Infrared image vehicle detection method

The invention relates to an infrared image vehicle detection method, and belongs to the technical field of image processing. According to the method, a single-frame image is acquired from an infrared monitoring video stream and input into a deep learning network model for vehicle detection; meanwhile, a sequence frame image is obtained in the infrared real-time monitoring video stream, and movement detection is carried out; and if a target is detected, inputting the target into a deep learning network model for vehicle detection. According to the method, two modes of static target detection and moving target detection are combined, and a single-frame image detection method and a sequence frame image detection method are adopted, so that vehicle target detection under an infrared imaging condition is realized, and the infrared image vehicle detection accuracy is improved. 本发明涉及一种红外图像车辆检测方法，属于图像处理技术领域。本发明在红外监控视频流中获取单帧图像，输入到深度学习网络模型进行车辆检测；同时在红外实时监控视频流中获取序列帧图像，进行移动侦测检测；如果检测到目标，则输入到深度学习网络模型进行车辆检测。本发明结合静目标检测和动目标检测两