{"title":"基于监控摄像头数据的高保真人体轨迹跟踪","authors":"Zexu Li, Lei Fang","doi":"arxiv-2312.16328","DOIUrl":null,"url":null,"abstract":"Human crowds exhibit a wide range of interesting patterns, and measuring them\nis of great interest in areas ranging from psychology and social science to\ncivil engineering. While \\textit{in situ} measurements of human crowd patterns\nrequire large amounts of time and labor to obtain, human crowd experiments may\nresult in statistics different from those that would emerge with a naturally\nemerging crowd. Here we present a simple, broadly applicable, highly accurate\nhuman crowd tracking technique to extract high-fidelity kinematic information\nfrom widely available surveillance camera videos. With the proposed technique,\nresearchers can access scientific crowd data on a scale that is orders of\nmagnitude larger than before. In addition to being able to measure an\nindividual's time-resolved position and velocity, our technique also offers\nhigh validity time-resolved acceleration and step frequency, and step length.\nWe demonstrate the applicability of our technique by applying it to\nsurveillance camera videos in Tokyo Shinjuku streamed on YouTube and exploiting\nits high fidelity to expose the hidden contribution of walking speed variance\nat the crossroad. The high fidelity and simplicity of this powerful technique\nopen up the way to utilize the large volume of existing surveillance camera\ndata around the world for scientific studies.","PeriodicalId":501305,"journal":{"name":"arXiv - PHYS - Adaptation and Self-Organizing Systems","volume":"49 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2023-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"High Fidelity Human Trajectory Tracking Based on Surveillance Camera Data\",\"authors\":\"Zexu Li, Lei Fang\",\"doi\":\"arxiv-2312.16328\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Human crowds exhibit a wide range of interesting patterns, and measuring them\\nis of great interest in areas ranging from psychology and social science to\\ncivil engineering. While \\\\textit{in situ} measurements of human crowd patterns\\nrequire large amounts of time and labor to obtain, human crowd experiments may\\nresult in statistics different from those that would emerge with a naturally\\nemerging crowd. Here we present a simple, broadly applicable, highly accurate\\nhuman crowd tracking technique to extract high-fidelity kinematic information\\nfrom widely available surveillance camera videos. With the proposed technique,\\nresearchers can access scientific crowd data on a scale that is orders of\\nmagnitude larger than before. In addition to being able to measure an\\nindividual's time-resolved position and velocity, our technique also offers\\nhigh validity time-resolved acceleration and step frequency, and step length.\\nWe demonstrate the applicability of our technique by applying it to\\nsurveillance camera videos in Tokyo Shinjuku streamed on YouTube and exploiting\\nits high fidelity to expose the hidden contribution of walking speed variance\\nat the crossroad. The high fidelity and simplicity of this powerful technique\\nopen up the way to utilize the large volume of existing surveillance camera\\ndata around the world for scientific studies.\",\"PeriodicalId\":501305,\"journal\":{\"name\":\"arXiv - PHYS - Adaptation and Self-Organizing Systems\",\"volume\":\"49 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-12-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - PHYS - Adaptation and Self-Organizing Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2312.16328\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - PHYS - Adaptation and Self-Organizing Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2312.16328","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
High Fidelity Human Trajectory Tracking Based on Surveillance Camera Data
Human crowds exhibit a wide range of interesting patterns, and measuring them
is of great interest in areas ranging from psychology and social science to
civil engineering. While \textit{in situ} measurements of human crowd patterns
require large amounts of time and labor to obtain, human crowd experiments may
result in statistics different from those that would emerge with a naturally
emerging crowd. Here we present a simple, broadly applicable, highly accurate
human crowd tracking technique to extract high-fidelity kinematic information
from widely available surveillance camera videos. With the proposed technique,
researchers can access scientific crowd data on a scale that is orders of
magnitude larger than before. In addition to being able to measure an
individual's time-resolved position and velocity, our technique also offers
high validity time-resolved acceleration and step frequency, and step length.
We demonstrate the applicability of our technique by applying it to
surveillance camera videos in Tokyo Shinjuku streamed on YouTube and exploiting
its high fidelity to expose the hidden contribution of walking speed variance
at the crossroad. The high fidelity and simplicity of this powerful technique
open up the way to utilize the large volume of existing surveillance camera
data around the world for scientific studies.