Modified Deep Reinforcement Learning with Efficient Convolution Feature for Small Target Detection in VHR Remote Sensing Imagery

Modified Deep Reinforcement Learning with Efficient Convolution Feature for Small Target Detection in VHR Remote Sensing Imagery

Small object detection in very-high-resolution (VHR) optical remote sensing images is a fundamental but challenaging problem due to the latent complexities. To tackle this problem, the MdrlEcf model is proposed by modifying deep reinforcement learning (DRL) and extracting the efficient convolution f...

Celý popis

Podrobná bibliografie
Hlavní autoři: Shuai Liu, Jialan Tang
Médium: Článek
Jazyk:English
Vydáno: MDPI AG 2021-03-01
Edice:ISPRS International Journal of Geo-Information
Témata:
deep reinforcement learning
attention networks
object detection
VHR remote sensing image
On-line přístup:https://www.mdpi.com/2220-9964/10/3/170

Internet

https://www.mdpi.com/2220-9964/10/3/170

Podobné jednotky