Aiming at the problems of large number of model parameters, large computational cost and low accuracy when using deep learning algorithms for pointer instrument recognition task, an intelligent detection and recognition system of circular pointer instrument based on the combination of improved pre-trained MobileNetV2 network model and circular Hough transform was proposed. Firstly, the Hough transform was used to solve the interference problem of non-circular areas in complex scene. Then, the circular areas were extracted to construct datasets. Finally, the circular pointer instrument recognition was realized by using the improved pre-trained MobileNetV2 network model. The average confusion matrix was used to measure the performance of the proposed model. Experimental results show that, the recognition rate of the proposed system in the recognition task of circular pointer instruments reaches 99.76%. At the same time, the results of comparing the proposed model with other five different network models show that the proposed model and ResNet50 both have the highest accuracy, but compared with ResNet50, the proposed network model has the model parameter number and model computational cost reduced by 90.51% and 92.40% respectively, verifying that the proposed model is helpful for the further deployment and implementation of industrial grade real-time circular pointer instrument detection and recognition in mobile terminals or embedded devices.

The purpose of image defogging is to remove the fog effect from image of surveillance video to improve the fog haze image visual effect. Presently, there is only a comparison between images before and after defogging, and the results are often distorted seriously and oversatuarted. Thereby, it is hard to ensure the clear details and the integrity of color information simultaneously. For tackling above problems, a new optimized method for images recovering was proposed with combination of HIS luminance component and RGB space, which was based on atmosphere scattering model and optical principals. In this method the relative depth relationship of image scene was analyzed by comparing images in fine and haze days with help of the most eye-sensitive HSI luminance component. Finally, by utilizing atmosphere scattering model and the comparison of depth of field, the recovering and result evaluation were conducted on the video obtained in haze. The experimental results show that, compared with the defogging methods calculated in RGB space, the proposed method has more clear defogging results and smaller degree of color distortion and oversaturation.