Multi-task image detection method and system

The embodiment of the invention provides a multi-task image detection method. The method comprises the following steps: acquiring a to-be-detected image; extracting features of the to-be-detected image through a first feature extraction layer based on machine learning; and through at least two task processing layers based on machine learning, based on the features, determining processing results of at least two tasks related to the to-be-detected image. 本说明书实施例提供一种多任务的图像检测方法，该方法包括获取待检测图像；通过基于机器学习的一个第一特征提取层，提取待检测图像的特征；以及通过基于机器学习的至少两个任务处理层，基于该特征，确定与待检测图像相关的至少两个任务的处理结果。