Related Experiment Video
Updated: May 16, 2026
07:52
Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories
Published on: July 10, 2019
An embedded real-time red peach detection system based on an OV7670 camera, ARM cortex-M4 processor and 3D look-up
Mercè Teixidó1, Davinia Font, Tomàs Pallejà
1Department of Computer Science and Industrial Engineering, University of Lleida, Jaume II 69, 25001 Lleida, Spain. mteixido@diei.udl.cat
Sensors (Basel, Switzerland)
|December 4, 2012
Summary
This study presents an embedded system for real-time fruit detection, crucial for future automated harvesting. The system uses an ARM Cortex-M4 processor and camera to track fruit, enabling robotic picking.
Area of Science:
- Robotics and Automation
- Computer Vision
- Agricultural Technology
Background:
- Automated fruit harvesting requires precise real-time fruit detection and tracking.
- Existing systems may lack the embedded processing power and portability for direct robotic integration.
Purpose of the Study:
- To develop an embedded real-time fruit detection system for robotic harvesting arms.
- To enable automatic fruit selection and picking directly from trees.
Main Methods:
- Utilized an ARM Cortex-M4 (STM32F407VGT6) processor and an Omnivision OV7670 camera.
- Implemented a 3D Look-Up Table (LUT) in RGB color space for fruit detection and tracking.
- Compared two methodologies for optimizing 3D LUTs using color models and fruit histograms.
Main Results:
- The embedded system achieves real-time fruit detection and tracking.
- The system can acquire general and zoomed orchard images.
- Relative tracking information for red peaches is updated up to ten times per second.
Conclusions:
- The developed embedded system is suitable for integration into robotic harvesting grippers.
- The 3D LUT approach provides efficient real-time performance for fruit detection.
- This technology paves the way for advanced automated fruit harvesting solutions.
