Real time action recognition using histograms of depth gradients and random decision forests

By Hossein Rahmani, Arif Mahmood, Du Q. Huynh, Ajmal Saeed Mian. 2014

116 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biomedical Engineering, Computer Vision and Pattern Recognition, Signal Processing

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 Biomedical Engineering

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis (2016, methodology): “In [27] random decision forests were utilized for learning and feature pruning over a combination of depth and skeleton-based features.”
NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding (2019, methodology): “In [58], random decision forests were utilized for learning and feature pruning over a combination of depth and skeleton-based features.”
Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos (2016, background): “The work of [46] combined different spatio-temporal depth and skeleton based gradient features and applied a random decision forest for action classification.”
Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, methodology): “[133] Joint Movement Volumes Stat Lowlv Hand X”
HOPC: Histogram of Oriented Principal Components of 3D Pointclouds for Action Recognition (2014, methodology): “Action recognition methods based on depth maps can be divided into holistic [19, 21, 13, 38, 29] and local approaches [32, 35, 11, 31].”
Skeleton-Based Online Action Prediction Using Scale Selection Network (2019, background): “As a result, activity analysis with 3D skeleton data becomes a popular domain of research [9], [10], [11], [12], [13], [14], [15], [16], [17] thanks to its succinctness, high level representation, and robustness against variations in viewpoints, illumination, clothing textures, and”
Skeleton-Based Human Action Recognition With Global Context-Aware Attention LSTM Networks (2017, neutral): “nition have been proposed [29], [30], [31], [32], [33], [34], [35], [36], [37], [38], [39], [40], [41].”
Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates (2017, neutral): “Skeleton-based action recognition has been explored in different aspects in recent years [40], [41], [42], [43], [44], [45], [46], [47], [48], [49], [50], [51], [52], [53], [54], [55], [56], [57].”
Action Classification with Locality-Constrained Linear Coding (2014, methodology): “Our algorithm outperformed existing state-of-the-art algorithms (Table I).”
Recognizing Actions in 3D Using Action-Snippets and Activated Simplices (2016, background): “HON4D (Oreifej and Liu 2013) 82.15 Rahmani et al. (Rahmani et al. 2014) 82.70 Tran et al. (Tran and Ly 2013) 84.54 Our Approach 91.40 and “draw circle” actions, which are indeed similar.”
A discussion on the validation tests employed to compare human action recognition methods using the MSR Action3D dataset (2014, unknown): “Only three works perform this test [8,49,52].”
Human Action Recognition From Various Data Modalities: A Review (2020, methodology): “Therefore, early methods [351], [352] have attempted to fuse hand-crafted features extracted from both the skeleton and the depth sequences for more accurate HAR.”
Mining Mid-Level Features for Action Recognition Based on Effective Skeleton Representation (2014, unknown): “[21] proposed an algorithm combining the discriminative information from depth maps as well as from 3D joints positions for action recognition.”
Learning Action Recognition Model from Depth and Skeleton Videos (2017, methodology): “[19] proposed a set of random forests to fuse the spatiotemporal depth and joints features.”
3D Action Recognition from Novel Viewpoints (2016, methodology): “For spatio-temporal representation, we propose group sparse Fourier Temporal Pyramid which robustly encodes the action specific most discriminative output features of the proposed human pose model.”
A Review of Human Activity Recognition Methods (2015, unknown): “Rahmani et al. (2014) trained a random decision forest (RDF) (Ho, 1995) and applied a joint representation of depth information and 3D skeletal positions for identifying human actions in real time.”
Learning a non-linear knowledge transfer model for cross-view action recognition (2015, background): “Figure 1: Existing cross-view action recognition techniques [11, 12, 19, 33, 40] connect source and target views with a set of linear transformations that are unable to capture the non-linear manifolds on which real actions lie.”
Bio-inspired predictive orientation decomposition of skeleton trajectories for real-time human activity prediction (2015, methodology): “By computing joint displacement vectors and joint movement volume, the representation in [11] is used to efficiently recognize activities from skeleton data.”