Automated Market Studies about Energy use based on Computer Vision and Deep Learning
Mentor: Elena Lopez Guillén
Phone: (+34) 918856567
University: Universidad de Alcalá
Partner Host Institution: Nielsen
- 2nd year of applied research compulsory This research line has been developed together with Nielsen. The second year of applied research in Nielsen is compulsory under this line.
Keywords: Data analytics, computer vision, deep learning, market studies, text recognition, natural scenes

Automated Market Studies about Energy use based on Computer Vision and Deep Learning

The study of energy consumption habits in consumers is useful to save money, energy and decrease pollution. Nowadays, the big amount of data managed in market statistics requires a certain grade of automation to process the information within an acceptable period of time.
In this regard, automated recognition in images can greatly help to perform energy market studies where visual inspection is required. The application of camera-based systems has exponentially grown in recent years due to the improvements in camera features and computer vision techniques. Besides, the rise of deep learning in the last decade has greatly enhanced the effectiveness of computer vision systems, which can automatically compute and extract very relevant information from images.
According to the previous considerations, the goal of the proposed project is to research on innovative computer vision and deep learning algorithms with the aim of contributing in the automation of energy consumption market studies based on information obtained from images.

Collaboration with Nielsen
Nielsen will be the industrial partner in this project. Nielsen is a global measurement and data analytics company that provides the most complete and trusted view available of consumers and markets worldwide. For this research proposal, Nielsen can provide the previous experience of its engineering and image recognition global teams, access to a large amount of labeled image data and specialized resources to conduct the research.

Departament: Electronics
Research Group: Robotics and e-Safety Unit
More Information:,
Relevants projects on the area:
Relevants publications on the area: 1.- R. Arroyo, P. F. Alcantarilla, L. M. Bergasa, and E. Romera, "Are you ABLE to perform a life-long visual topological localization?", Autonomous Robots (AURO), 42 (3), pp. 665-685, March 2018.
2.- R. Arroyo, P. F. Alcantarilla, L. M. Bergasa and E. Romera, "Fusion and Binarization of CNN Features for Robust Topological Localization across Seasons", in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4656-4663, October 2016.