Object detection in satellite imagery is very important for a wide array of applications in surveillance system, monitoring tasks etc. The satellite images have lower resolution as compared to aerial images and hence detecting smaller objects such as vehicles, aircrafts in a remotely sensed image is a challenging task. In this paper, we focus on the comparative study of three different models namely YoloV3, SSD and RCNN. We have tested all the three models to find out which model performed best for the task of airplane detection when trained on aerial images and tested for small object detection (airplanes in our case) on satellite images. Finally, we illustrated the comparison of the three models on the basis of accuracy, losses etc.
Comparative Assessment of Different Deep Learning Models for Aircraft Detection
01.06.2020
725001 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Small aircraft detection using deep learning
Emerald Group Publishing | 2021
|On the Detection of Aircraft Single Engine Taxi using Deep Learning Models
ArXiv | 2024
|