Recognizing actions using depth motion maps-based histograms of oriented gradients

By Xiaodong Yang, Chenyang Zhang, Yingli Tian. 2012

573 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Endocrinology, Diabetes and Metabolism

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Endocrinology, Diabetes and Metabolism

Citations in the corpus

Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos (2016, neutral): “DHOG [85] 66.”
Multimodal Multipart Learning for Action Recognition in Depth Videos (2015, methodology): “Depth HOG [38] (as reported in [16]) 66.11% Actionlet Ensemble [2] (as reported in [16]) 82.22% HON4D [3] 96.67% Max Margin Time Warping [16] 97.22% HOPC [42] 98.33% Proposed MMMP 100.0% of each part by a magnitude based norm, and utilizing a soft part selection by a sparsity inducing norm.”
Histogram of Oriented Principal Components for Cross-View Action Recognition (2014, methodology): “HOPC is extracted at a point by projecting all three eigenvectors of the pointcloud within a local spatio-temporal support volume, scaled by their corresponding eigenvalues, on the vertices of a regular dodecahedron.”
HOPC: Histogram of Oriented Principal Components of 3D Pointclouds for Action Recognition (2014, background): “Action recognition methods based on depth maps can be divided into holistic [19,21,13,38,29] and local approaches [32,35,11,31].”
RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, methodology): “For continuous gesture recognition, Wang et al. [118] first segmented the continuous depth sequence into segmented sequences using quantity of movement (QOM) [119], and then adopted improved DMM (IDMM) to encode the dynamics of depth sequences into texture images for large-scale continuous gesture r”
Scene Flow to Action Map: A New Representation for RGB-D Based Action Recognition with Convolutional Neural Networks (2017, methodology): “The other methods, WHDMM+SDI [68, 3], extracted features and conducted classification with ConvNets from depth and RGB individually and adopted multiply- score fusion for final recognition.”
A novel hierarchical framework for human action recognition (2016, methodology): “The widely-used features 23 include sampled 3D points from silhouettes [6, 7], histograms of oriented 24 gradients [8], histogram of oriented 4D normals [9], histogram of oriented 25 principal components [10], etc.”
Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks (2016, methodology): “rmation over conventional RGB video, e.g. being insensitive to illumination changes and reliable to estimate body silhouette and skeleton [23]. Since the ﬁrst work [24] reported in 2010, many methods [25]–[29] have been proposed using speciﬁcally hand-crafted feature descriptors extracted from depth”
Action Classification with Locality-Constrained Linear Coding (2014, neutral): “[9] added temporal derivative of 2D projections to get Depth Motion Maps (DMM).”
Improving Human Action Recognition Using Fusion of Depth Camera and Inertial Sensors (2015, methodology): “[7] proposed to project depth frames onto three orthogonal Cartesian planes for the purpose of characteriz ing an action.”
Motion Recognition Employing Multiple Kernel Learning of Fisher Vectors Using Local Skeleton Features (2015, methodology): “Along with this change, various modalities such as skeleton[19][23][7], color, depth[14][22], silhouette[9][2] and space-time occupancy[17][18] are used as features for action recognition.”
HON4D: Histogram of Oriented 4D Normals for Activity Recognition from Depth Sequences (2013, methodology): “Finally, we also compare with the motion map method from [26].”
Joint Angles Similarities and HOG2 for Action Recognition (2013, unknown): “[21] employ a HOG [4] feature extraction after projecting the depth maps into three orthogonal planes and accumulating the depth maps throughout each gesture into a motion image.”
A Comprehensive Survey of Vision-Based Human Action Recognition Methods (2019, background): “[68] proposed a depth motion map (DMM) to project and compress the spatiotemporal depth structure from the front, side, and upper views to form three motion history maps.”
Accurate 3D action recognition using learning on the Grassmann manifold (2015, methodology): “Yang et al.[33] employ Histograms of Oriented Gradients features (HOG) computed from Depth Motion Maps (DMM), as the representation of an action sequence.”
Evolutionary joint selection to improve human action recognition with RGB-D devices (2014, methodology): “Yang et al. (2012) propose a method to recognise human actions from sequences of depth maps.”
Ieee Transactions on Pattern Analysis and Machine Inteligence 1 Super Normal Vector for Human Activity Recognition with Depth Cameras (unknown): “Our previous work on depth motion maps [49] stacked differences between consecutive projected depth maps from three orthogonal views.”