ATR performance improvement using images with corrupted or missing pixels

Surveillance images downlinked from unmanned air vehicles (UAVs) may have corrupted pixels due to channel interferences from the adversary’s jammer. Moreover, the images may be deliberately downsampled in order to conserve the scarce bandwidth in UAVs. As a result, the automatic target recognition (ATR) performance may degrade significantly because of poor image quality due to corrupted and missing pixels. In this paper, we present some preliminary results of a novel approach to automatic target recognition based on corrupted images. First, we present a new matrix completion algorithm to reconstruct missing pixels in electro-optical (EO) images. Second, we extensively evaluated our algorithm using many EO images with different missing rates. It was observed that recovering performance in terms of peak signal-to-noise ratio (PSNR) is very good. Third, we compared with a state-of-the-art algorithm and found that our performance is superior. Finally, experiments using an ATR algorithm showed that the target detection performance (precision and recall) has been improved after applying our algorithm, as compared to those results generated by using interpolated images.

[1]  Hairong Qi,et al.  Identify anomaly componentbysparsity and low rank , 2015, 2015 7th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS).

[2]  Truong Q. Nguyen,et al.  SAR image compression using wavelets , 2001, SPIE Defense + Commercial Sensing.

[3]  Truong Q. Nguyen,et al.  Very low bit-rate video compression using wavelets , 2001, SPIE Defense + Commercial Sensing.

[4]  Chiman Kwan,et al.  A Complete Image Compression Scheme Based on Overlapped Block Transform with Post-Processing , 2006, EURASIP J. Adv. Signal Process..

[5]  Chiman Kwan,et al.  Enhancing Mastcam Images for Mars Rover Mission , 2017, ISNN.

[6]  Chiman Kwan,et al.  Perceptually Lossless Image Compression with Error Recovery , 2018, ICVISP.

[7]  Chiman Kwan,et al.  Missing Link Prediction in Social Networks , 2018, ISNN.

[8]  Dongxu Li,et al.  A Hierarchical Approach To Multi-Player Pursuit-Evasion Differential Games , 2005, Proceedings of the 44th IEEE Conference on Decision and Control.

[9]  Emmanuel J. Candès,et al.  Exact Matrix Completion via Convex Optimization , 2009, Found. Comput. Math..

[10]  Chiman Kwan,et al.  Bum scar detection using cloudy MODIS images via low-rank and sparsity-based models , 2016, 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[11]  Vishal M. Patel.  Sparse and Redundant Representations for Inverse Problems and Recognition , 2010 .

[12]  Chiman Kwan,et al.  Perceptually Lossless Video Compression with Error Concealment , 2018, ICVISP.

[13]  J. Zhou.  Fast Anomaly Detection Algorithms For Hyperspectral Images , 2015 .

[14]  Chiman Kwan,et al.  Anomaly detection in hyperspectral images through spectral unmixing and low rank decomposition , 2016, 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[15]  Chiman Kwan,et al.  Application of Deep Belief Network to Land Cover Classification Using Hyperspectral Images , 2017, ISNN.

[16]  Chiman Kwan,et al.  A novel and comprehensive compressive sensing-based system for data compression , 2012, 2012 IEEE Globecom Workshops.

[17]  Chiman Kwan,et al.  Pansharpening of Mastcam images , 2017, 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[18]  Baoxin Li,et al.  A Generic Approach to Object Matching and Tracking , 2006, ICIAR.

[19]  Yuzhong Shen,et al.  Deep learning for effective detection of excavated soil related to illegal tunnel activities , 2017, 2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON).

[20]  Chiman Kwan,et al.  New sparsity based pansharpening algorithms for hyperspectral images , 2017, 2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON).

[21]  David B. Dunson,et al.  Nonparametric Bayesian Dictionary Learning for Analysis of Noisy and Incomplete Images , 2012, IEEE Transactions on Image Processing.

[22]  Chiman Kwan,et al.  On the use of radiance domain for burn scar detection under varying atmospheric illumination conditions and viewing geometry , 2017, Signal Image Video Process..

[23]  Chiman Kwan,et al.  A joint sparsity approach to tunnel activity monitoring using high resolution satellite images , 2017, 2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON).

[24]  William H. Press,et al.  Numerical Recipes 3rd Edition: The Art of Scientific Computing , 2007 .

[25]  Chiman Kwan,et al.  High Performance Video Codec with Error Concealment , 2018, 2018 Data Compression Conference.

[26]  Roberto Brunelli,et al.  Template Matching Techniques in Computer Vision: Theory and Practice , 2009 .

[27]  Chiman Kwan,et al.  High performance image completion using sparsity based algorithms , 2018, Commercial + Scientific Sensing and Imaging.

[28]  Chiman Kwan,et al.  Hybrid Sensor Network Data Compression with Error Resiliency , 2018, 2018 Data Compression Conference.

[29]  Hairong Qi,et al.  Low-rank tensor decomposition based anomaly detection for hyperspectral imagery , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[30]  Hairong Qi,et al.  DOES multispectral / hyperspectral pansharpening improve the performance of anomaly detection? , 2017, 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).