TARGET OBJECT POSITION DETECTION METHOD AND APPARATUS BASED ON VIDEO STREAM, AND DEVICE AND MEDIUM

摘要

The present application relates to artificial intelligence technology. Disclosed is a target object position detection method based on a video stream. The method comprises: acquiring a video stream, and performing image framing on the video stream to obtain a framed image set; detecting a target region of the framed image set using a target region detection model so as to obtain a target image set; recognizing a target object position sequence of the target image set using a target object position sequence recognition model, and according to the target object position sequence, deleting a target image, corresponding to an abnormal target object position sequence, from the target image set so as to obtain a standard target image set; and performing image association on all target images in the standard target image set, and recognizing a target object position according to the standard target image set subjected to the image association. In addition, the present application further relates to blockchain technology, and the video stream can be stored in a blockchain. The present application can be applied to the detection of the position of a thyroid nodule. By means of the present application, the accuracy of carrying out target object position detection on the basis of a video stream can be improved.