Real time hand pose estimation using depth sensors

By Cem Keskin, Mustafa Furkan Kıraç, Yunus Emre Kara, Lale Akarun. IEEE International Conference on Computer Vision, 2011

418 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/df74f8ee027cf7050aade9f7bc541a526c5cf079

How researchers see this paper

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

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

Hand gesture recognition with depth images: A review (2012, methodology): “Of the papers reviewed, 22 use the Kinect as the depth sensor for gesture recognition [5-26], and of these 9 use OpenNI and the NITE middleware for hand tracking [10, 14-16, 18, 21, 22, 25, 26], as opposed to implementing a method of their own.”
First-Person View Hand Segmentation of Multi-Modal Hand Activity Video Dataset (2020, background): “Therefore, understanding hands with computer vision systems has been deeply explored through hand tracking [41, 54], hand pose estimation [18, 21, 22, 27, 29], grasp detection [10, 47], hand gesture recognition [58], multi-view prediction [29], and hand-action classiﬁcation [50].”
Action Classification with Locality-Constrained Linear Coding (2014, background): “Since the release of Microsoft Kinect depth camera, depth based human action recognition methods [11], [23], [18], [10], [19], [24], [9], [5], [7] start to emerge.”
Parsing the Hand in Depth Images (2014, methodology): “Similar work has been done in both the fields of full-body tracking [8], [29], [40] and hand parsing [28], [30].”
3D Gestural Interaction: The State of the Field (2013, methodology): “used structured light-based depth sensing to also track hand and finger poses in real time [41].”
Feature learning based on SAE-PCA network for human gesture recognition in RGBD images (2015, methodology): “We follow the same experimental protocol with [7,12], where half of the samples are used to train, and the other half are used for testing.”
Fusion of Inertial and Depth Sensor Data for Robust Hand Gesture Recognition (2014, methodology): “For example, in [10], depth images captured by Kinect were used to achieve American Sign Language (ASL) recognition.”
TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 1 ModDrop (2018, positive): “A group of recent works is dedicated to inferring the hand pose through pixel-wise hand segmentation and estimating the positions of hand or body joints in a bottom-up fashion [20], [21], [22], [23], [24].”
Training a Feedback Loop for Hand Pose Estimation (2015, methodology): “A popular approach is to use a discriminative method to predict the position of the joints [13, 21, 30, 31, 35], because they are now robust and fast.”
Survey on 3D Hand Gesture Recognition (2016, background): “[38], [61] generalized the idea of [37] to the 3D hand pose estimation using depth data.”
Real-Time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor (2017, background): “Random forests are a popular choice [12, 36, 34, 45, 43] due to their capacity but still result in kinematically inconsistent and jittery pose estimates.”
Multi-scale Deep Learning for Gesture Detection and Localization (2014, background): “A group of recent works is dedicated to inferring the hand pose through pixel-wise hand segmentation and estimating the positions of hand joints in a bottom-up fashion [19–22].”
A Survey on Human Motion Analysis from Depth Data (2013, methodology): “the full hand, also a mapping only for body parts can be learned [129] as shown in Figure 20(c).”
DART: Dense Articulated Real-Time Tracking (2014, methodology): “Discriminative approaches have proven extremely successful for the problem of human pose estimation [29, 31], and similar approaches have also been applied to hand tracking [17].”
Hands Deep in Deep Learning for Hand Pose Estimation (2015, methodology): “Motivated by work for human pose estimation [20], [10] uses Random Forests to perform a per-pixel classification of depth images and then a local mode-finding algorithm to estimate the 2D joint locations.”
Real time action recognition using histograms of depth gradients and random decision forests (2014, background): “In this context, the depth based action recognition research can be broadly divided into two categories, namely, algorithms mainly using depth images [6, 5, 3, 12, 15, 7] and others mainly using joint positions [14, 13].”