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

Pedestrian detection method and device in complex environment based on YOLOv3 improvement

A complex environment and pedestrian detection technology, applied in the field of pedestrian detection, can solve the problems of mutual occlusion, different sizes, and missed detection of pedestrians, and achieve the effect of improving recognition accuracy

Pending Publication Date: 2022-03-08
BEIJING HUANENG XINRUI CONTROL TECH
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In complex scenes, pedestrians occlude each other and have different sizes, which will lead to a large number of missed detections

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
  • Pedestrian detection method and device in complex environment based on YOLOv3 improvement
  • Pedestrian detection method and device in complex environment based on YOLOv3 improvement
  • Pedestrian detection method and device in complex environment based on YOLOv3 improvement

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] In order to enable those skilled in the art to better understand the technical solution of the present disclosure, the present disclosure will be described in further detail below in conjunction with the accompanying drawings and specific embodiments.

[0068] In one aspect of this embodiment, as figure 1 As shown, it relates to a pedestrian detection method S100 in a complex environment based on YOLOv3 improvement, and the method S100 includes:

[0069] S110. Prepare a data set, and perform data augmentation to simulate data in a complex environment.

[0070] Specifically, in this step, image and label data required by the YOLO network are prepared to obtain a training set. For example, a total of 1223 photos with pedestrian targets in the KITTI dataset were selected, and the pictures were uniformly adjusted to a size of 1024*1024, and other categories of the KITTI dataset were eliminated, leaving only a single category of pedestrians for pedestrian detection. In thi...

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 provides a pedestrian detection method and device in a complex environment based on YOLOv3 improvement. The method comprises the following steps: preparing a data set, and performing data enhancement to simulate data in a complex environment; a YOLOv3 improved network model is built; the YOLOv3 improved network model is trained; and detecting the pedestrian by using the optimal training model. According to the pedestrian detection method in the complex environment based on YOLOv3 improvement disclosed by the invention, a backbone network of YOLOv3 is improved, and an output feature layer is improved, so that pedestrian detection under a high-resolution image is realized, the algorithm recognition precision is improved, and the problem that pedestrians shield each other in the complex environment is solved; and a large number of targets are missed due to different sizes.

Description

technical field [0001] The disclosure belongs to the technical field of artificial intelligence, and in particular relates to a pedestrian detection method and device in a complex environment improved based on YOLOv3. Background technique [0002] In recent years, computer vision technology has achieved rapid development with the support of deep learning, attracting many researchers to devote themselves to it. Although thousands of researchers have different focuses, the ultimate goal is the same: to make Technology serves people, or liberates productivity, so research related to people is indispensable. [0003] Pedestrian detection plays an important role in the field of intelligent monitoring and security. In order to prevent property safety and deployment, most public places are equipped with monitoring equipment. However, despite this, when a large amount of pedestrian data appears in the monitoring equipment, only based on the inspection of a special person, it will l...

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 Applications(China)
IPC IPC(8): G06V40/10G06T5/50G06T7/00G06K9/62G06N3/04G06N3/08G06V10/764G06V10/774
CPCG06T7/0002G06T5/50G06N3/084G06N3/045G06F18/214G06F18/241
Inventor 曹利蒲李丹阳陈岩磊张澈杨继明田长风王军陈婷婷李涛
Owner BEIJING HUANENG XINRUI CONTROL TECH