Discussion Panel on Computer Vision and Occupational Ergonomics

Author(s):  
Robert G. Radwin ◽  
SangHyun Lee ◽  
Kang Li ◽  
Max Lieblich ◽  
Byoung-keon Daniel Park

Computer vision has already impacted a diverse field of applications, ranging from industrial robotics, intelligent and autonomous vehicles, security surveillance, manufacturing inspection, and human-computer interaction. Furthermore, digital imaging technologies are advancing ever smaller in size, finer in granularity, and faster in processing, while becoming less expensive and thus more accessible to businesses, organizations, and individuals in devices such as smart phones and tablets. Consumer products such as the Kinect™ offer advanced marker-less 3D motion capture capabilities at a low cost. New computer vision methods are now being researched and developed for occupational ergonomics applications. It is anticipated that these new tools will profoundly impact the future of occupational ergonomics and provide a variety of new instruments and techniques for design, analysis and evaluation in the practice of ergonomics. A panel of leading experts will describe some of the cutting edge research they are pursuing utilizing computer vision for occupational ergonomics applications. Radwin, Lee and Li use algorithms that track pixel patterns recorded from conventional video for quantifying repetitive hand motion, manual lifting and whole-body activities. Lee and Li describe the use computer vision tools to predict joint angles for a whole-body link model. Lieblich and Park describe the use of Kinect™ for classifying postures and generating individualized task specific avatars. Each of these approaches has specific advantages and limitations, which will be addressed by the panel. A discussion will follow exploring future research needs as well as engaging in a discussion among panelists and attendees about the needs, limitations, and obstacles that this new technology faces in bringing it into practice.

2018 ◽  
Vol 32 (2) ◽  
pp. 103-119
Author(s):  
Colleen M. Boland ◽  
Chris E. Hogan ◽  
Marilyn F. Johnson

SYNOPSIS Mandatory existence disclosure rules require an organization to disclose a policy's existence, but not its content. We examine policy adoption frequencies in the year immediately after the IRS required mandatory existence disclosure by nonprofits of various governance policies. We also examine adoption frequencies in the year of the subsequent change from mandatory existence disclosure to a disclose-and-explain regime that required supplemental disclosures about the content and implementation of conflict of interest policies. Our results suggest that in areas where there is unclear regulatory authority, mandatory existence disclosure is an effective and low cost regulatory device for encouraging the adoption of policies desired by regulators, provided those policies are cost-effective for regulated firms to implement. In addition, we find that disclose-and-explain regulatory regimes provide stronger incentives for policy adoption than do mandatory existence disclosure regimes and also discourage “check the box” behavior. Future research should examine the impact of mandatory existence disclosure rules in the year that the regulation is implemented. Data Availability: Data are available from sources cited in the text.


Author(s):  
Anne Steinemann

Abstract Fragrance is used in consumer products around the world. However, fragrance has been associated with adverse effects on indoor and outdoor air quality and human health. Questions arise, such as the following: Why does fragrance in products pose problems? What are sources of emissions and exposures? What are health and societal effects? What are possible solutions? This paper examines the issue of fragranced consumer products and its science and policy dimensions, with a focus on the implications for air quality and human health. Results include new findings and new questions for future research directions.


Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 343
Author(s):  
Kim Bjerge ◽  
Jakob Bonde Nielsen ◽  
Martin Videbæk Sepstrup ◽  
Flemming Helsing-Nielsen ◽  
Toke Thomas Høye

Insect monitoring methods are typically very time-consuming and involve substantial investment in species identification following manual trapping in the field. Insect traps are often only serviced weekly, resulting in low temporal resolution of the monitoring data, which hampers the ecological interpretation. This paper presents a portable computer vision system capable of attracting and detecting live insects. More specifically, the paper proposes detection and classification of species by recording images of live individuals attracted to a light trap. An Automated Moth Trap (AMT) with multiple light sources and a camera was designed to attract and monitor live insects during twilight and night hours. A computer vision algorithm referred to as Moth Classification and Counting (MCC), based on deep learning analysis of the captured images, tracked and counted the number of insects and identified moth species. Observations over 48 nights resulted in the capture of more than 250,000 images with an average of 5675 images per night. A customized convolutional neural network was trained on 2000 labeled images of live moths represented by eight different classes, achieving a high validation F1-score of 0.93. The algorithm measured an average classification and tracking F1-score of 0.71 and a tracking detection rate of 0.79. Overall, the proposed computer vision system and algorithm showed promising results as a low-cost solution for non-destructive and automatic monitoring of moths.


Electronics ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 517
Author(s):  
Seong-heum Kim ◽  
Youngbae Hwang

Owing to recent advancements in deep learning methods and relevant databases, it is becoming increasingly easier to recognize 3D objects using only RGB images from single viewpoints. This study investigates the major breakthroughs and current progress in deep learning-based monocular 3D object detection. For relatively low-cost data acquisition systems without depth sensors or cameras at multiple viewpoints, we first consider existing databases with 2D RGB photos and their relevant attributes. Based on this simple sensor modality for practical applications, deep learning-based monocular 3D object detection methods that overcome significant research challenges are categorized and summarized. We present the key concepts and detailed descriptions of representative single-stage and multiple-stage detection solutions. In addition, we discuss the effectiveness of the detection models on their baseline benchmarks. Finally, we explore several directions for future research on monocular 3D object detection.


