DISR: Deep Infrared Spectral Restoration Algorithm for Robot Sensing and Intelligent Visual Tracking Systems

Infrared imaging spectrometer (IRIS) often suffers from overlapped bands and random noises, which limit the precision of subsequent processing in robot vision sensing. To address this problem, we propose a novel Gabor transform-based infrared spectrum restoration method by successfully exploring the intrinsic structure of the clean IR spectrum from the degraded one. At first, a total variation (TV) regularized Gabor coefficients adjustment descriptor is designed and incorporated into the spectrum restoration model. Then, the proposed model is inferred via an efficient optimization approach based on split Bregman iteration method. Comprehensive experiments illustrate the significant and consistent improvements of the developed model over state-of-the-art approaches. The restored high-resolution spectrum can be utilized for detecting the different materials in the robot visual tracking systems.

[1]  Hai Liu,et al.  Nonlocal low-rank-based blind deconvolution of Raman spectroscopy for automatic target recognition. , 2018, Applied optics.

[2]  S. Y. Chen,et al.  Kalman Filter for Robot Vision: A Survey , 2012, IEEE Transactions on Industrial Electronics.

[3]  Hai Liu,et al.  Richardson–Lucy blind deconvolution of spectroscopic data with wavelet regularization , 2015 .

[4]  Sannyuya Liu,et al.  Flexible FTIR Spectral Imaging Enhancement for Industrial Robot Infrared Vision Sensing , 2020, IEEE Transactions on Industrial Informatics.

[5]  C. Helstrom Image Restoration by the Method of Least Squares , 1967 .

[6]  Naixue Xiong,et al.  Deep Matrix Factorization With Implicit Feedback Embedding for Recommendation System , 2019, IEEE Transactions on Industrial Informatics.

[7]  Tom Goldstein,et al.  The Split Bregman Method for L1-Regularized Problems , 2009, SIAM J. Imaging Sci..

[8]  Sanya Liu,et al.  Blind spectral deconvolution algorithm for Raman spectrum with Poisson noise , 2014 .

[9]  Shie Qian,et al.  Discrete Gabor transform , 1993, IEEE Trans. Signal Process..

[10]  Rohit Bhargava,et al.  Using Fourier transform IR spectroscopy to analyze biological materials , 2014, Nature Protocols.

[11]  Guoxia Xu,et al.  Spectral semi-blind deconvolution methods based on modified φ regularizations , 2019, Optics & Laser Technology.

[12]  Han Zhang,et al.  Convolutional Sparse Learning for Blind Deconvolution and Application on Impulsive Feature Detection , 2018, IEEE Transactions on Instrumentation and Measurement.

[13]  Sannyuya Liu,et al.  RISIR: Rapid Infrared Spectral Imaging Restoration Model for Industrial Material Detection in Intelligent Video Systems , 2019, IEEE Transactions on Industrial Informatics.

[14]  Pavel Matějka,et al.  Noise reduction in Raman spectra: Finite impulse response filtration versus Savitzky–Golay smoothing , 2007 .

[15]  Sannyuya Liu,et al.  Data-driven Online Learning Engagement Detection via Facial Expression and Mouse Behavior Recognition Technology , 2019, Journal of Educational Computing Research.

[16]  Hao Zhang,et al.  FBRDLR: Fast blind reconstruction approach with dictionary learning regularization for infrared microscopy spectra , 2018 .

[17]  Y Ichioka,et al.  Image restoration by Wiener filtering in the presence of signal-dependent noise. , 1977, Applied optics.

[18]  Josep M. Guerrero,et al.  Industrial Applications of the Kalman Filter: A Review , 2013, IEEE Transactions on Industrial Electronics.

[19]  Sanya Liu,et al.  Blind Poissonian reconstruction algorithm via curvelet regularization for an FTIR spectrometer. , 2018, Optics express.

[20]  Esther Baumann,et al.  High-coherence mid-infrared dual-comb spectroscopy spanning 2.6 to 5.2 μm , 2017, 1709.07105.

[21]  Yan Li,et al.  High spectral specificity of local chemical components characterization with multichannel shift-excitation Raman spectroscopy , 2015, Scientific Reports.

[22]  Yasushi Yagi,et al.  Material Classification from Time-of-Flight Distortions , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Limin Shao,et al.  Self-Weighted Correlation Coefficients and Their Application to Measure Spectral Similarity , 2009, Applied spectroscopy.

[24]  Xiaoyu Cui,et al.  Stepwise method based on Wiener estimation for spectral reconstruction in spectroscopic Raman imaging. , 2017, Optics express.

[25]  Sannyuya Liu,et al.  Efficient Blind Signal Reconstruction With Wavelet Transforms Regularization for Educational Robot Infrared Vision Sensing , 2019, IEEE/ASME Transactions on Mechatronics.

[26]  Tingting Liu,et al.  FTIR spectral imaging enhancement for teacher’s facial expressions recognition in the intelligent learning environment , 2018, Infrared Physics & Technology.

[27]  Seok-Beom Roh,et al.  Identification of Black Plastics Based on Fuzzy RBF Neural Networks: Focused on Data Preprocessing Techniques Through Fourier Transform Infrared Radiation , 2018, IEEE Transactions on Industrial Informatics.

[28]  Hongbin Pu,et al.  Emerging Spectroscopic and Spectral Imaging Techniques for the Rapid Detection of Microorganisms: An Overview. , 2018, Comprehensive reviews in food science and food safety.

[29]  Qiuxia Liu,et al.  Depth IR spectroscopic data resolution improvement for antibiotics component analysis in critically ill elderly patients , 2018, Infrared Physics & Technology.

[30]  Roman Z. Morawski,et al.  Kalman-filter-based algorithms of spectrophotometric data correction III. Use of splines for approximation of spectra , 1997 .