Kamda Delly Sunggara, Aviv Yuniar Rahman, Istiadi
Oil palm is one of the most important vegetable oil-producing plants. Currently, oil palm grows as a wild (forest), semi-wild, and cultivated plant that has spread to many countries with tropical climates, even near subtropical Asia, South America, and Africa. The purpose of this research is to classify detection errors in the oil palm harvesting process. And in this case, also training in choosing the right position when harvesting oil palm. In testing the detection of errors in the process of harvesting oil palm using 1000 data. Variations in training and testing data are 50 and 100. In the tests carried out, it can be said that the palm oil detection test using data with a multiple of 50 produces the highest mAP value of 100%, namely on the 50th to 450th data test. Then the results of testing the safety detection of oil palm harvesting at multiples of 100 have the highest mAP results of 97% which is in the test data of 300. The results of false and true motion detection tests to detect movements of oil palm harvesting with multiples of 50 have produced a 100% map. This proves that the Yolo method can be applied in the field of maintaining security in the process of harvesting oil palm. © 2023 IEEE.
Universitas Widyagama Malang, Department of Informatic Engineering, Malang, Indonesia
Research at a Glance
Register to unlock
Topics & SDG Alignment
Register to unlock
Collaboration
Register to unlock
Author Profile (Selected)
Register to unlock
References Overview
Register to unlock
Journal & Source
Register to unlock
Metadata & Integrity
Register to unlock