Pedestrian tracking method based on twin neural network

Abstract

The invention belongs to the field of computer vision, and particularly relates to a pedestrian tracking method based on a twin neural network, which comprises the following steps: inputting a video;performing pedestrian marking; acquiring a pedestrian space-time group; establishing and training a twin neural network, and storing the trained twin neural network; obtaining a pedestrian short track; and obtaining pedestrian long trajectories. By adopting the pedestrian tracking method to track pedestrians, the accuracy of pedestrian tracking is effectively improved.

Description

technical field [0001] The invention belongs to the field of computer vision, in particular to a pedestrian tracking method based on twin neural networks. Background technique [0002] With the development of artificial intelligence technology, computer vision has been widely used in human daily life such as smart home, video surveillance and intelligent transportation, and pedestrian tracking is one of the key issues in these fields. Due to the pose changes, size changes, appearance changes and pedestrian occlusions of pedestrian targets during motion, it is very difficult to achieve accurate tracking of pedestrians. [0003] Early target tracking algorithms were mainly based on target modeling or tracking target features. The main methods are: (1) Feature matching method, first extracting target features, and then finding the most similar features in subsequent frames for target positioning; (2) Based on the search method, people add the prediction algorithm to the tracki...

AI Technical Summary

Problems solved by technology

Due to the posture changes, size changes, appearance changes and pedestrian occlusions of pedestrian targets during motion, it is very difficult to achieve accurate tracking of pedestrians.

[0003] Early target tracking algorithms were mainly based on target modeling or tracking target features. The main methods are: (1) Feature matching method, first extracting target features, and then finding the most similar features in subsequent frames for target positioning; (2) Based on the search method, people add the prediction algorithm to the tracking, and search for the target near the predicted value, which reduces the scope of the search. However, these methods no longer meet the needs of today's pedestrian tracking, and some new methods are urgently needed to replace them. ; and the traditional method is greatly affected by factors such as image illumination changes, pedestrian posture changes, image noise, etc.

Images