Zoom out CNNs features for optical remote sensing change detection

In this paper, we propose a novel unsupervised optical remote sensing change detection (CD) based on pre-trained convolutional neural network (CNN) on ImageNet dataset and superpixel (SLIC) segmentation technique. The proposed approach can be divided into three steps. First, bi-temporal images are stacked, and Principal Component Analysis (PCA) is applied to extract three higher uncorrelated channels, which will be later segmented into superpixels. Second, we zoom out each region into three levels and fit them separately into a pre-trained CNN. Third, we extract features of different zooming levels that represent the same region (superpixel) and concatenate them. We compare the concatenated features to get the final change map. The experimental results demonstrate the efficacy of the proposed approach.

[1]  Jitendra Malik,et al.  Object Instance Segmentation and Fine-Grained Localization Using Hypercolumns , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Ming-Hsuan Yang,et al.  Hierarchical Convolutional Features for Visual Tracking , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[3]  Hanjiang Lai,et al.  Deep Cascaded Regression for Face Alignment , 2015 .

[4]  Geoffrey J. Hay,et al.  Object-based change detection , 2012 .

[5]  Vassilis Athitsos,et al.  Evaluation of Deep Learning based Pose Estimation for Sign Language Recognition , 2016, PETRA.

[6]  Turgay Çelik,et al.  Unsupervised Change Detection in Satellite Images Using Principal Component Analysis and $k$-Means Clustering , 2009, IEEE Geoscience and Remote Sensing Letters.

[7]  Dongmei Chen,et al.  Change detection from remotely sensed images: From pixel-based to object-based approaches , 2013 .

[8]  Nicholas J. Tate,et al.  A critical synthesis of remotely sensed optical image change detection techniques , 2015 .

[9]  Qi Tian,et al.  Good Practice in CNN Feature Transfer , 2016, ArXiv.

[10]  Alexander Gepperth,et al.  Towards incremental deep learning: multi-level change detection in a hierarchical recognition architecture , 2015 .

[11]  Kunihiko Fukushima,et al.  Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position , 1980, Biological Cybernetics.

[12]  Gregory Shakhnarovich,et al.  Feedforward semantic segmentation with zoom-out features , 2014, CVPR.

[13]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[14]  Francesca Bovolo,et al.  Supervised change detection in VHR images using contextual information and support vector machines , 2013, Int. J. Appl. Earth Obs. Geoinformation.

[15]  Jitendra Malik,et al.  Region-Based Convolutional Networks for Accurate Object Detection and Segmentation , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[17]  Alexander Gepperth,et al.  Towards incremental deep learning: multi-level change detection in a hierarchical visual recognition architecture , 2016, ESANN.

[18]  James C. Bezdek,et al.  Pattern Recognition with Fuzzy Objective Function Algorithms , 1981, Advanced Applications in Pattern Recognition.

[19]  Junyu Dong,et al.  Automatic Change Detection in Synthetic Aperture Radar Images Based on PCANet , 2016, IEEE Geoscience and Remote Sensing Letters.

[20]  Ashbindu Singh,et al.  Review Article Digital change detection techniques using remotely-sensed data , 1989 .

[21]  Qingjie Liu,et al.  Convolutional neural network features based change detection in satellite images , 2016, International Workshop on Pattern Recognition.

[22]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Rahul Mohan,et al.  Deep Deconvolutional Networks for Scene Parsing , 2014, ArXiv.

[24]  Jie Wang,et al.  Transferring Pre-Trained Deep CNNs for Remote Scene Classification with General Features Learned from Linear PCA Network , 2017, Remote. Sens..

[25]  Lorenzo Bruzzone,et al.  Automatic analysis of the difference image for unsupervised change detection , 2000, IEEE Trans. Geosci. Remote. Sens..

[26]  Gui-Song Xia,et al.  Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery , 2015, Remote. Sens..

[27]  Jian Sun,et al.  Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  Pascal Fua,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Bertrand Le Saux,et al.  Semantic Segmentation of Earth Observation Data Using Multimodal and Multi-scale Deep Networks , 2016, ACCV.

[30]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[31]  Jefersson Alex dos Santos,et al.  Towards better exploiting convolutional neural networks for remote sensing scene classification , 2016, Pattern Recognit..

[32]  Roberto Manduchi,et al.  Bilateral filtering for gray and color images , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[33]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).