Deep learning tools for the measurement of animal behavior in neuroscience

被引:242
作者
Mathis, Mackenzie Weygandt [1 ]
Mathis, Alexander [1 ]
机构
[1] Harvard Univ, Cambridge, MA 02138 USA
关键词
POSE ESTIMATION; TRACKING; MOTION; MOTOR;
D O I
10.1016/j.conb.2019.10.008
中图分类号
Q189 [神经科学];
学科分类号
071006 ;
摘要
Recent advances in computer vision have made accurate, fast and robust measurement of animal behavior a reality. In the past years powerful tools specifically designed to aid the measurement of behavior have come to fruition. Here we discuss how capturing the postures of animals - pose estimation - has been rapidly advancing with new deep learning methods. While challenges still remain, we envision that the fast-paced development of new deep learning tools will rapidly change the landscape of realizable real-world neuroscience.
引用
收藏
页码:1 / 11
页数:11
相关论文
共 96 条
[1]   Toward a Science of Computational Ethology [J].
Anderson, David J. ;
Perona, Pietro .
NEURON, 2014, 84 (01) :18-31
[2]   PoseTrack: A Benchmark for Human Pose Estimation and Tracking [J].
Andriluka, Mykhaylo ;
Iqbal, Umar ;
Insafutdinov, Eldar ;
Pishchulin, Leonid ;
Milan, Anton ;
Gall, Juergen ;
Schiele, Bernt .
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :5167-5176
[3]  
[Anonymous], ARXIV190602831
[4]  
[Anonymous], ARXIV190706922
[5]  
[Anonymous], NOBEL PRIZE PHYSL ME
[6]  
[Anonymous], 2017, P IEEE C COMP VIS PA
[7]  
[Anonymous], ELIFE
[8]  
[Anonymous], 2015, IEEE C COMP VIS PATT
[9]  
[Anonymous], BIORXIV
[10]  
[Anonymous], P IEEE C COMP VIS PA