Next Article in Journal
Consideration of Uncertainty Information in Accessibility Analyses for an Effective Use of Urban Infrastructures
Previous Article in Journal
Impact of Innovation City Projects on National Balanced Development in South Korea: Identifying Regional Network and Centrality
Article

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

School of Software Engineering, Xi’an Jiaotong University, Xi’an 710049, China
*
Author to whom correspondence should be addressed.
Academic Editors: Wolfgang Kainz and Amr Abd-Elrahman
ISPRS Int. J. Geo-Inf. 2021, 10(3), 170; https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi10030170
Received: 22 January 2021 / Revised: 25 February 2021 / Accepted: 14 March 2021 / Published: 16 March 2021
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 feature. Firstly, an efficient attention network is constructed by introducing the local attention into the convolutional neural network. Combining the shallow low-level features with rich detail descriptions and high-level features with more semantic meanings effectively, efficient convolution features can be obtained. By this, the attention network can effectively enhance the ability to extract small target features and suppressing useless features. Secondly, the efficient feature map is sent to the region proposal network constructed by modified DRL. Using the modified reward function, this model can accumulate more rewards to conduct the search process, and potentially generate effective subsequent proposals and classification scores. It also can increase the effectiveness of object locations and classifications for small targets. Quantitative and qualitative experiments are conducted to verify the detection performance of different models. The results show that the proposed MdrlEcf can effectively and accurately locate and identify related small objects. View Full-Text
Keywords: deep reinforcement learning; attention networks; object detection; VHR remote sensing image deep reinforcement learning; attention networks; object detection; VHR remote sensing image
Show Figures

Figure 1

MDPI and ACS Style

Liu, S.; Tang, J. Modified Deep Reinforcement Learning with Efficient Convolution Feature for Small Target Detection in VHR Remote Sensing Imagery. ISPRS Int. J. Geo-Inf. 2021, 10, 170. https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi10030170

AMA Style

Liu S, Tang J. Modified Deep Reinforcement Learning with Efficient Convolution Feature for Small Target Detection in VHR Remote Sensing Imagery. ISPRS International Journal of Geo-Information. 2021; 10(3):170. https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi10030170

Chicago/Turabian Style

Liu, Shuai, and Jialan Tang. 2021. "Modified Deep Reinforcement Learning with Efficient Convolution Feature for Small Target Detection in VHR Remote Sensing Imagery" ISPRS International Journal of Geo-Information 10, no. 3: 170. https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi10030170

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop