The hyperspectral imaging system (HIS) using a Fourier transform infrared (FTIR) spectrometer is one of the key technologies for detection and identification of chemical warfare agents (CWAs). Recently, various detection algorithms based on machine learning techniques have been studied. These algorithms are robust against performance degradation caused by noise signatures generated by FTIR instruments. However, interference signatures from background materials degrade detection performance. In this paper, we propose an efficient algorithm that uses a support vector machine (SVM) classifier to detect CWAs. In contrast to the conventional algorithms that use measured spectra to train the SVM classifier, the proposed algorithm trains the SVM classifier using CWA signatures obtained by removing background signatures from measured spectra. Therefore, the proposed algorithm is robust against the performance degradation induced by interference signatures from background materials. Experimental results verify that the algorithm can detect CWA clouds effectively.
A compact stand-off chemical detector using a Michelson interferometer has been developed and is presented. Its size is only 104 × 183 × 108 mm3 and its weight is 2.5 kg, which makes it suitable for hand-held operation. This compact detector is a minimized version of the conventional Michelson interferometer. The housing for the interferometer was designed to be divided into two parts for minimization and convenient assembly. All the optics composing the interferometer were directly fastened to the housing. The moving mirror module in the Michelson interferometer was specially designed for the small size detector. Using a symmetrically positioned linear elastic plate, the tip and tilt angle of reflected light from the moving mirror were smaller than 8 arc sec during linear back-and-fourth motion without any active alignment feedback system, which results in low noise in the interference signal. The spectra of SF6 and NH3 were measured with changing concentration and the detection limit was determined to be 46.7 and 65.2 mg / m2, respectively. Additionally, outdoor measurement was demonstrated with a distance of about 1 km.
A passive Fourier transform infrared (FTIR) spectrometer is an instrument that can detect and identify chemical contaminants. An FTIR spectrometer exploits the infrared radiation of the surrounding terrain as a light source and receives a mixed signal of background signal, gas signal, and noise. The performance of most detection algorithms for detecting gaseous plumes, such as the normalized matched filter (NMF) and adaptive subspace detector (ASD), deteriorates due to the noise generated by an FTIR spectrometer. In this paper, a noise reduction algorithm based on the maximum noise fraction (MNF) transform to improve the performance of hazardous gas detection algorithms is proposed. We apply the MNF transform to the measured spectra and remove the high noise fraction component. Then the noise-reduced spectra are restored by conducting the inverse MNF transform. The experimental results show that the proposed algorithm reduces the noise and enhances the gas detection performance.
Recently, a hyperspectral imaging system (HIS) with a Fourier Transform InfraRed (FTIR) spectrometer has been widely used due to its strengths in detecting gaseous fumes. Even though numerous algorithms for detecting gaseous fumes have already been studied, it is still difficult to detect target gases properly because of atmospheric interference substances and unclear characteristics of low concentration gases. In this paper, we propose detection algorithms for classifying hazardous gases using a deep neural network (DNN) and a convolutional neural network (CNN). In both the DNN and CNN, spectral signal preprocessing, e.g., offset, noise, and baseline removal, are carried out. In the DNN algorithm, the preprocessed spectral signals are used as feature maps of the DNN with five layers, and it is trained by a stochastic gradient descent (SGD) algorithm (50 batch size) and dropout regularization (0.7 ratio). In the CNN algorithm, preprocessed spectral signals are trained with 1 × 3 convolution layers and 1 × 2 max-pooling layers. As a result, the proposed algorithms improve the classification accuracy rate by 1.5% over the existing support vector machine (SVM) algorithm for detecting and classifying hazardous gases.