Method and device for detecting foreign matter invasion

Abstract

The invention discloses a method for detecting foreign matter invasion. The method comprises the following steps: receiving a current frame of visible light image sent by acquisition equipment; determining a bounding box corresponding to a foreign matter in the current frame of visible light image through a pre-trained recognition model, and receiving an infrared video sent by the collection device; determining a bounding box of the foreign matter in the current frame of infrared image according to the coordinates of the bounding box of the foreign matter determined in the current frame of visible light image; and tracking the foreign matter in the infrared video according to the boundary frame of the foreign matter in the current frame of infrared image and a pre-constructed filter. Visible light detection and infrared detection are combined, and deviation of visible light images and infrared images can be corrected under the condition of multiple factors. When target tracking is carried out, the characteristic data of the visible light image is not used, and the infrared image is adopted, so that the influence of illumination change is reduced, and the robustness is improved.

Description

technical field [0001] The present application relates to the field of computers, in particular to a method and device for detecting foreign object intrusion. Background technique [0002] At present, more and more companies and enterprises are paying more and more attention to on-site safety issues. With the widespread popularization of cameras and other equipment, foreign object intrusion detection systems have emerged as needed. The system can detect the entry of foreign objects with potential safety hazards in the monitoring area in a timely manner, and immediately assign professionals to clean them up, so as to minimize losses such as circuit short-circuit equipment failures caused by foreign objects hanging. [0003] In the prior art, the foreign object intrusion detection system processes the visible light image. When the illumination condition of visible light changes drastically, the target characteristics change greatly, and the target tracking based on the visibl...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, the foreign object intrusion detection system processes the visible light image. When the visible light changes drastically in the lighting conditions, the characteristics of the target change greatly, and the target tracking based on the visible light image may fail.

At the same time, when tracking the target, it needs to be tracked in the visible light image, which consumes a lot of hardware resources and requires high hardware performance.

Images