Faster Interactive Segmentation of Identical-Class Objects With One Mask in High-Resolution Remotely Sensed Imagery

Zhili Zhang , Associate Member, IEEE, Jiabo Xu, Student Member, IEEE, Xiangyun Hu ,Bingnan Yang , and Mi Zhang
1 Zhili Zhang, Jiabo Xu, Bingnan Yang, and Mi Zhang are with the School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China (e-mail: zhangzhili@whu.edu.cn; xujiabo@whu.edu.cn; bingnan.yang@whu.edu.cn; mizhang@whu.edu.cn).
2 Xiangyun Hu is with the School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China, and also with the Hubei Luojia Laboratory, Wuhan 430079, China (e-mail: huxy@whu.edu.cn).
Corresponding author { mizhang@whu.edu.cn }

Novel heuristic scheme for faster IS of all buildings simultaneously. The IS model represents the IS model. The proposed ICODet rapidly detects all objects of the identical class (highlighted with yellow dotted-line boxes) in images, guided by a support object with its mask.