An Empirical Study of the Convolution Neural Networks Based Detection on Object With Ambiguous Boundary in Remote Sensing Imagery - A Case of Potential Loess Landslide.
Guangle YaoWenlong ZhouMingzhe LiuQiang XuHonghui WangJun LiYuanzhen JuPublished in: IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens. (2022)
Keyphrases
- remote sensing imagery
- neural network
- change detection
- remote sensing
- bounding box
- pattern recognition
- object detection
- false alarms
- spatial relations
- remote sensing images
- wavelet transformation
- remote sensing data
- complex scenes
- data sets
- image processing
- man made
- multi source
- multiple objects
- object segmentation
- multispectral
- unsupervised learning
- fuzzy logic