Building fire environment detection method based on image data

The invention relates to the technical field of building fire detection, in particular to a building fire environment detection method based on image data. The method comprises the following steps: acquiring a target video image of a building environment, and preprocessing the image; obtaining the importance degree of pixel points in the image; obtaining a self-adaptive filtering window according to the importance degree of the pixel points; according to the adaptive filtering window, completing the enhancement of the image quality; and obtaining a fire detection result of the building environment based on the enhanced image. According to the embodiment of the invention, the quality of the collected image can be improved, and the precision and efficiency of building environment fire detection are improved. 本申请涉及楼宇火灾检测技术领域，具体涉及基于图像数据的楼宇火灾环境检测方法。所述方法包括：获取楼宇环境的目标视频图像，对图像进行预处理；获取图像内像素点的重要程度；根据像素点的重要程度，获取自适应滤波窗口；根据自适应滤波窗口，完成对图像质量的增强；基于增强的图像，获得楼宇环境的火灾检测结果。本申请实施例能够能够对采集的图像进行质量提高，进而提高楼宇环境火灾检测的精度和效率。