A method and device for determining a to-be-identified object

Abstract

The embodiment of the invention provides a method and device for determining a to-be-identified object, and relates to the technical field of video processing, the method comprises the steps: obtaining a to-be-processed video from monitoring equipment of a public security platform, the to-be-processed video comprising N frames of images; wherein N is greater than or equal to 2; The monitoring equipment is arranged in a vehicle passing area; inputting the first image into a classification model to obtain each identification object in the first image; wherein the recognition object comprises thetype of the recognition object and image information corresponding to the recognition object; wherein the types of the identified objects comprise pedestrians, non-motor vehicles and motor vehicles;wherein the first image is any one of the N frames of images; and extracting image information corresponding to each identification object from the to-be-processed video, and marking the type of the identification object corresponding to each image information. And attribute detection is carried out by using the extracted information of the features of the to-be-identified object, so that the calculation amount is reduced, and the efficiency is improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of video processing, and in particular to a method and device for determining an object to be recognized. Background technique [0002] In today's society, due to the needs of security management, monitoring equipment is full of streets, communities, buildings and other public places. When a police situation occurs, first determine the image of the suspect or the suspect vehicle from the video data collected by the monitoring equipment, and then the police officers search for the suspect or the suspect vehicle based on the image of the suspect or the suspect vehicle. [0003] In the prior art, after the monitoring equipment collects the video stream, it usually detects and recognizes each frame of image in the video stream, determines the face or vehicle and other objects in each frame of image, and then detects the detected objects in each frame of image Objects are matched to determi...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, after the monitoring equipment collects the video stream, it usually detects and recognizes each frame of image in the video stream, determines the face or vehicle and other objects in each frame of image, and then detects the detected objects in each frame of image Objects are matched to determine all images of an object. Since this method needs to detect and identify each frame of image, the amount of calculation is large and the efficiency is low.

Images