scholarly journals Kimera: From SLAM to spatial perception with 3D dynamic scene graphs

2021 ◽  
Vol 40 (12-14) ◽  
pp. 1510-1546
Author(s):  
Antoni Rosinol ◽  
Andrew Violette ◽  
Marcus Abate ◽  
Nathan Hughes ◽  
Yun Chang ◽  
...  
Keyword(s):  
Real Time ◽  
Mental Model ◽  
Comprehensive Evaluation ◽  
Real Life ◽  
Dynamic Environment ◽  
Human Perception ◽  
Object Localization ◽  
Dynamic Scene ◽  
Shape Estimation ◽  
Levels Of Abstraction

Humans are able to form a complex mental model of the environment they move in. This mental model captures geometric and semantic aspects of the scene, describes the environment at multiple levels of abstractions (e.g., objects, rooms, buildings), includes static and dynamic entities and their relations (e.g., a person is in a room at a given time). In contrast, current robots’ internal representations still provide a partial and fragmented understanding of the environment, either in the form of a sparse or dense set of geometric primitives (e.g., points, lines, planes, and voxels), or as a collection of objects. This article attempts to reduce the gap between robot and human perception by introducing a novel representation, a 3D dynamic scene graph (DSG), that seamlessly captures metric and semantic aspects of a dynamic environment. A DSG is a layered graph where nodes represent spatial concepts at different levels of abstraction, and edges represent spatiotemporal relations among nodes. Our second contribution is Kimera, the first fully automatic method to build a DSG from visual–inertial data. Kimera includes accurate algorithms for visual–inertial simultaneous localization and mapping (SLAM), metric–semantic 3D reconstruction, object localization, human pose and shape estimation, and scene parsing. Our third contribution is a comprehensive evaluation of Kimera in real-life datasets and photo-realistic simulations, including a newly released dataset, uHumans2, which simulates a collection of crowded indoor and outdoor scenes. Our evaluation shows that Kimera achieves competitive performance in visual–inertial SLAM, estimates an accurate 3D metric–semantic mesh model in real-time, and builds a DSG of a complex indoor environment with tens of objects and humans in minutes. Our final contribution is to showcase how to use a DSG for real-time hierarchical semantic path-planning. The core modules in Kimera have been released open source.

Ambulatory Assessment

2009 ◽  
Vol 14 (2) ◽  
pp. 109-119 ◽  
Author(s):  
Ulrich W. Ebner-Priemer ◽  
Timothy J. Trull
Keyword(s):  
Real Time ◽  
Clinical Psychology ◽  
Real Life ◽  
Ambulatory Assessment ◽  
Computer Assisted ◽  
Affective Valence ◽  
Time Data ◽  
Physiological Processes ◽  
Context Specific ◽  
Questionnaire Studies

Convergent experimental data, autobiographical studies, and investigations on daily life have all demonstrated that gathering information retrospectively is a highly dubious methodology. Retrospection is subject to multiple systematic distortions (i.e., affective valence effect, mood congruent memory effect, duration neglect; peak end rule) as it is based on (often biased) storage and recollection of memories of the original experience or the behavior that are of interest. The method of choice to circumvent these biases is the use of electronic diaries to collect self-reported symptoms, behaviors, or physiological processes in real time. Different terms have been used for this kind of methodology: ambulatory assessment, ecological momentary assessment, experience sampling method, and real-time data capture. Even though the terms differ, they have in common the use of computer-assisted methodology to assess self-reported symptoms, behaviors, or physiological processes, while the participant undergoes normal daily activities. In this review we discuss the main features and advantages of ambulatory assessment regarding clinical psychology and psychiatry: (a) the use of realtime assessment to circumvent biased recollection, (b) assessment in real life to enhance generalizability, (c) repeated assessment to investigate within person processes, (d) multimodal assessment, including psychological, physiological and behavioral data, (e) the opportunity to assess and investigate context-specific relationships, and (f) the possibility of giving feedback in real time. Using prototypic examples from the literature of clinical psychology and psychiatry, we demonstrate that ambulatory assessment can answer specific research questions better than laboratory or questionnaire studies.

scholarly journals Real-time Array Shape Estimation Method of Horizontal Suspended Linear Array Based on Non-acoustic Auxiliary Sensors

IEEE Access ◽  
2021 ◽  
pp. 1-1
Author(s):  
Zonglun Che ◽  
Jun Wang ◽  
Jing Zhu ◽  
Bingbing Zhang ◽  
Yang Zhang ◽  
...  
Keyword(s):  
Real Time ◽  
Linear Array ◽  
Estimation Method ◽  
Shape Estimation ◽  
Array Shape Estimation

Risk early warning management and intelligent real-time system of financial enterprises based on fuzzy theory

