DeepLabCut: markerless pose estimation of user-defined body parts with deep learning
Explore this paper's citation graph
Summary
This work presents an efficient method for markerless pose estimation based on transfer learning with deep neural networks that achieves excellent results with minimal training data and shows that the toolbox, called DeepLabCut, can achieve human accuracy with only a few hundred frames of training data.
- Type
- preprint
- Published
- 2018-04-09
- Cited by
- 4,558
- References
- 82
- Access
- Open access
- OpenAlex
- https://openalex.org/W2797291297
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:4748395
Keywords
Tracking (education), Artificial intelligence, Deep learning, Computer science, Computer vision
References
- Closed-loop neuromodulation of spinal sensorimotor circuits controls refined locomotion after complete spinal cord injury
- Beyond the Kalman Filter: Particle Filters for Tracking Applications
- Biomechanics and Motor Control of Human Movement
- Decoding complete reach and grasp actions from local primary motor cortex populations
- On aims and methods of Ethology
- Automated Tracking of Animal Posture and Movement during Exploration and Sensory Orientation Behaviors
- A hitchhiker's guide to behavioral analysis in laboratory rodents
- Rats track odour trails accurately using a multi-layered strategy with near-optimal sampling
- idTracker: tracking individuals in a group by automatic identification of unmarked animals
- Pictorial Structures for Object Recognition
- Computerized video analysis of social interactions in mice
- Toward a science of computational ethology.
- A 3D-Video-Based Computerized Analysis of Social and Sexual Interactions in Rats
- 2D Human Pose Estimation: New Benchmark and State of the Art Analysis
- SEE: a tool for the visualization and analysis of rodent exploratory behavior.
- Automated image-based tracking and its application in ecology.
- The co-ordination and regulation of movements
- Adaptive background mixture models for real-time tracking
- DeepPose: Human Pose Estimation via Deep Neural Networks
- Big behavioral data: psychology, ethology and the foundations of neuroscience
Cited by
- Fast animal pose estimation using deep neural networks
- Modulation of tactile feedback for the execution of dexterous movement
- A hybrid versatile method for state estimation and feature extraction from the trajectory of animal behavior
- Movement-related activity dominates cortex during sensory-guided decision making
- Spontaneous behaviors drive multidimensional, brain-wide activity
- The Roles of Supervised Machine Learning in Systems Neuroscience
- Robust mouse tracking in complex environments using neural networks
- Exploration in the Presence of Mother in Typically and Non-typically Developing Pre-walking Human Infants
- Human-level saccade detection performance using deep neural networks
- Behavioral tracking gets real
- Automated leg tracking reveals distinct conserved gait and tremor signatures in Drosophila models of Parkinson’s Disease and Spinocerebellar ataxia 3
- Magnetoelectric materials for miniature, wireless neural stimulation at therapeutic frequencies
- On the inference speed and video-compression robustness of DeepLabCut
- Using DeepLabCut for 3D markerless pose estimation across species and behaviors
- Mouse Academy: high-throughput automated training and trial-by-trial behavioral analysis during learning
- Creatures great and SMAL: Recovering the shape and motion of animals from video
- Multiview Supervision By Registration
- optoPAD: a closed-loop optogenetics system to study the circuit basis of feeding behaviors
- Real-time markerless video tracking of body parts in mice using deep neural networks
- Stytra: An open-source, integrated system for stimulation, tracking and closed-loop behavioral experiments
Related papers
- Overview of deep learning in medical imaging
- Survey of Machine Learning Applications of Convolutional Neural Networks to Medical Image Analysis
- Foreground object segmentation from binocular stereo video
- 6-DOF object localization by combining monocular vision and robot arm kinematics
- An Object Detection and Pose Estimation Approach for Position Based Visual Servoing
- Object-oriented stripe structured-light vision-guided robot
- Tracking in 3D: Image Variability Decomposition for Recovering Object Pose and Illumination
- Exploring Deep Learning for View-Based 3D Model Retrieval
- Hand-eye calibration using a single image and robotic picking up using images lacking in contrast
- Motion-based Object Detection and Tracking in Color Image Sequence