Awesome
jitter-compensation
Remote Sensing Image Jitter Detection and Compensation Using Convolutional Neural Network
This the code from the paper Remote Sensing Image Jitter Detection and Compensation Using Convolutional Neural Network
We use neural networks to correct the deformed remote sensing images.
Framework: python3.5 + tensorflow1.4 + keras the most latest version
Platform: Windows Spyder
Proposed architecture:
<center> <img src="https://github.com/caiya55/jitter-compensation/raw/master/fig/overview.jpg" width="70%" height="70%" /> Figure 1. Architecture of the proposed framework </center>CNN framework
<center> <img src="https://github.com/caiya55/jitter-compensation/raw/master/fig/network.jpg" width="80%" height="80%" /> Figure 2. Architecture of the proposed neural network </center>Experiment results on real remote sensing images are expressed below:
<center> <img src="https://github.com/caiya55/jitter-compensation/raw/master/fig/result1.jpg" width="80%" height="80%" /> Figure 3. Left: Raw deformed image; Middle: Resotred image by proposed method. Right: Resoted image by on board sensors </center> <center> <img src="https://github.com/caiya55/jitter-compensation/raw/master/fig/result2.jpg" width="80%" height="80%" /> Figure 4. Left: Raw deformed image; Middle: Resotred image by proposed method. Right: Resoted image by on board sensors </center> <center> <img src="https://github.com/caiya55/jitter-compensation/raw/master/fig/result3.jpg" width="80%" height="80%" /> Figure 4. Left: Raw deformed image; Middle: Resotred image by proposed method. Right: Resoted image by on board sensors </center>