【摘要】 提出一种轻量高效的视频火焰检测算法。该算法以基于深度学习的卷积神经网络目标检测算法为主体,提取监控视频中的图像帧,识别并定位火焰区域。加入运动目标检测模块作为后处理机制,依据连续视频帧中火焰的运动特性,采用基于混合高斯模型的运动目标检测算法对火焰目标检测结果进行合理化判断,减少类似火焰的静止物体或光线造成的误报,效率高且资源消耗少。此外,收集并标注了一套火焰检测数据集(Fire detection dataset,FDD),包含多种场景下多类型燃烧物产生的火焰图片2 487张以及15段不同场景下的火灾视频数据。在FDD的视频检测实验中本文算法准确率达到了98.94%,证明了本文算法的有效性。更多还原

【Abstract】 This paper proposes a lightweight and efficient flame detection algorithm of videos. The flame detection algorithm is based on the convolutional neural network of deep learning. Considering the motion characteristics of the flame in the continuous video frame,this paper evaluates the flame detection results by the motion object detection and removes the false positive results caused by stationary objects or lights.The motion object detection algorithm based on the Gaussian mixture model is highly efficient. In addition,we collect and label a set of fire detection dataset(FDD),including 2 487 flame images and 15 fire videos under various scenarios with different flammable materials. In conclusion,the proposed algorithm obtains98.94% accuracy on FDD test videos.更多还原