Object theft detection method and device based on behavior recognition algorithm

The invention provides an object theft detection method and device based on a behavior recognition algorithm, and the method comprises the steps: carrying out the sparse coding of an object placement region in a current frame image of a to-be-detected video, and comparing a sparse code corresponding to the current frame image with a sparse code of a reference image of the object placement region; and under the condition that the distance between the sparse code corresponding to the current frame image and the sparse code corresponding to the reference image is greater than a first preset threshold value, detecting whether an object theft behavior exists based on a behavior recognition algorithm according to a video segment containing the current frame image in the to-be-detected video. The use frequency of a behavior recognition algorithm is reduced, the resource consumption is reduced, the detection efficiency is improved, and the detection delay is reduced. 本发明提供一种基于行为识别算法的物体被盗检测方法及装置，该方法包括：对待检测视频的当前帧图像中的物体