Geodesic
M2F2-RCNN: Multi-functional Faster RCNN Based on Multi-scale Feature Fusion for Region Search in Remote Sensing Images
Computer Science and Information Systems, Tome 20 (2023) no. 4.

Voir la notice de l'article provenant de la source Computer Science and Information Systems website

In order to realize fast and accurate search of sensitive regions in remote sensing images, we propose a multi-functional faster RCNN based on multi-scale feature fusion model for region search. The feature extraction network is based on ResNet50 and the dilated residual blocks are utilized for multi-layer and multi-scale feature fusion. We add a path aggregation network with a convolution block attention module (CBAM) attention mechanism in the backbone network to improve the efficiency of feature extraction. Then, the extracted feature map is processed, and RoIAlign is used to improve the pooling operation of regions of interest and it can improve the calculation speed. In the classification stage, an improved non-maximum suppression is used to improve the classification accuracy of the sensitive region. Finally, we conduct cross validation experiments on Google Earth dataset and the DOTA dataset. Meanwhile, the comparison experiments with the state-of-the-art methods also prove the high efficiency of the proposed method in region search ability.
Keywords: remote sensing images, region search, multi-functional faster RCNN, multi-scale feature fusion, convolution block attention module 
@article{CSIS_2023_20_4_a3,
     author = {Shoulin Yin and Liguo Wang and Qunming Wang and Mirjana Ivanovi\'c and Jinghui Yang},
     title = {M2F2-RCNN: {Multi-functional} {Faster} {RCNN} {Based} on {Multi-scale} {Feature} {Fusion} for {Region} {Search} in {Remote} {Sensing} {Images}},
     journal = {Computer Science and Information Systems},
     publisher = {mathdoc},
     volume = {20},
     number = {4},
     year = {2023},
     url = {http://geodesic.mathdoc.fr/item/CSIS_2023_20_4_a3/}
}
TY  - JOUR
AU  - Shoulin Yin
AU  - Liguo Wang
AU  - Qunming Wang
AU  - Mirjana Ivanović
AU  - Jinghui Yang
TI  - M2F2-RCNN: Multi-functional Faster RCNN Based on Multi-scale Feature Fusion for Region Search in Remote Sensing Images
JO  - Computer Science and Information Systems
PY  - 2023
VL  - 20
IS  - 4
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/CSIS_2023_20_4_a3/
ID  - CSIS_2023_20_4_a3
ER  - 
%0 Journal Article
%A Shoulin Yin
%A Liguo Wang
%A Qunming Wang
%A Mirjana Ivanović
%A Jinghui Yang
%T M2F2-RCNN: Multi-functional Faster RCNN Based on Multi-scale Feature Fusion for Region Search in Remote Sensing Images
%J Computer Science and Information Systems
%D 2023
%V 20
%N 4
%I mathdoc
%U http://geodesic.mathdoc.fr/item/CSIS_2023_20_4_a3/
%F CSIS_2023_20_4_a3
Shoulin Yin; Liguo Wang; Qunming Wang; Mirjana Ivanović; Jinghui Yang. M2F2-RCNN: Multi-functional Faster RCNN Based on Multi-scale Feature Fusion for Region Search in Remote Sensing Images. Computer Science and Information Systems, Tome 20 (2023) no. 4. http://geodesic.mathdoc.fr/item/CSIS_2023_20_4_a3/