Detection of salient objects in image and video is of great importance in many computer vision applications. In spite of the fact that the state of the art in saliency detection for still images has been changed substantially over the last few years, there have been few improvements in video saliency detection. This paper investigates the use of recently introduced non-local neural networks in video salient object detection. Non-local neural networks are applied to capture global dependencies and hence determine the salient objects. The effect of non-local operations is studied separately on static and dynamic saliency detection in order to exploit both appearance and motion features. A novel deep non-local neural network architecture is introduced for video salient object detection and tested on two well-known datasets DAVIS and FBMS. The experimental results show that the proposed algorithm outperforms state-of-the-art video saliency detection methods.

Natural light always plays important role in designing of residential apartments in terms of energy saving and health of lifestyle. To find a practical approach for saving electricity energy in lightening of dark places has always been a challenging topic in recent years. Most existing studies on the interior lightening by using sunlight in architectural concepts have focused on position of windows and patio in plans. This paper describes a new application of optical fibers for transferring sunlight into the rooms by conducting an experimental test. The experimental tests indicated that a group of optical fibers can successfully conduct the natural light from the roof of an apartment in to dark spots through walls. Also, from the outcomes it is concluded that the daytime running electricity lamps can decrease in compare with traditional methods.