Trainable, vision-based automated home cage behavioral phenotyping

Proceedings of Measuring Behavior 2016 : 10th International Conference on Methods and Techniques in Behavioral Research. International Conference on Methods and Techniques in Behavioral Research (10th : 2016 : Dublin, Ireland) Pub Date : 2010-08-24 DOI:10.1145/1931344.1931377

Hueihan Jhuang, Estíbaliz Garrote, N. Edelman, T. Poggio, Andrew D. Steele, Thomas Serre

{"title":"Trainable, vision-based automated home cage behavioral phenotyping","authors":"Hueihan Jhuang, Estíbaliz Garrote, N. Edelman, T. Poggio, Andrew D. Steele, Thomas Serre","doi":"10.1145/1931344.1931377","DOIUrl":null,"url":null,"abstract":"We describe a fully trainable computer vision system enabling the automated analysis of complex mouse behaviors. Our system computes a sequence of feature descriptors for each video sequence and a classifier is used to learn a mapping from these features to behaviors of interest. We collected a very large manually annotated video database of mouse behaviors for training and testing the system. Our system performs on par with human scoring, as measured from the ground-truth manual annotations of thousands of clips of freely behaving mice. As a validation of the system, we characterized the home cage behaviors of two standard inbred and two nonstandard mouse strains. From this data, we were able to predict the strain identity of individual mice with high accuracy.","PeriodicalId":92837,"journal":{"name":"Proceedings of Measuring Behavior 2016 : 10th International Conference on Methods and Techniques in Behavioral Research. International Conference on Methods and Techniques in Behavioral Research (10th : 2016 : Dublin, Ireland)","volume":"26 1","pages":"33:1-33:4"},"PeriodicalIF":0.0000,"publicationDate":"2010-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of Measuring Behavior 2016 : 10th International Conference on Methods and Techniques in Behavioral Research. International Conference on Methods and Techniques in Behavioral Research (10th : 2016 : Dublin, Ireland)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/1931344.1931377","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 8

Abstract

We describe a fully trainable computer vision system enabling the automated analysis of complex mouse behaviors. Our system computes a sequence of feature descriptors for each video sequence and a classifier is used to learn a mapping from these features to behaviors of interest. We collected a very large manually annotated video database of mouse behaviors for training and testing the system. Our system performs on par with human scoring, as measured from the ground-truth manual annotations of thousands of clips of freely behaving mice. As a validation of the system, we characterized the home cage behaviors of two standard inbred and two nonstandard mouse strains. From this data, we were able to predict the strain identity of individual mice with high accuracy.

查看原文本刊更多论文

可训练的，基于视觉的自动化家庭笼行为表型

我们描述了一个完全可训练的计算机视觉系统，能够自动分析复杂的鼠标行为。我们的系统为每个视频序列计算一个特征描述符序列，并使用一个分类器来学习从这些特征到感兴趣行为的映射。我们收集了一个非常大的手动注释的鼠标行为视频数据库，用于训练和测试系统。我们的系统的表现与人类评分相当，这是根据成千上万个行为自由的老鼠片段的真实人工注释来衡量的。为了验证该系统的有效性，我们对两种标准近交系和两种非标准系小鼠的家笼行为进行了表征。根据这些数据，我们能够高精度地预测单个小鼠的品系身份。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Proceedings of Measuring Behavior 2016 : 10th International Conference on Methods and Techniques in Behavioral Research. International Conference on Methods and Techniques in Behavioral Research (10th : 2016 : Dublin, Ireland)

自引率

0.00%

发文量