Monocular 3D pose estimation and tracking by detection

By Mykhaylo Andriluka, Stefan Roth, Bernt Schiele. 2010

590 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields (2016, methodology): “The spatial model for articulated pose is either based on tree-structured graphical models [10, 30, 4, 3, 26, 40, 17], which parametrically encode the spatial relationship between adjacent parts following a kinematic chain, or non-tree models [37, 31, 20, 18, 8] that augment the tree structure with…”
Convolutional Pose Machines (2016, background): “The classical approach to articulated pose estimation is the pictorial structures model [2, 3, 9, 14, 26, 27, 30, 43] in which spatial correlations between parts of the body are expressed as a tree-structured graphical model with kinematic priors that couple connected limbs.”
Feature Boosting Network For 3D Pose Estimation (2019, background): “3D pose estimation (estimating the locations of the joints of the human hand or body in 3D space) is a challenging and fast-growing research area, thanks to its wide applications in gesture recognition, activity understanding, human-machine interaction, etc. [2].”
3D Shape Induction from 2D Views of Multiple Objects (2016, methodology): “Recognition-based methods have been used to estimate geometry of out-door scenes [14, 26], indoor environments [9, 27], and objects [1, 25].”
Learning Human Pose Estimation Features with Convolutional Networks (2013, background): “In a similar spirit, more general techniques using pictorial structures [2, 3, 17, 37, 33, 34], “poselets” [9], and other part-models [16, 50] have received increased attention.”
Pose Machines: Articulated Pose Estimation via Inference Machines (2014, methodology): “Pictorial structure models [1,2,3,4,5,6], express the human body as a tree-structured graphical model with kinematic priors that couple connected limbs.”
An Efficient Convolutional Network for Human Pose Estimation (2016, methodology): “The classical approaches are based on the pictorial structures model [1, 2, 7, 10, 14, 18, 19, 32] that uses a tree-structured graphical model to encode spatial dependencies between neighbouring joints.”
3D Human Pose Estimation from Monocular Images with Deep Convolutional Neural Network (2014, unknown): “In this paper, we focus on estimating 3D human pose from monocular RGB images [1–3].”
Fusing 2D Uncertainty and 3D Cues for Monocular Body Pose Estimation (2016, unknown): “In the past, this usually involved inferring a 3D human pose either optimizing an energy function derived from image information, such as silhouettes [5, 13, 20, 21, 24, 29, 43, 53], feature trajectories [68] and 2D joint locations [3, 4, 19, 33, 45, 51, 62, 63], or 2D recognitionbased pose retrieva”
Exploiting Temporal Information for 3D Human Pose Estimation (2017, methodology): “Using temporal information Since estimating poses for each frame individually leads to incoherent and jittery predictions over a sequence, many approaches tried to exploit temporal information [42, 43, 20, 44, 11].”
Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, background): “They extend this idea in Andriluka et al. (2010) towards 3D pose estimation from monocular images.”
ArtTrack: Articulated Multi-Person Tracking in the Wild (2016, background): “Earlier approaches to articulated pose tracking in monocular videos rely on hand-crafted image representations and focus on simplified tasks, such as tracking upper body poses of frontal isolated people [24, 31, 27, 8], or tracking walking pedestrians with little degree of articulation [2, 3].”
Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments (2014, background): “matic discriminative prediction [10], [11], [12], [13], [14], whereas others aim at model-image alignment [15], [16], [17], [18], [19], [20], [21], [22], [23] or accurate modeling of 3D shape[24], [25] or clothing[26].”
GMCP-Tracker: Global Multi-object Tracking Using Generalized Minimum Clique Graphs (2012, methodology): “We tested the proposed method on the diverse sequences of Town Center [1], TUD-corssing [2], TUD-Stadtmitte [2], PETS2009 [3], and a new sequence called Parking Lot, all with promising results.”
Recovering Accurate 3D Human Pose in the Wild Using IMUs and a Moving Camera (2018, background): “For multiple people, the work [1] infers the 3D poses using a tracking formulation that is based on short tracklets of 2D body parts.”
3D Pose from Motion for Cross-View Action Recognition via Non-linear Circulant Temporal Encoding (2014, unknown): “[2] track body parts exploiting recent advancements in 2D human pose detection and apply pose and motion priors to recover 3D pose in realistic videos.”
Pictorial Human Spaces: How Well Do Humans Perceive a 3D Articulated Pose? (2013, methodology): “The synchronization between the two cameras is done automatically by the system.”
MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior (2017, unknown): “, the “loose-limbed people” [28] and “tracking-by-detection” [11].”
Multiple Viewpoint Recognition and Localization (2010, unknown): “For example, Andriluka et al. [7] use a bank of viewpoint-dependent human appearance models and combine these with a learned motion prior to gather consistent information across motion tracks.”