The existing thermal infrared (TIR) ship detection methods may suffer serious performance degradation in the situation of heavy sea clutter. To cope with this problem, a novel ship detection method based on morphological reconstruction and multi-feature analysis is proposed in this paper. Firstly, the TIR image is processed by opening- or closing-based gray-level morphological reconstruction (GMR) to smooth intricate background clutter while maintaining the intensity, shape, and contour features of ship target. Then, considering the intensity and contrast features, the fused saliency detection strategy including intensity foreground saliency map (IFSM) and brightness contrast saliency map (BCSM) is presented to highlight potential ship targets and suppress sea clutter. After that, an effective contour descriptor namely average eigenvalue measure of structure tensor (STAEM) is designed to characterize candidate ship targets, and the statistical shape knowledge is introduced to identify true ship targets from residual non-ship targets. Finally, the dual method is adopted to simultaneously detect both bright and dark ship targets in TIR image. Extensive experiments show that the proposed method outperforms the compared state-of-the-art methods, especially for infrared images with intricate sea clutter. Moreover, the proposed method can work stably for ship target with unknown brightness, variable quantities, sizes, and shapes.
An important component of any chemiresistive gas sensor is the way in which the resistance of the sensing film is interrogated. The geometrical structure of an electrode can enhance the performance of a gas-sensing device and in particular the performance of sensing films with large surface areas, such as carbon nanotubes. In this study, we investigated the influence of geometrical structure on the performance of gas sensors, combining the characteristics of carbon nanotubes with a novel gas sensor electrode structure based on fractal geometry. The fabricated sensors were tested with exposure to nitric oxide, measuring both the sensor resistance and capacitance (RC) of the sensor responses. Experimental results showed that the sensors with fractal electrode structures had a superior performance over sensors with traditional geometrical structures. Moreover, the RC characteristics of these fractal sensors could be further improved by using different test frequencies that could aid in the identification and quantification of a target gas.
1 April 2019 in Journal of Physics: Conference Series
Dangerous rock collapse may cause traffic accidents and other potential traffic safety hazards in mountainous areas. In this paper, aiming at the problem that dangerous rock collapse disaster is difficult to monitor and judge, a method of measuring the cross section area of collapse rock is proposed based on parallel binocular vision, which is convenient for the relevant departments to deal with the emergency ahead of time. This paper first calibrates the binocular camera on the MATLAB platform, and then corrects and matches the collected images on the OpenCV platform. The feasibility of measuring area by pixel method and spatial coordinate method is verified by using regular triangular and rectangular shapes. Then the pixel method is applied to the measurement of cross sectional area of rock collapse, which provides a method for predicting the disaster grade of collapse of dangerous rock.