RESEARCHDeep Learning and Vision
We are happy to announce that we were accepted in the NVIDIA Inception program
“Propelling A.I. startups with powerful GPU tools, tech, and deep learning expertise.”
Inception nurtures dedicated and exceptional startups who are revolutionizing industries with advances in AI and data science. This virtual accelerator program helps startups during critical stages of product development, prototyping, and deployment.
Development of methods for monitoring crops using vision and deeplearning
The research project seeks to develop vegetable monitoring methods that will flexibly estimate the relevant variables in the monitoring task under various environmental conditions.
- To investigate the impact of classification methods such as vector support machines and their application in spaces that maximize class separability.
- Evaluation of technologies based on deep learning to segment folliage, classify fruits and diagnose diseases.
- The creation of a method that integrates information of shape and appearance in the monitoring of the status of the plant and that is robust (effective and repeatable) to changes in the environment and of the species of the plant.
- Development of a color space to facilitate the detection of the variables involved in the monitoring of the plant.
- Generation of databases available in the cloud with great diversity of crops and images taken with different sensors.