2020 ◽  
pp. 1-11
Author(s):  
Qiaoying Ding
Keyword(s):  
Real Time ◽  
Early Warning ◽  
Financial Risk ◽  
Evaluation Method ◽  
Comprehensive Evaluation ◽  
Fuzzy Theory ◽  
Fuzzy Comprehensive Evaluation ◽  
Real Time System ◽  
Enterprise Risk ◽  
Early Warning Management

The financial market is changing rapidly. Since joining the WTO, our country’s financial companies have faced pressure from dual competition at domestic and abroad. The complex internal and external environment has forced financial enterprise managers to improve risk prevention awareness, early warning and monitoring, so as to responding to emergencies and challenges in the financial market. However, traditional forecasting and analysis methods have problems such as large workload, low efficiency, and low accuracy. Therefore, this article applies intelligent computing to the forecast of financial markets, using related concepts of fuzzy theory and Internet intelligent technology, and proposes to establish a model system for financial enterprise risk early warning management and intelligent real-time monitoring based on fuzzy theory. This article first collected a large amount of data through the literature investigation method, and made a systematic and complete introduction to the related theoretical concepts of fuzzy theory and financial risk early-warning management, has laid a sufficient theoretical foundation for the subsequent exploration of the application of fuzzy theory in financial enterprise risk early warning management and intelligent real-time systems; Then a fuzzy comprehensive evaluation method that combines the analytic hierarchy process and fuzzy evaluation method is proposed, taking a listed company mainly engaged in automobile sales in our province as a case, the company’s financial risk management and modeling experiment of the intelligent real-time system; Finally quoted specific cases again, used the fuzzy comprehensive evaluation method to carry out risk warning and evaluation on the PPP projects of private enterprises in our province, and concluded that the project risk score is between 20-60, which is meet the severe-medium range in the risk level. Research shows that the use of fuzzy theory and modern network technology can make more accurate warnings and assessments of potential and apparent risks of financial enterprises, greatly improving the safety of financial enterprise management and reducing the losses caused by various risks.

scholarly journals DOLARS, a Distributed On-Line Activity Recognition System by Means of Heterogeneous Sensors in Real-Life Deployments—A Case Study in the Smart Lab of The University of Almería

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 405
Author(s):  
Marcos Lupión ◽  
Javier Medina-Quero ◽  
Juan F. Sanjuan ◽  
Pilar M. Ortigosa
Keyword(s):  
Real Time ◽  
Activity Recognition ◽  
Real Life ◽  
Recognition System ◽  
Machine Learning Algorithms ◽  
Sensor Data ◽  
Heterogeneous Sensors ◽  
On Line ◽  
The University

Activity Recognition (AR) is an active research topic focused on detecting human actions and behaviours in smart environments. In this work, we present the on-line activity recognition platform DOLARS (Distributed On-line Activity Recognition System) where data from heterogeneous sensors are evaluated in real time, including binary, wearable and location sensors. Different descriptors and metrics from the heterogeneous sensor data are integrated in a common feature vector whose extraction is developed by a sliding window approach under real-time conditions. DOLARS provides a distributed architecture where: (i) stages for processing data in AR are deployed in distributed nodes, (ii) temporal cache modules compute metrics which aggregate sensor data for computing feature vectors in an efficient way; (iii) publish-subscribe models are integrated both to spread data from sensors and orchestrate the nodes (communication and replication) for computing AR and (iv) machine learning algorithms are used to classify and recognize the activities. A successful case study of daily activities recognition developed in the Smart Lab of The University of Almería (UAL) is presented in this paper. Results present an encouraging performance in recognition of sequences of activities and show the need for distributed architectures to achieve real time recognition.

scholarly journals A Probabilistic Model for Real-Time Semantic Prediction of Human Motion Intentions from RGBD-Data

Sensors ◽  
2021 ◽  
Vol 21 (12) ◽  
pp. 4141
Author(s):  
Wouter Houtman ◽  
Gosse Bijlenga ◽  
Elena Torta ◽  
René van de Molengraft
Keyword(s):  
Real Time ◽  
Collision Avoidance ◽  
Probabilistic Model ◽  
Real Life ◽  
Human Motion ◽  
Model Based ◽  
Multiple Hypotheses ◽  
Navigation Algorithms ◽  
The Right ◽  
Motion Behavior

For robots to execute their navigation tasks both fast and safely in the presence of humans, it is necessary to make predictions about the route those humans intend to follow. Within this work, a model-based method is proposed that relates human motion behavior perceived from RGBD input to the constraints imposed by the environment by considering typical human routing alternatives. Multiple hypotheses about routing options of a human towards local semantic goal locations are created and validated, including explicit collision avoidance routes. It is demonstrated, with real-time, real-life experiments, that a coarse discretization based on the semantics of the environment suffices to make a proper distinction between a person going, for example, to the left or the right on an intersection. As such, a scalable and explainable solution is presented, which is suitable for incorporation within navigation algorithms.

