Unlock instant, AI-driven research and patent intelligence for your innovation.

A pedestrian tracking method, device and equipment

A pedestrian tracking and pedestrian technology, applied in the computer field, can solve the problems of long calculation time, low pedestrian tracking efficiency, large amount of calculation, etc., and achieve the effect of improving efficiency

Active Publication Date: 2021-06-04
BEIJING QIYI CENTURY SCI & TECH CO LTD
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Due to the deep learning method, there are a large number of convolution and full connection operations in the neural network, and the convolution and full connection operations consume a lot of calculations, which makes the calculation time longer
As a result, the efficiency of pedestrian tracking through deep learning is low

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A pedestrian tracking method, device and equipment
  • A pedestrian tracking method, device and equipment
  • A pedestrian tracking method, device and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0064] The technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention.

[0065] Pedestrian tracking is the basis of various algorithms. A stable and efficient pedestrian tracking method can effectively improve the efficiency of algorithms such as AI. At present, one of the more mainstream pedestrian tracking methods is to perform pedestrian tracking through deep learning. However, deep learning requires the use of neural networks, and there are a large number of operations such as convolution and full connection in neural networks, and operations such as convolution and full connection consume a lot of calculations, which makes calculations take a relatively long time. long. As a result, the efficiency of pedestrian tracking through deep learning is low.

[0066] The embodiment of the present invention provides a pedestrian tracking method, which can store the features mat...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

Embodiments of the present invention provide a pedestrian tracking method, device, and equipment, wherein the method includes: acquiring video frames to be detected; detecting candidate pedestrians in the video frames to be detected; extracting candidate pedestrian features of candidate pedestrians; determining candidate pedestrian features difference with the features saved in the feature queue, and when the difference satisfies the preset condition, determine the candidate pedestrian as the target pedestrian; wherein, the saved features in the feature queue are features matching the target pedestrian. The efficiency of the pedestrian tracking process can be improved.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a pedestrian tracking method, device and equipment. Background technique [0002] Target tracking, such as pedestrian tracking, is an important aspect in the field of computer vision, and has broad application prospects in artificial intelligence (AI), video surveillance, human-computer interaction, robotics, military guidance and other fields. [0003] In an existing method, pedestrian tracking is completed through deep learning. Taking Multi-Domain Convolutional Neural Networks (MDNet) as an example, use multi-domain training, use convolutional neural network (Convolutional Neural Networks, CNN) features, use full connection for online fine-tuning, and also select candidate The process of target frame collection, combined with the process of judging the probability that each target frame is a target, finally determines that the candidate frame with the highest probab...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06N3/04
Inventor 钟韬
Owner BEIJING QIYI CENTURY SCI & TECH CO LTD