Social Distancing detection using Deep Learning
=============
<img src="/images/SocialDistancing1.png" width="100%" height="100%" title="Final Result" alt="Final Result"></img><br/>
**Background**
Coronavirus disease (COVID-19) is a new strain of disease in humans discovered in 2019 that has never been identified in the past.
Coronavirus is a large family of viruses that causes illness in patients ranging from common cold to advanced respiratory syndromes such as Middle East Respiratory Syndrome (MERS-COV) and Severe Acute Respiratory Syndrome (SARS-COV).
Many people are currently affected and are being treated across the world causing a global pandemic.
Several countries have declared a national emergency and have quarantined millions of people.
To be a part of the worldwide trend, I've created a Social Distancing detection system.
Application Workflow
-------------
<img src="/images/SocialDistancing2.png" width="70%" height="70%" title="Application Workflow" alt="Application Workflow"></img><br/>
* Detect Pedestrians in the perspective view
* Train YOLOv3 detector for pedestrian detection
* Convert perspective view into Bird's-eye view
* Morphs the perspective view into a bird’s-eye (top-down) view
* We assumes that every person is standing on the same flat ground plane.
* Measure the distances between persons in Bird's-eye view
* Estimate pedestrian's (x, y) location in the bird's-eye view.
* Selecting bottom-center point of each person's bounding box in the perspective view and transform the points into bird's-eye view.
Part1 - Detect Pedestrians in the perspective view
-------------
<img src="/images/SocialDistancing3-1.png" width="70%" height="70%" title="Detect Pedestrians" alt="Detect Pedestrians"></img><br/>
#### COVID19_PeopleExtractGT.mlx
This file extracts dataset provider given ground truth information, [Oxford Town Centre Dataset](http://www.robots.ox.ac.uk/ActiveVision/Research/Projects/2009bbenfold_headpose/project.html)[1], and get ready for the training.
#### COVID19_TrainPeopleYOLOv3.mlx
Train the pedestrian detection model from ground truth data, extracted from above file.
Part2 - Convert perspective view into Bird's-eye view & Measure the distances between persons in Bird's-eye view
-------------
<img src="/images/SocialDistancing4-1.png" width="100%" height="100%" title="Calibration" alt="Calibration"></img><br/>
#### COVID19_SocialDistancingScript.mlx
This file includes the entire social distancing system development script with pretrained people detection model.
It covers calibration process from perspective view into bird's-eye view, extract person's location and measure the distances each other.
<img src="/images/SocialDistancing5-1.png" width="50%" height="50%" title="Measurement" alt="Measurement"></img><br/>
Part3 - Test application and App for interactive execution
-------------
### COVID19_PeopleVideoRunning.mlx
With the pretrained people detector, and using COVID19_SocialDistancingScript.mlx, it can run social distancing detector for existing video.
<img src="/images/SocialDistancing1.png" width="100%" height="100%" title="Final Result" alt="Final Result"></img><br/>
### COVID19_SocialDistancing.mlapp
I have built a lightweight tool that enables even non-technical users to create the system for their own.
<img src="/images/SocialDistancing6.png" width="100%" height="100%" title="App for Social Distancing" alt="App for Social Distancing"></img><br/>
Requires
- [MATLAB](https://www.mathworks.com/products/matlab.html)
- [Deep Learning Toolbox](https://www.mathworks.com/products/deep-learning.html)
- [Image Processing Toolbox](https://www.mathworks.com/products/image.html)
- [Computer Vision Toolbox](https://www.mathworks.com/products/computer-vision.html)
- [Parallel Computing Toolbox](https://www.mathworks.com/products/parallel-computing.html)
- [MATLAB Coder](https://www.mathworks.com/products/matlab-coder.html)
- [GPU Coder](https://www.mathworks.com/products/gpu-coder.html)
For more information on Deep Learning in MATLAB
-------------
[![View Social-Distancing-Monitoring-System on File Exchange](https://www.mathworks.com/matlabcentral/images/matlab-file-exchange.svg)](https://kr.mathworks.com/matlabcentral/fileexchange/76760-social-distancing-monitoring-system)
**[Download a free MATLAB trial for Deep Learning](https://www.mathworks.com/products/deep-learning.html)**
References
-------------
[1] B. Benfold and I. Reid. Guiding visual surveillance by tracking human attention. In BMVC, 2009
Copyright 2020 The MathWorks, Inc.
