Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A deep learning-based passenger detection method and system

A technology of deep learning and detection methods, applied in neural learning methods, character and pattern recognition, instruments, etc., can solve problems such as low precision and difficult real-time detection models

Active Publication Date: 2022-03-11
哈尔滨思派科技有限公司
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a method and system for passenger detection based on deep learning, which solves the problems of low precision and difficult real-time performance of the detection model in the prior art

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 deep learning-based passenger detection method and system
  • A deep learning-based passenger detection method and system
  • A deep learning-based passenger detection method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The principles and features of the present invention are described below in conjunction with the accompanying drawings, and the examples given are only used to explain the present invention, and are not intended to limit the scope of the present invention.

[0046] Convolutional Neural Network (CNN) is an efficient recognition method developed in recent years, especially in the fields of image recognition and pattern classification, which has attracted extensive attention. Training a convolutional neural network model involves the following steps:

[0047]1. Use the convolutional layer to convolve the input image. The convolution layer includes a convolution kernel, and the processing of the picture through the selected convolution kernel is firstly based on the principle of the local perception field. It is generally believed that people's cognition of the outside world is from local to global, and the spatial connection of images is also that local pixels are closely...

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

The invention relates to the field of vehicle target detection, in particular to a passenger detection method and system based on deep learning. The method comprises the following steps: adopting the YOLO method to train the YOLO neural network used to recognize the rectangular frame of the passenger's body shape; acquiring target video information; using the YOLO neural network trained in step S1 to identify the target video information, and according to the recognition result It is judged whether the target passenger is included in the target video information. The present invention proposes a passenger detection method and system based on deep learning. The YOLO method is used to train the convolutional neural network. Based on the characteristics of simple YOLO prediction process, fast speed and high detection rate, the present invention can be used in complex environments, such as illumination In environments where there are changes and vibrations, etc., it has high Precision / Recall and high detection speed.

Description

technical field [0001] The invention relates to the field of vehicle target detection, in particular to a passenger detection method and system based on deep learning. Background technique [0002] At present, domestic and foreign bus passenger flow statistics methods are mainly divided into two categories. One is based on non-image passenger flow statistics methods. Looking back at the development history of bus passenger flow statistics systems, there have been programs such as pressure pedals, infrared detection, and IC cards. To detect the bus passenger flow, but there are many problems in engineering applications. As far as the pressure pedal solution is concerned, it indirectly infers the number of times and weights of passengers based on piezoresistors to infer the number of people. Due to the huge flow of people on the bus and the differences in people's weight, different steps and the severity of pedaling, etc., resulting in The results of missed detection and fals...

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): G06V40/10G06V20/40G06V10/82G06N3/08
CPCG06N3/084G06V40/10G06V20/41
Inventor 吴艳霞曾相未徐宇凡
Owner 哈尔滨思派科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com