Rare Metals ◽  
2021 ◽  
Author(s):  
Jia-Xing Song ◽  
Xin-Xing Yin ◽  
Zai-Fang Li ◽  
Yao-Wen Li

Abstract As a promising photovoltaic technology, perovskite solar cells (pero-SCs) have developed rapidly over the past few years and the highest power conversion efficiency is beyond 25%. Nowadays, the planar structure is universally popular in pero-SCs due to the simple processing technology and low-temperature preparation. Electron transport layer (ETL) is verified to play a vital role in the device performance of planar pero-SCs. Particularly, the metal oxide (MO) ETL with low-cost, superb versatility, and excellent optoelectronic properties has been widely studied. This review mainly focuses on recent developments in the use of low-temperature-processed MO ETLs for planar pero-SCs. The optical and electronic properties of widely used MO materials of TiO2, ZnO, and SnO2, as well as the optimizations of these MO ETLs are briefly introduced. The commonly used methods for depositing MO ETLs are also discussed. Then, the applications of different MO ETLs on pero-SCs are reviewed. Finally, the challenge and future research of MO-based ETLs toward practical application of efficient planar pero-SCs are proposed. Graphical abstract


2019 ◽  
Vol 18 (1-2) ◽  
pp. 101-128
Author(s):  
Mair E. Lloyd ◽  
James Robson

Abstract Between 2000 and 2013, over 8,000 students studied the module Reading Classical Latin at the Open University, the United Kingdom’s largest distance education provider. But while many learners attained high grades, a significant proportion withdrew from study or failed the module. In 2015, the original module was replaced with a completely new course, Classical Latin: The Language of Ancient Rome. This article details the innovative ways in which new technology and pedagogical theory from Modern Foreign Language (MFL) learning were drawn on by the team designing this new module, resulting in a learning experience which gives greater emphasis to elements such as spoken Latin, the intrinsic pleasure of reading, and cultural context. The (largely positive) effects of these pedagogical changes on student success and satisfaction are subsequently analysed using a rich mix of qualitative and quantitative data. Finally, the authors reflect on lessons learned and the possibilities for future research and enhancement.


SAGE Open ◽  
2021 ◽  
Vol 11 (3) ◽  
pp. 215824402110269
Author(s):  
Guangbao Fang ◽  
Philip Wing Keung Chan ◽  
Penelope Kalogeropoulos

Using data from the Teaching and Learning International Survey (TALIS; 2013), this article explores teachers’ needs, support, and barriers in their professional development. The research finds that Australian teachers expressed greater needs in information and communication technology (ICT) use and new technology training for teaching, while Shanghai teachers required more assistance to satisfy students’ individual learning and pedagogical competencies. More than 80% of Australian and Shanghai teachers received scheduled time to support their participation in professional development, whereas less than 20% of Australian and Shanghai teachers received monetary or nonmonetary support. In terms of barriers, Australian and Shanghai teachers reported two significant barriers that conflicted with their participation in professional development: “working schedule” and “a lack of incentives to take part.” This article reveals implications of the study in the design of an effective professional development program for Australian and Shanghai teachers and ends with discussing the limitations of the research and future research directions.


Sensors ◽  
2019 ◽  
Vol 19 (22) ◽  
pp. 4916 ◽  
Author(s):  
Qiaoyun Wu ◽  
Yunzhe Zhang ◽  
Qian Yang ◽  
Ning Yuan ◽  
Wei Zhang

The vital importance of rapid and accurate detection of food borne pathogens has driven the development of biosensor to prevent food borne illness outbreaks. Electrochemical DNA biosensors offer such merits as rapid response, high sensitivity, low cost, and ease of use. This review covers the following three aspects: food borne pathogens and conventional detection methods, the design and fabrication of electrochemical DNA biosensors and several techniques for improving sensitivity of biosensors. We highlight the main bioreceptors and immobilizing methods on sensing interface, electrochemical techniques, electrochemical indicators, nanotechnology, and nucleic acid-based amplification. Finally, in view of the existing shortcomings of electrochemical DNA biosensors in the field of food borne pathogen detection, we also predict and prospect future research focuses from the following five aspects: specific bioreceptors (improving specificity), nanomaterials (enhancing sensitivity), microfluidic chip technology (realizing automate operation), paper-based biosensors (reducing detection cost), and smartphones or other mobile devices (simplifying signal reading devices).


2020 ◽  
Vol 98 (Supplement_2) ◽  
pp. 21-21
Author(s):  
David J Smith

Abstract Most commodity crops undergo milling, husking, ginning or other processing procedures before use as human food or fiber. Byproduct nutrient density varies with the type of grain or oil seed processed and use typically varies with nutrient needs of specific production situations. Drought or high grain prices may increase the use of byproducts; regionally available, low-cost ingredients such as cotton ginning byproduct may be used extensively by beef producers to replace forage. Doubt associated with the use of such byproducts is not typically related to nutritional value but with uncertainties about the presence of residual pesticides, herbicides, or harvest-aid chemicals. Potential chemical residues in consumer products and the concomitant financial and reputational losses borne by the industry provide an impetus for concern. Negative experiences with contaminated Australian beef established a long-lived suspicion of “cotton trash” that continues to impact the industry today. The purpose of this review is to discuss sources, amounts, and risks of chemical residues associated with byproduct feeds used in the southern United States with cotton ginning byproducts as a major focus. The use patterns of specific crop protection and harvest-aid chemicals will be discussed in context with chemical tolerances established by the U.S. EPA. In addition, U.S. pesticide monitoring programs in beef will be discussed. Although data describing the transmission of chemical residues from byproduct feeds into beef products are limited, the available data suggest some best practices could be adopted to mitigate concerns and minimize possible agrochemical residue contamination of beef.


Sign in / Sign up

Export Citation Format

Share Document