A three-dimensional virtual mouse generates synthetic training data for behavioral analysis.

A three-dimensional virtual mouse generates synthetic training data for behavioral analysis.
复制标题

DOI:
10.1038/s41592-021-01103-9
复制
发表时间:
2021-04
期刊:
影响因子:
48
通讯作者:
Murphy TH
Murphy TH
中科院分区:
生物学1区
文献类型:
--
作者:
Bolaños LA;Xiao D;Ford NL;LeDue JM;Gupta PK;Doebeli C;Hu H;Rhodin H;Murphy TH

文献摘要

参考文献

被引文献

相似文献

我们开发了一种基于CT扫描的3D合成动画鼠标,它使用动画和半随机、关节约束的运动来生成具有地面真实标签位置的合成行为数据。图像域转换生成逼真的合成视频,用于训练2D和3D姿势估计模型,其精度类似于典型的手动训练数据集。基于3D模型的姿势估计的输出产生了比2D视频更好的行为集群定义,并可能促进自动行为分类。
We develop a 3D synthetic animated mouse based on CT scans that is actuated using animation and semi-random, joint-constrained movements to generate synthetic behavioural data with ground-truth label locations. Image-domain translation produced realistic synthetic videos used to train 2D and 3D pose estimation models with accuracy similar to typical manual training datasets. The outputs from the 3D model-based pose estimation yielded better definition of behavioral clusters than 2D videos and may facilitate automated ethological classification.
DOI: 10.1016/j.cell.2015.05.047
发表时间: 2015-07-02
期刊: Cell
影响因子: 64.5
作者:
Levine JH;Simonds EF;Bendall SC;Davis KL;Amir el-AD;Tadmor MD;Litvin O;Fienberg HG;Jager A;Zunder ER;Finck R;Gedman AL;Radtke I;Downing JR;Pe'er D;Nolan GP
通讯作者: Nolan GP
DOI: 10.1007/s11307-010-0386-x
发表时间: 2011-10
影响因子: 3.1
作者:
Khmelinskii, Artem;Baiker, Martin;Kaijzel, Eric L.;Chen, Josette;Reiber, Johan H. C.;Lelieveldt, Boudewijn P. F.
通讯作者: Lelieveldt, Boudewijn P. F.
DOI: 10.1038/s41593-018-0209-y
发表时间: 2018-09-01
影响因子: 25
作者:
Mathis, Alexander;Mamidanna, Pranav;Bethge, Matthias
通讯作者: Bethge, Matthias
DOI: 10.1093/oxfordjournals.aob.a083391
发表时间: 1954-01-01
期刊: ANNALS OF BOTANY
影响因子: 4.2
作者:
HOPKINS, B;SKELLAM, JG
通讯作者: SKELLAM, JG
DOI: 10.1088/1742-5468/2008/10/p10008
发表时间: 2008-10-01
影响因子: 2.4
作者:
Blondel, Vincent D.;Guillaume, Jean-Loup;Lefebvre, Etienne
通讯作者: Lefebvre, Etienne