scholarly journals Electronic Orientation Aid for Visually Impaired using Graphics Processing Unit (GPU)

2020 ◽  
Vol 32 ◽  
pp. 03054
Author(s):  
Akshata Parab ◽  
Rashmi Nagare ◽  
Omkar Kolambekar ◽  
Parag Patil
Keyword(s):  
Real Time ◽  
Visually Impaired ◽  
Graphics Processing Unit ◽  
Human Perception ◽  
Processing Unit ◽  
Surrounding Environment ◽  
Visually Impaired People ◽  
Impaired People ◽  
Definition Of ◽  
Graphics Processing

Vision is one of the very essential human senses and it plays a major role in human perception about surrounding environment. But for people with visual impairment their definition of vision is different. Visually impaired people are often unaware of dangers in front of them, even in familiar environment. This study proposes a real time guiding system for visually impaired people for solving their navigation problem and to travel without any difficulty. This system will help the visually impaired people by detecting the objects and giving necessary information about that object. This information may include what the object is, its location, its precision, distance from the visually impaired etc. All these information will be conveyed to the person through audio commands so that they can navigate freely anywhere anytime with no or minimal assistance. Object detection is done using You Only Look Once (YOLO) algorithm. As the process of capturing the video/images and sending it to the main module has to be carried at greater speed, Graphics Processing Unit (GPU) is used. This will help in enhancing the overall speed of the system and will help the visually Impaired to get the maximum necessary instructions as quickly as possible. The process starts from capturing the real time video, sending it for analysis and processing and get the calculated results. The results obtained from analysis are conveyed to user by means of hearing aid. As a result by this system the blind or the visually impaired people can visualize the surrounding environment and travel freely from source to destination on their own.

scholarly journals Home-based Cardiac Rehabilitation - the real barriers of programs at distance

2021 ◽  
Vol 28 (Supplement_1) ◽  
Author(s):  
J Brito ◽  
I Aguiar-Ricardo ◽  
P Alves Da Silva ◽  
B Valente Da Silva ◽  
N Cunha ◽  
...  
Keyword(s):  
Exercise Training ◽  
Cardiac Rehabilitation ◽  
Real Time ◽  
Training Session ◽  
Real Life ◽  
Participation Rate ◽  
Exercise Session ◽  
Exterior Space ◽  
Supervised Exercise ◽  
Home Based

Abstract Funding Acknowledgements Type of funding sources: None. Introduction Despite the established benefits of cardiac rehabilitation (CR), it remains significantly underutilized. Home-based CR (CR-HB) programs should offer the same core CR components as Centre-based programs (CR-CB) but several aspects need to be adapted, communication and supervision must be improved. Although CR-HB has been successfully deployed and is a valuable alternative to CR-CB, there is less structured experience with these non-uniform programs and further studies are needed to understand which patients (pts) are indicated to this type of program. Purpose To investigate pt-perceived facilitators and barriers to home-based rehabilitation exercise. Methods Prospective cohort study which included pts who were participating in a CR-CB program and accepted to participate in a CR-HB program after CR-CB closure due to COVID-19. The CR-HB consisted in a multidisciplinary digital CR program, including pt risk evaluation and regular assessment, exercise, educational and psychological sessions. The online exercise training sessions consisted of recorded videos and real time online supervised exercise training group sessions. It was recommended to do each session 3 times per week, during 60 min. A pictorial exercise training guidebook was available to all participants including instructions regarding safety, clothing and warm-up, and a detailed illustrated description of each  exercise sessions. Also, for questions or difficulties regarding the exercises, an e-mail and telephone was provided. Once a month, real time CR exercise sessions was provided with a duration of 60min. Results 116 cardiovascular disease pts (62.6 ± 8.9years, 95 males) who were attending a face-to-face CR program were included in a CR-HB program. The majority of the pts had coronary artery disease (89%) and 5% valvular disease. Regarding risk factors, obesity was the most common (75%) followed by hypertension (60%), family history (42%), dyslipidaemia (38%), diabetes (18%), and smoking (13%). Almost half (47%) of the participants did at least one online exercise training session per week: 58% did 2-3 times per week, 27% once per week and 15% more than 4 times per week. Participants who did less than one exercise session per week reported as cause: lack of motivation (38%), preference of a different mode of exercise training such as exercise in the exterior space (26%), technology barrier such as impossibility to stream online videos (11%), fear of performing exercise without supervision (4%), and limited space at home (4%). Conclusions Our study based on real-life results of a CR-HB program shows a sub-optimal rate of participation in exercise sessions due to different causes, but mainly for the lack of motivation to exercise alone or preference for walking in exterior space. The knowledge of the CR-HB program barriers will facilitate to find out strategies to increase the participation rate and to select the best candidates for this type of programs.

Sign in / Sign up

Export Citation Format

Share Document