To solve the mobile robot path planning in uncertain environments, a new path planning algorithm is presented on the basis of the biological immune network. The environment surrounding the robot is taken as the antigen, and the behavior strategy of robot is taken as the antibody. The selection model of antibody concentration is defined based on the Jernes idiotypic immune network hypothesis, and the mobile robot path planning is realized through the selection of the antibody concentration. The simulation of path planning for mobile robot in multi-obstacle environments shows that the robot can find a safe path in complicated environments, which verifies the better adaptivity of proposed planning model. The simulation in dynamic environments shows that the robot can safely avoid all dynamic obstacles, which verifies the better flexility of new algorithm.

Detection of moving object is a hot topic in computer vision. Traditionally, it is detected for every pixel in whole image by Gaussian mixture background model, which may waste more time and space. In order to improving the computational efficiency, an advanced Gaussian mixture model based on Region of Interest was proposed. Firstly, the solution finds out the most probably region where the target may turn up. And then Gaussian mixture background model is built in this area. Finally, morphological filter algorithm is used for improving integrity of the detected targets. Results show that the improved method could have a more perfect detection but no more time increasing than typical method.