The invention belongs to the technical field of image processing, and particularly relates to a target detection method based on a video image recognition technology, which comprises the following steps: video input, target monitoring, target tracking and target output. A monitoring area focused on is separated from a picture background through background modeling in area monitoring, background factor interference is reduced, invalid targets are further effectively filtered through a target area suppression method, meanwhile, effective targets are continuously and accurately positioned througha target tracking method, and false alarm targets are eliminated. Compared with the prior art, the technical scheme provided by the invention has the advantages that the background and the target inthe scene are separated by analyzing the video image of the surveillance camera without the technical support of other hardware equipment, so that the effective target appearing in the camera scene isanalyzed and tracked; the invention has the capability of filtering various backgrounds such as wind, rain, snow, fallen leaves, birds and fluttering flags, so that the practicability of the video image recognition technology is effectively improved.