Detection of Indonesian Fishing Vessels on Unmanned Aerial Vehicle Images using YOLOv5s

UPT Port, Marine and Fishery Resources Management Tamperan, Pacitan, several obstacles are often encountered in carrying out operational supervision of the transportation of fishing vessels. Namely, some sailors or fishermen place their boats not in the zone, so officers have to check which boats are not appropriate and instructed to justify parking even though the number of personnel and technology is limited, which takes a long time in the data collection process. To solve this problem, the authors researched the detection of Indonesian fishing vessel types (daplangan boat, jukung boat, hand line boat, and purse seine boat) on Unmanned Aerial Vehicle (UAV) images taken in the parking zone at the port. After obtaining the image data, preprocessing is carried out in several stages: image standardization by resizing as needed, data sharing (69% training data, 19% validation data, 11% test data) by cross-validation, and making ground truth. Deep learning-based detection technique specifications using the YOLOv5s architecture. The results obtained from the method used are the recall value of 0.932, precision value of 0.941, mAP@ 0.5 of 0.972, and mAP@ 0.5:0.95 of 0.74.