Fast Defocus Blur Detection Network via Global Search and Local Refinements

Defocus blur detection aims at separating regions on focus from out-of-focus for image processing. With today’s popularity of mobile phones with portrait mode, accurate defocus blur detection has received more and more attention. There are many challenges that we currently confront, such as blur boundaries of defocus regions, interference of messy backgrounds and identification of large flat regions. To address these issues, in this paper, we propose a new deep neural network with both global and local pathways for defocus blur detection. In global pathway, we locate the objects on focus by semantical search. In local pathway, we refine the predicted blur regions via multi-scale supervisions. In addition, the refined results in local pathway are fused with searching results in global pathway by a simple concatenation operation. The structure of our new network is developed in a feasible way and its function appears to be quite effective and efficient, which is suitable for the deployment on mobile devices. It takes about 0.2[Formula: see text]s per image on a regular personal laptop. Experiments on both CUHK dataset and our newly proposed Defocus400 dataset show that our model outperforms existing state-of-the-art methods.

Indoor Constant Illumination Control Strategy Research Based on Natural Lighting Analysis

Lighting energy consumption occupies a large proportion in the building electricity consumption. It cannot only save energy, but also reduce the uneven and constant illumination of the working face, which makes full use of the natural lighting and combines with the intelligent lighting control. An office building in Zhengzhou of China has been selected as an example for analyzing the climatic factors that influence building daylighting and the factors of the building itself, the illuminance of working faces in different sky models and at different times has been simulated and calculated to analyze the illuminance variation law in the direction of room depth and parallel direction of side Windows. Partition and point combined constant illumination control strategy for the lamps in different areas has been put forward and realized by BP neural network algorithm. By controlling the dimming of artificial light source and adjusting the curtain opening degree intelligently, uniform and constant illumination has been achieved. Energy saving effect in combination with natural lighting has been evaluated to prove that the control strategy cannot only maintain constant illumination in every working face but also significantly reduce the electric energy consumption and carbon dioxide emissions.