Search

The traditional dual differential luminance algorithm was influenced by the surrounding environment, and was not applicable to accurate detection at night. In view of the interference factors of reality, this paper improved the dual differential luminance algorithm by using the method of amending coefficient. Meanwhile, combined with the traffic emergency control measures under different visibility, ten detection modes were subdivided. The next, an experimental system was built in the Meteorological Observatory of Beijing, and the detection software was developed. At last, the experimental data was compared with the correlation values of scatterometer. The results show that the detection accuracies are raised, and the optimized algorithm and system can be used for highway network visibility detection.

People's travel and traffic safety are affected by low visibility. With the development of transportation in recent years, the detection of license plate area under low visibility has become one of the hot topics of research. This article studies the license plate detection under low visibility based on video images. The research content is divided into two parts: defogging and license plate inspection. First of all, the collected image is processed in grayscale, the related defogging coefficient is set, and the dark channel algorithm is used to remove the fog component in the image, which greatly improves the clarity of the image. Second, using the top hat calculation related theory, combined with the image edge extraction, opening and closing operation steps to detect the license plate area. Finally with the help of MATLAB software for test verification, the results show that the algorithm has a good detection effect.

This paper presents a new recognition algorithm for plant pathology images based on the Non-negative Matrix Factorization, the proposed algorithm is combined with optimal wavelet packet basis to recognize patterns and conduct data encoding in the internet of things oriented intelligent agricultural system. The experimental results show that the performance of the proposed recognition algorithm is far better than those of the principal component analysis and linear discriminant analysis, and the recognition rate are improved, on average, about 14.65% and 11.18% higher than the rates of the above algorithms respectively. The presented algorithm is characterized by the fast speed, high calculation accuracy and easy hardware implementation.