Target tracking method and apparatus based on human-machine interaction, and storage medium

Abstract

The disclosure provides a target tracking method and apparatus based on human-machine interaction, and a storage medium. According to the method, a to-be-tracked target can be determined through a triggering instruction generated based on a target selection operation of a user without operation learning of multiple continuous frames of images, the acquisition operation of the target is reduced, and the target acquisition efficiency and the tracking efficiency can be improved; the dimension and the scale of a target image in a next frame can be detected based on extracted image characteristicsso that the tracking effect of a rigid target, a target with scale transformation, a target with high-speed motion, and a target which is shielded for a long time can be optimized to a certain extent,and the precision of target tracking is improved; and the effect of the operation efficiency and the target tracking can be guaranteed on general portable devices.

Description

Technical field [0001] The present disclosure relates to the field of tracking technology, and in particular to a target tracking method, device and storage medium based on human-computer interaction that can be applied to portable devices. Background technique [0002] Tracking technology has always been one of the hot spots in the field of computer vision, and it has broad application prospects in many aspects such as military frame observation, precision guidance, fire strike, battlefield evaluation, and security monitoring. [0003] At this stage, there are two ways to track moving target objects. The first is to use KCF (Kernal Correlation Filter) and then superimpose HOG (Histogram of OrientedGradient) features to achieve the Tracking of moving target objects; the second is to use KCF to superimpose depth features to realize the detection of moving target objects. When the first scheme is adopted, when the target object is in a relatively complex scene, it is impossible to a...

AI Technical Summary

Problems solved by technology

When the first solution is adopted, when the target object is in a relatively complex scene, it is impossible to accurately locate and detect the target object, especially the ability to distinguish the foreground and background of the scene is not strong

Although the second solution can solve the problem of the first solution, its computational complexity is high, and it cannot run faster on portable devices with average computing power.

Images