In this work, we propose a novel Deep Convolutional Neural Network (DCNN) tailored for gas classification. Inspired by the great success of DCNN in the field of computer vision, we designed a DCNN with up to 38 layers. In general, the proposed gas neural network, named GasNet, consists of: six convolutional blocks, each block consist of six layers; a pooling layer; and a fully-connected layer. Together, these various layers make up a powerful deep model for gas classification. Experimental results show that the proposed DCNN method is an effective technique for classifying electronic nose data. We also demonstrate that the DCNN method can provide higher classification accuracy than comparable Support Vector Machine (SVM) methods and Multiple Layer Perceptron (MLP).

In this paper, we present a novel one-dimensional deep convolutional neural network (1D-DCNN) with a multilabel way based algorithm for comprehensively and automatically extracting features and classifying mixture gases. Although a number of pattern recognition methods have been used to analyze the mixed gases, the performances of these methods highly depend on the hand-crafted feature engineering. By contrast, the proposed implementation, based on one-dimensional convolution, is capable of automatically extracting features and distinguishing the individual component of binary mixture gases composed of Ethylene, CO and Methane. To the best of our knowledge, the proposed 1D-DCNN algorithm is firstly applied in the mixture gases recognition. In addition, the proposed 1D-DCNN with multilabel way not only significantly reduces the label dimension but also quantifies the probability of each component in mixed gases. Compared with the conventional pattern recognition algorithms including support vector machine (SVM), artificial neural network (ANN), k-nearest neighbor (KNN) and random forest (RF), the proposed 1D-DCNN exhibits higher recognition accuracy (96.30%) based on our extensive experimental results using 10- fold cross validation.

Division of focal plane (DoFP) polarization image sensors capture polarization properties of light at every imaging frame. However, these imaging sensors capture only partial polarization information, resulting in reduced spatial resolution output and a varying instantaneous field of overview (IFoV). Interpolation methods are used to reduce the drawbacks and recover the missing polarization information. In this paper, we propose residual interpolation as an alternative to normal interpolation for division of focal plane polarization image sensors, where the residual is the difference between an observed and a tentatively estimated pixel value. Our results validate that our proposed algorithm using residual interpolation can give state-of-the-art performance over several previously published interpolation methods, namely bilinear, bicubic, spline and gradient-based interpolation. Visual image evaluation as well as mean square error analysis is applied to test images. For an outdoor polarized image of a car, residual interpolation has less mean square error and better visual evaluation results.

Division of focal plane (DoFP) polarimeter is widely used in polarization imaging sensors. The periodically arranged micro-polarizers integrated on the focal plane ensure its outstanding real-time performance, but reduce the spatial resolution of output images and further affect the calculation of polarization parameters. In this paper, a four-layer, end-to-end fully convolutional neural network called Fork-Net is proposed, which aims to directly improve the imaging quality of three polarization properties: intensity (i.e., S₀), degree of linear polarization (DoLP), and angle of polarization (AoP), rather than focusing on reducing the interpolation error of intensity images of different polarization orientations. The Fork-Net accepts raw mosaic images as input and directly outputs S₀, DoLP, and AoP. It is also trained with a customized loss function. The experimental results show that compared with existing methods, the proposed one achieves the highest peak signal-to-noise ratio (PSNR) and prominent visual quality on output images.

This paper presents a fast and effective polarization image demosaicking algorithm, which explores inter-channel dependency of Stokes parameters for the minimization of residual aliasing artifacts after cubic spline interpolation. A guided filtering approach is used for denoising. An optimization based on the confidence level of the aforementioned guided filtering, the correlations between the demosaicked image and input, as well as the total intensity, angle and degree of linear polarization, is constructed and solved with Newton’s method. Experimental results demonstrate that the proposed algorithm can surpass the existing methods in terms of both objective root mean squared error and structural similarity index by at least 36.0% and 3.4%, respectively, and by close visual inspection of the clarity of objects in the angle and degree of linear polarization images. The proposed algorithm consists of only convolutions and elementwise operations, making it fast and parallelizable for efficient GPU acceleration. An image of size 512×612×4 can be processed within 10 s on i7-6700k CPU, and gains further 5 times speedup with M4000M GPU.

In this paper, we present a block-matching and 3-D filtering (BM3D) algorithm dedicated to the division-of-focal-plane (DoFP) polarization images. This algorithm based on a non-local collaborative filtering method is capable of exploiting all the different polarization channels simultaneously. Compared with the previously reported implementations for DoFP sensors, the proposed algorithm attenuates Gaussian noise in the transform domain by stacking similar 2-D image patches to form a 3-D block. According to our extensive experimental results, the proposed algorithm outperforms all the existing denoising algorithms for DoFP images including the state-of-the-art principle component analysis in terms of peak-signal-to-noise-ratio and structural similarity index. Moreover, the comparison is further extended to visual comparison, it is indicated that the image details are well-preserved by the proposed BM3D algorithm.