Abstract

Crystal Guava is one type of seedless guava that has high economic value and is favored by the people of Indonesia. Crystal guava fruit has a dark green color when it is still unripe and turns light green when it is ripe. With the decreasing workforce in agriculture, it is necessary to think about developing an automatic crystal guava harvesting process, where the three-dimensional positioning of suitable guava fruit is a very important process. The purpose of this study was to determine the three-dimensional position of ripe Crystal Guava fruit using stereo sensing. Crystal guava plants in pots that have been fruitful are imaged using a stereo camera and then the image of the plants obtained is processed to separate the image of the fruit from other components. The fruit image resulting from image processing is then calculated for its three-dimensional position using the triangulation principle. Stereo cameras were placed at a distance of 30 cm to 70 cm from plants with four treatments, the distances between cameras were 8 cm, 10 cm, 12 cm, and 14 cm. The test results with different camera distances show that the average accuracy of three-dimensional positioning is 99.3%, 99.3%, 98.8%, 98.7%, respectively. The average three-timed Root Mean Square Error values ​​for the four camera distance treatments were 0.34 cm, 0.37 cm, 0.61 cm, 0.57 cm, respectively.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.