Search

The detection ability of laser fuze is easily disturbed by smoke, which causes false alarm. In order to study on the backscattering characteristics of pulsed laser fuze in smoke, the relevant model based on Mie scattering theory and Monte Carlo method was established, and the backscattering signal in smoke was simulated using 905 nm pulsed laser. To verify the accuracy of the model, the actual peak voltage was compared with the simulated normalized intensity and correlation analysis was conducted. Then, the backscattering characteristics of the pulsed laser fuze under different smoke concentrations, length of pipes and distances were analyzed. Finally, the influence of different smoke environment was obtained. The results can provide support for the anti-smoke interference of the pulsed laser fuze.

Based on the idea of machine learning and the sufficient appearance, a mixture random Naive Bayes visual tracker with online texture and shape feature selection is proposed. The texture and shape of global and local region is described with binary feature of intensity and pyramid histogram of oriented gradients using normalized spatial pyramid. An online mixture of Naive Bayes classifier is designed and realized according to binary and multimodel description. The classifier predicts the class posterior probability to generate the confidence map, then the tracker analyzes the confidence map to track the object, learns the appearance with maximum likelihood estimation, and selects the feature with cross validation. Compared with homogeneous methods, the tracker is evaluated with performance and complexity based on benchmarks. The experimental results show that the tracker has certain adaption to illumination change and partial occlusion, and fast execution speed as well as little memory space. ©, 2015, Chinese Optical Society. All right reserved.