Method for detecting and smoothly following moving object based on video images

Abstract

The invention provides a method for detecting and smoothly following a moving object based on video images. The method includes the steps of preprocessing an image sequence to obtain a foreground image, screening out all moving objects through a contour identifying method, rapidly calculating the horizontal positions of the moving objects by dimension reduction, smoothing the motion state of the objects through a boundary layer strategy, and generating an angular velocity curve of model robot following motion. The algorithm is simple and easily realizable, and moving objects can be rapidly identified. The method has low requirements on hardware configuration environment, and can be widely used in visual sense system of a model robot. The jittering phenomenon can be prevented while realizing a model robot smoothly following the movement of a moving object.

Description

technical field [0001] The invention relates to the technical field of video image processing, in particular to a method for detecting and smoothly following a moving target based on video images. Background technique [0002] Traditional window models can only statically display clothes, and using model robots for fashion displays can attract customers to stop by interacting with customers, thereby greatly increasing passenger flow. The invention provides a method for detecting and smoothly following a moving target based on a video image, which is applied to the vision system of a model robot to realize its recognition and smooth following of a moving target. When a pedestrian appears or passes in front of the model, the model Robots can perform turn-following or other forms of interaction. [0003] The more common video-based target tracking method is to detect and track the determined target through feature extraction and target tracking. However, the pedestrians faced ...

AI Technical Summary

Problems solved by technology

[0003] The more common video-based target tracking method is to detect and track the determined target through feature extraction and target tracking. However, the pedestrians facing the models in the shop window are constantly changing, and the determined target cannot be preset in advance.

The more common methods such as neural network, deep learning and SVM based on machine learning train the classifier through a large number of pedestrian or face samples, and then detect the video image, but have higher requirements for the computing speed of the hardware environment

Images