Abstract. Maneuvering target tracking technology is widely used in both military and civilian fields. Kalman filtering technique is the key technology for maneuvering target tracking. However, due to the uncertainty of the environment and the diversity of the sensors, the defects of traditional Kalman filter are revealed. To solve these problems, a variety of new Kalman filters have been proposed. In this paper, we sum up the application of different Kalman filters for target tracking in various environments, including the adaptive Kalman filter, the extended Kalman filter(EKF), and the unscented Kalman filter(UKF), and analyze the key problems including the improvement of accuracy, real time performance and robustness.

No abstract

No abstract

Abstract. This paper mainly focuses on the content-based image search system. First introduces the research status of CBIR in China and abroad, and then proposes and illustrates two key problems affecting the accuracy of the system, summarizes commonly used methods to solve these two problems.

Infrared weak small target detection is one of the key technologies in the infrared early warning system, infrared imaging guidance system and wide-field view surveillance system etc. In the complex and low signal-to-noise ratio background environment, the target has only a few pixels. There is no shape and texture information to use. All of the above issues bring great difficulties to infrared dim-small target detection. In this paper, in order to deal with the shortcoming of large pixel tracking in moving target detection algorithm based on time domain filtering, apply the dim target detection based on Laplace operator to the subject of this paper, the false alarm points obviously to be less, and the target point is usually in the form of a single pixel, lay a good foundation for reducing the complexity of the algorithm.