  
Marino Marrocu ◽  
Simone Manca
Keyword(s):  
Neural Network ◽  
Residential Building ◽  
Semantic Segmentation ◽  
The State ◽  
Main Method ◽  
Multilabel Classification ◽  
Energy Footprint ◽  
Load Monitoring ◽  
Segmentation Of Images ◽  
Domestic Appliances

Non-intrusive load monitoring (NILM) is the main method used to monitor the energy footprint of a residential building and disaggregate total electrical usage into appliance-related signals. The most common disaggregation algorithms are based on the Hidden Markov Model, while solutions based on deep neural networks have recently caught the attention of researchers. In this work we address the problem through the recognition of the state of activation of the appliances using a fully convolutional deep neural network, borrowing some techniques used in the semantic segmentation of images and multilabel classification. This approach has allowed obtaining high performances not only in the recognition of the activation state of the domestic appliances but also in the estimation of their consumptions, improving the state of the art for a reference dataset.

3 years of experience in distance teaching for doctors of forensic experts in general human pathology

2020 ◽  
Author(s):  
Sergey Parilov ◽  
Anatoly Nesterov ◽  
Denis Zemlyansky
Keyword(s):  
Visual Information ◽  
Educational Process ◽  
Information Support ◽  
Educational Technologies ◽  
Distance Teaching ◽  
Search Activity ◽  
Second Stage ◽  
Human Pathology ◽  
Third Stage ◽  
Three Stages

The trends in the development of education include the trend of informatization of education and the trend of innovative education. In forensic medicine, the competence to learn to cognize compulsorily includes understanding of general pathological processes, and only through this prism should the ability to verify particular pathological changes occurring in the human body as a result of various types of injuries and diseases arise. To implement these trends, we use distance educational technologies, taking into account the following criteria: for an individual trajectory of professional formation and development of a cadet doctor; for the development of thinking in the process of professional development; of objectivity; of productive communication; of information support for the co-creation of teachers and cadets; feedback. In order to apply the indicated criteria in full, the process of perception and processing of visual information was divided into three stages. The first stage is the analysis of the structure of the information supplied. At the second stage, new images are created. The third stage is a search activity. The above-described structuring of the content of educational information and the principles of organizing the educational process using distance educational technologies have successfully taught doctors of forensic experts to apply knowledge of general human pathology in the production of examinations.

Methods and algorithms for classifying air targets by importance based on data from an airborne radar system Part 1. Two-stage ranking of air targets according to the degree of danger during the operation of radar in the multipurpose tracking mode

2021 ◽  
Author(s):  
A.S. Bogachev ◽  
I.R. Zagrebelnyi ◽  
V.I. Merkulov
Keyword(s):  
Situational Awareness ◽  
Technical Condition ◽  
Information Support ◽  
Airborne Radar ◽  
Two Stage ◽  
Radar Systems ◽  
Tracking Mode ◽  
Priority Task ◽  
System Part

Classification of air targets by rank of importance is the basis for ensuring situational awareness of pilots (crew members) of military aircraft, therefore, the problem of increasing the reliability of target classification is very urgent. The requirement to provide the pilot (crew) with full situational awareness means providing him with complete and reliable information about tactical, electronic, navigation situations and the technical condition of on-board systems. It should be noted that when classifying air targets according to the rank of importance, dangerous, favorable for attack and non-dangerous targets are currently usually distinguished. Specific tasks of classifying air targets by importance rank belong to the class of object recognition tasks. In modern aviation radio-electronic complexes, the classification of air targets according to the rank of importance is usually carried out according to the data of on-board radar systems, as well as electronic intelligence systems and optoelectronic systems. It should be noted that one of the main information modes of functioning of modern and future radar systems is the multipurpose tracking mode, in which an airborne radar can simultaneously track a large number of targets in its area of responsibility. In the conduct of hostilities, ensuring one's own security is a priority task for aircraft of various purposes. In this case, the role of dangerous air targets can be not only targets belonging to the opposing side, but also their own aircraft in dangerous encounters, in which a collision can occur between them. Therefore, the problem of preventing dangerous encounters and preventing aircraft collisions with each other becomes one of the key problems in group operations of military aviation. It should be noted that by now there are various methods of assessing goals according to the degree of their danger, but there is no systematic presentation of them. An attempt is made in the article to give a systematized presentation of new methods for solving this problem, based on a two-stage decision-making on the predicted minimum distance of closest approach and the time to reach it. Based on this approach, the following are considered: the method of subjective reduction of private indicators; procedures for determining the hazard indicators of air targets in the antenna coordinate system; rules for making decisions on the degree of danger of targets, taking into account their possible maneuver; – the composition of information support for solving this problem has been determined.

scholarly journals Panoptic Segmentation on Panoramic Radiographs: Deep Learning-Based Segmentation of Various Structures Including Maxillary Sinus and Mandibular Canal

2021 ◽  
Vol 10 (12) ◽  
pp. 2577
Author(s):  
Jun-Young Cha ◽  
Hyung-In Yoon ◽  
In-Sung Yeo ◽  
Kyung-Hoe Huh ◽  
Jung-Suk Han
Keyword(s):  
Deep Learning ◽  
Maxillary Sinus ◽  
Semantic Segmentation ◽  
Mandibular Canal ◽  
Panoramic Radiographs ◽  
Automated Method ◽  
Recognition Quality ◽  
Dental Practitioners ◽  
Set Up ◽  
Segmentation Of Images

Panoramic radiographs, also known as orthopantomograms, are routinely used in most dental clinics. However, it has been difficult to develop an automated method that detects the various structures present in these radiographs. One of the main reasons for this is that structures of various sizes and shapes are collectively shown in the image. In order to solve this problem, the recently proposed concept of panoptic segmentation, which integrates instance segmentation and semantic segmentation, was applied to panoramic radiographs. A state-of-the-art deep neural network model designed for panoptic segmentation was trained to segment the maxillary sinus, maxilla, mandible, mandibular canal, normal teeth, treated teeth, and dental implants on panoramic radiographs. Unlike conventional semantic segmentation, each object in the tooth and implant classes was individually classified. For evaluation, the panoptic quality, segmentation quality, recognition quality, intersection over union (IoU), and instance-level IoU were calculated. The evaluation and visualization results showed that the deep learning-based artificial intelligence model can perform panoptic segmentation of images, including those of the maxillary sinus and mandibular canal, on panoramic radiographs. This automatic machine learning method might assist dental practitioners to set up treatment plans and diagnose oral and maxillofacial diseases.

Sign in / Sign up

Export Citation Format

Share Document