The Yale human grasping dataset: Grasp, object, and task data in household and machine shop environments

By Ian M. Bullock, Thomas Feix, Aaron M. Dollar. 2015

106 citations recorded by the source corpus.

This paper presents a dataset of human grasping behavior in unstructured environments. Wide-angle head-mounted camera video was recorded from two housekeepers and two machinists during their regular work activities, and the grasp types, objects, and tasks were analyzed and coded by study staff. The full dataset contains 27.7 hours of tagged video and represents a wide range of manipulative behaviors spanning much of the typical human hand usage. We provide the original videos, a spreadsheet including the tagged grasp type, object, and task parameters, time information for each successive grasp, and video screenshots for each instance. Example code is provided for MATLAB and R, demonstrating how to load in the dataset and produce simple plots.

Subfields: Control and Systems Engineering, Radiological and Ultrasound Technology, Evaluation & Benchmarks, Human-Computer Interaction, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Control and Systems Engineering

In Radiological and Ultrasound Technology

In Evaluation & Benchmarks

In Human-Computer Interaction

In Robotics & Control

Citations in the corpus

Ego4D: Around the World in 3,000 Hours of Egocentric Video (2021, background): “[25] Ian M Bullock, Thomas Feix, and Aaron M Dollar.”
GanHand: Predicting Human Grasp Affordances in Multi-Object Scenes (2020, background): “Previous work has focused on providing alternative information such as grasp taxonomies [60, 56, 7, 30].”
Ego2Hands: A Dataset for Egocentric Two-hand Segmentation and Detection (2020, methodology): “To demonstrate cross-dataset adaptation performance, [10] provided binary-labelling for 855 and 488 frames from human grasping datasets UTG [9] and YHG [8] respectively.”
Generalizing Hand Segmentation in Egocentric Videos With Uncertainty-Guided Model Adaptation (2020, unknown): “YHG dataset [9].”
First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations (2017, methodology): “Yale [6] RGB X 33 - 9,100 Grasp UTG [7] RGB X 17 Grasp GTEA [14] RGB X 61 525 31,222 Action EgoHands [5] RGB X 4 48 4,800 Action”
HOnnotate: A Method for 3D Annotation of Hand and Object Poses (2019, background): “Many works provide egocentric RGB or RGB-D sequences for action recognition [3,6,7,13,48].”
WorkingHands: A Hand-Tool Assembly Dataset for Image Segmentation and Activity Mining (2019, unknown): “Yale [6] 0 18K N 11 Khan et al. [16] 1.6K N Man.”
The GRASP Taxonomy of Human Grasp Types (2016, methodology): “housekeepers and machinists [54], [56].”