Collective Minds and Machine Challenge: Leveraging Crowdsource Developed Algorithms to Label Satellite Images

Published on November 07, 2018

Abstract

The Laboratory for Innovation Science at Harvard (LISH) has researched the effects of open innovation in government, academia and private industry since 2010. This paper examines the use of crowdsourcing to develop an algorithm for image annotation.

Manual image annotation, the act of assigning, identifying and tagging different elements within a single digital image, is time consuming and potentially expensive task depending on the size and complexity of the images and libraries. A growing demand for both researchers and practitioners to annotate images has resulted in the exploration of a range of crowdsourcing approaches to collect such annotations. As part of the Valley of the Khans Project, the University of California at San Diego (UCSD), the Mongolian Academy of Science, the International Association for Mongol Studies and the National Geographic Society leveraged the power of the crowd to annotate images to identify structures and artifacts in the quest to discover the tomb of Genghis Khan.

While the crowd was successful in performing annotation tasks, the use of crowds in other instances for similar tasks has been limited due to the constraints on the amount of data participants can process. Given the identified limits, LISH, UCSD, NASA and the National Geographic Society wanted to investigate if an algorithm could be developed via an open challenge, that was capable of preforming the same task of image annotation, learning from collective human perception.


Authors

Rinat Sergeev

Dr. Rinat Sergeev is Senior Data Scientist & Scientific Advisor at the Crowd Innovation Lab/NASA Tournament Lab at Harvard University. Rinat works as a head of data science team, and a lead science and technical expert on exploring and utilizing crowdsourcing approaches in application to the data science and algorithmic challenges, coming from NASA, Business, or Academia. In his role, Rinat provides full guidance and support on the way of the project from learning the area and formulating the problem, to controlling the challenge execution and analysing it’s outcome, working closely with all the parties involved. Rinat received his PhD in Quantum Mechanics in Ioffe Institute, Saint Petersburg. Following his innate curiosity, he pursued challenges in a variety of academic fields, from Semiconductors to Immunology and Epidemiology. His research interests include conceptual analysis, analytical approaches and models in multiple areas. His personal interests include Math puzzles, strategic games and politics.

Jin Paik

Jin H. Paik is the Program Director and Senior Researcher at the Laboratory for Innovation Science at Harvard (LISH). In his role, he serves as the lab’s general manager. He works to develop the lab’s strategic vision, as well as to direct project and research activities. He oversees the development of open innovation projects through partnerships with NASA, Harvard Medical School, federal government agencies, academic and research institutions, and industry leaders. He advises organizations on innovation strategies with a focus on starting and scaling open innovation practices. He has worked extensively on programs that focus on data science, development and use of artificial intelligence, technology commercialization, and the future of work. Prior to joining the LISH team, he worked at the Harvard Kennedy School and Mathematica Policy Research. He holds a bachelor’s degree from the University of Michigan and a master’s degree from Harvard University.

Steven Randazzo

Steven is currently serving as an Assistant Director of Research Management at the Laboratory for Innovation Science at Harvard. Previously, he was the Director of Growth and Research at Viva + Impulse Creative Co., a digital advertising agency, where he was responsible for the growth and direction of the agency. Prior to his work with Viva +Impulse, Steven served as the Communications Director and Cofounder of the U.S. Department of Health and Human Services IDEA Lab where he worked with startups and internal government teams to change the way government and health care solved some of the nation’s biggest problems.

Prior to the IDEA Lab, Steven worked at the Substance Abuse and Mental Health Services Administration, as a Senior Advisor to the Administrator after serving in Governor Bill Richardson’s Administration as the Legislative Liaison for the New Mexico Human Services Department.

Karim Lakhani

Karim R. Lakhani is a Professor of Business Administration at the Harvard Business School and one of the Principal Investigators of the Laboratory for Innovation Science at Harvard (LISH). He specializes in the management of technological innovation in firms and communities. His research is on distributed innovation systems and the movement of innovative activity to the edges of organizations and into communities. He has extensively studied the emergence of open source software communities and their unique innovation and product development strategies. He has also investigated how critical knowledge from outside of the organization can be accessed through innovation contests. Currently, Professor Lakhani is investigating incentives and behavior in contests and the mechanisms behind scientific team formation through field experiments on the Topcoder platform and the Harvard Medical School.

View Resource

Sign in below to view this resource. If you do not have an account, you can register for free.