- 1、本文档共8页,可阅读全部内容。
- 2、原创力文档(book118)网站文档一经付费(服务费),不意味着购买了该文档的版权,仅供个人/单位学习、研究之用,不得用于商业用途,未经授权,严禁复制、发行、汇编、翻译或者网络传播等,侵权必究。
- 3、本站所有内容均由合作方或网友上传,本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺!文档内容仅供研究参考,付费前请自行鉴别。如您付费,意味着您自己接受本站规则且自行承担风险,本站不退款、不进行额外附加服务;查看《如何避免下载的几个坑》。如果您已付费下载过本站文档,您可以点击 这里二次下载。
- 4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等,请点击“版权申诉”(推荐),也可以打举报电话:400-050-0827(电话支持时间:9:00-18:30)。
查看更多
Material Classification with Thermal Imagery
Philip Saponaro, Scott Sorensen, Abhishek Kolagunda, and Chandra Kambhamettu
Video/Image Modeling and Synthesis (VIMS) Lab,
Dept. of Computer and Information Science, University of Delaware
Newark, Delaware
saponaro,sorensen,abhi,chandrak@udel.edu
Abstract ness of emitting thermal radiation compared to a black body
source at the same temperature. Metals have very low emis-
Material classification is an important area of research sivity and high reflectance, while woods have high emissiv-
in computer vision. Typical algorithms use color and tex- ity. Thus many metals appear mirrorlike in the LWIR im-
ture information for classification, but there are problems agery.
due to varying lighting conditions and diversity of colors in When water comes into contact with an object, the per-
a single material class. In this work we study the use of long meation behavior changes based on the material. For exam-
wave infrared (i.e. thermal) imagery for material classifica- ple, in wood the water follows along the grain of the wood
tion. Thermal imagery has the benefit of relative invariance and is jagged in appearance, while in metals the water stays
to color changes, invariance to lighting conditions, and can above the surface and hardly moves if the surface is flat,
even work in the dark. We collect a database of 21 differ- and in paper materials, the water spreads radially. We use
ent material classes with both color and thermal imagery. the permeation behavior as a cue for classification. We con-
您可能关注的文档
- Large-scale hierarchical text classification without labelled data英文文献资料.pdf
- Leaf Classification Utilizing a Convolutional1英文文献资料.pdf
- Learning Pattern Classification—A Survey英文文献资料.pdf
- Lec14_text_classification英文文献资料.pdf
- Linear Classification英文文献资料.pdf
- LOTTE+DUTY+FREE+MAGAZINE+FEB.2016英文文献资料.pdf
- Mining relationships among interval-based events for classification[1]英文文献资料.pdf
- Minute.of.Uniting the classification of cultured and uncultured bacteria and archaea using 16S rRNA gene sequences英文文献资料.pdf
- Model-Free Episodic Control_DeepMind英文文献资料.pdf
- Mol Pharmacol-2014-Free-mol.113.090563英文文献资料.pdf
文档评论(0)