没有合适的资源?快使用搜索试试~ 我知道了~
社交距离监控系统:支持AI的社交距离检测工具,可通过分析来自摄像机的实时视频流来检测人们是否彼此保持安全距离。 -创意积分:La...
共63个文件
xml:40个
png:9个
mlx:4个
需积分: 24 6 下载量 153 浏览量
2021-02-04
00:10:10
上传
评论
收藏 3.93MB ZIP 举报
温馨提示
社交距离监控系统:支持AI的社交距离检测工具,可通过分析来自摄像机的实时视频流来检测人们是否彼此保持安全距离。 -创意积分:Landing AI(https:landing.ai)
资源详情
资源评论
资源推荐
收起资源包目录
Social-Distancing-Monitoring-System-master.zip (63个子文件)
Social-Distancing-Monitoring-System-master
images
SocialDistancing4.png 74KB
SocialDistancing3-1.png 404KB
.gitkeep 0B
SocialDistancing1.png 1.11MB
SocialDistancing4-1.png 1003KB
SocialDistancing6.png 928KB
SocialDistancing5-1.png 14KB
SocialDistancing2.png 72KB
SocialDistancing5.png 74KB
SocialDistancing3.png 74KB
T.mat 816B
GithubSubmission.prj 177B
resources
project
Root.type.Categories
FileClassCategory.type.Category.xml 107B
FileClassCategory.type.Category
convenience.type.Label.xml 82B
other.type.Label.xml 82B
derived.type.Label.xml 82B
test.type.Label.xml 85B
design.type.Label.xml 82B
none.type.Label.xml 82B
artifact.type.Label.xml 88B
ProjectData.type.Info.xml 71B
uuid-8a4d8e10-e660-4470-812b-18af87e9e63d.xml 47B
Root.type.Files
yolov3Helper.type.File
1.type.DIR_SIGNIFIER.xml 47B
generateYOLOv3Detections.m.type.File.xml 141B
upsampleLayer.m.type.File.xml 141B
generateTargets.m.type.File.xml 141B
images.type.File
SocialDistancing2.png.type.File.xml 47B
SocialDistancing1.png.type.File.xml 47B
.gitkeep.type.File.xml 47B
SocialDistancing6.png.type.File.xml 47B
SocialDistancing3.png.type.File.xml 47B
1.type.DIR_SIGNIFIER.xml 47B
SocialDistancing5.png.type.File.xml 47B
SocialDistancing5-1.png.type.File.xml 47B
SocialDistancing4.png.type.File.xml 47B
SocialDistancing3-1.png.type.File.xml 47B
SocialDistancing4-1.png.type.File.xml 47B
T.mat.type.File.xml 141B
TRDATA.mat.type.File.xml 141B
images.type.File.xml 47B
COVID19_PeopleExtractGT.mlx.type.File.xml 141B
importGroundTruth.m.type.File.xml 141B
COVID19_SocialDistancingScript.mlx.type.File.xml 141B
LICENSE.type.File.xml 47B
COVID19_SocialDistancing.mlapp.type.File.xml 141B
PeopleYOLOv3.mat.type.File.xml 141B
COVID19_TrainPeopleYOLOv3.mlx.type.File.xml 141B
durationForVideo.mat.type.File.xml 141B
README.md.type.File.xml 47B
COVID19_PeopleVideoRunning.mlx.type.File.xml 141B
yolov3Helper.type.File.xml 47B
Project.xml 74B
COVID19_PeopleVideoRunning.mlx 8KB
LICENSE 1KB
COVID19_SocialDistancingScript.mlx 94KB
yolov3Helper
generateTargets.m 6KB
upsampleLayer.m 890B
generateYOLOv3Detections.m 2KB
README.md 4KB
COVID19_SocialDistancing.mlapp 78KB
COVID19_TrainPeopleYOLOv3.mlx 47KB
COVID19_PeopleExtractGT.mlx 6KB
TRDATA.mat 36KB
共 63 条
- 1
Ruin-鸣
- 粉丝: 24
- 资源: 4569
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功
评论0