A power substation is susceptible to intrusions of foreign objects. The intrusions can likely result in failures of power supplies. Therefore, recognizing foreign objects becomes important to ensure constant and stable power supplies. However, existing object recognition methods fail to achieve acceptable accuracy and performance. In this paper, we propose an efficient Foreign Objects Detection Network for Power Substation (FODN4PS) to improve the recognition accuracy with less time. FODN4PS consists of a Moving Object Region Extraction Network (MORE Net) and a classification network, where the MORE Net can get the position of foreign objects, and the classification network can recognize the category of foreign objects. Experimental results show that FODN4PS is faster and more accurate in object recognition than the Fast R-CNN and Mask R-CNN.

变电站容易受到异物的侵入。入侵可能会导致电源故障。因此，识别异物对于确保稳定稳定的电源至关重要。但是，现有的对象识别方法无法实现可接受的准确性和性能。在本文中，我们提出了一种高效的变电站异物检测网络（FODN4PS），以在较短的时间内提高识别精度。FODN4PS由移动物体区域提取网络（MORE Net）和分类网络组成，其中MORE Net可以获取异物的位置，而分类网络可以识别异物的类别。实验结果表明，FODN4PS在对象识别方面比Fast R-CNN和Mask R-CNN更快，更准确。