Considering typical remote sensing object detection problems, this paper proposes an improved remote sensing object detection model based on the YOLOv3 algorithm. This model introduces the SE attention module to get richer features and uses K-means to extract the more suitable anchor for remote sensing images. The experiments are carried out under the DOTA data set, and the results show that, under the premise of unchanged detection speed, the accuracy of detection is improved, and the improved algorithm has a better effect on detecting the small and dense objects.
Remote Sensing Object Detection Based on Improved YOLOv3
2022-10-12
1468673 byte
Conference paper
Electronic Resource
English
SAR SHIP DETECTION BASED ON IMPROVED YOLOV3
TIBKAT | 2021
|Vehicle detection method based on improved YOLOv3
IEEE | 2022
|Improved YOLOv3 Object Classification in Intelligent Transportation System
ArXiv | 2020
|Traffic Object Detection and Distance Estimation Using YOLOv3
SAE Technical Papers | 2022
|Traffic Object Detection and Distance Estimation Using YOLOv3
British Library Conference Proceedings | 2022
|