One of the most important industries in any country is the agricultural sector. However, in some countries, farmers and fishermen have limited technology compared to other developed Countries. One of the effects of limited technology the quality of crops, fruits, and vegetables is low. Determination of quality and the level of ripeness of the fruit requires a consistency that can be difficult and tiring for people when it becomes repetitive work.
The objective of the system is to minimize the number of human-computer interactions, speed up the identification process, and improve the usability of the graphical user interface compared to existing manual systems.
Using machine learning algorithms and image processing techniques.
The goal is to build an accurate, fast and reliable fruit detection system, which is a crucial element of an autonomous agricultural robotics platform; is a key element for fruit yield estimation and automated harvesting. Recent work in deep neural networks has led to the development of a state-of-the-art object detector called Faster Region-based CNN (Faster R-CNN). We adapted this model using transfer learning for a fruit detection task using images obtained from two modalities: color (RGB) and Near-Infrared (NIR). Early and late fusion methods for combining multimodal (RGB and NIR) information are investigated.
Log in or sign up for Devpost to join the conversation.