Robotic broccoli harvesting [Farmer]
Introduction
The selective hand-harvest of fresh market broccoli is labor-intensive and comprises about 35% of the total production costs[1]. Advanced technologies can reduce labor and at the same time increase the efficiency of harvesting procedures. Automated broccoli harvesters have been considered for many years, but changes in the labor picture have increased interest in this idea. The current state of mechanization in broccoli harvest is the use of harvest-aids. This way, workers manually cut the heads off the plants and the harvest-aid helps in sorting and packing the crop in the field. However, the procedure is still labor consuming.[2]
Autonomous harvesting robots with the use of machine vision can bring the desirable results. Machine vision, also known as computer vision, is the science that deals with object recognition and classification by extracting useful information about the object from its image or image set.[3]
Related Scientific Article
Machine vision for a selective broccoli harvesting robot[1]
A research was conducted to determine whether machine vision can be used to detect broccoli heads, as a first step in the development of a fully autonomous selective harvester. In total, 208 broccoli heads were detected by the machine vision software, indicating a sensitivity score of 91.2%.
References
[1] Blok, P.M., Barth, R., van den Berg, W. Machine vision for a selective broccoli harvesting robot (2016), IFAC-PapersOnLine, 49 (16), pp. 66-71.
[2] https://pdfs.semanticscholar.org/d241/95f95ff9fda64e38e09badcad03d191ae122.pdf
[3] Machine Vision. John Billingsley, University of Southern Queensland