Real-time human action recognition based on depth motion maps

By Kui Liu, Nasser Kehtarnavaz. Journal of Real-Time Image Processing, 2013

312 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/e0b874137e89916ed2f757c58973526c7bead359

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

Improving Human Action Recognition Using Fusion of Depth Camera and Inertial Sensors (2015, background): “For each projection view, the absolute difference between two consecutive projected maps is accumulated through an entire depth video sequence forming a so called depth motion map (DMM) [30].”
A discussion on the validation tests employed to compare human action recognition methods using the MSR Action3D dataset (2014, background): “Other authors repeat the test 100 times instead of 10 [60,61], and even 200 times [25] (see Table 6).”
UTD-MHAD: A multimodal dataset for human action recognition utilizing a depth camera and a wearable inertial sensor (2015, background): “A brief explanation of these features is given here, more details appear in [18].”
A survey of depth and inertial sensor fusion for human action recognition (2015, background): “…major feature representation techniques for human action recognition based on depth sequences include a bag of 3D points [42], projected depth maps [15, 18, 75], space-time occupancy patterns [63, 64], spatio-temporal depth cuboid [69], surface normals [48, 74], and skeleton joints [25, 62, 73].”
A Comprehensive Survey of Vision-Based Human Action Recognition Methods (2019, methodology): “In an RGBD video, the depth data can be seen as a space-time structure composed of depth information.”
Low-Rank Tensor Learning with Discriminant Analysis for Action Classification and Image Recovery (2014, methodology): “Experiment setting 2 Here we use the same conditions as Chen et al. (Chen, Liu, and Kehtarnavaz 2013).”
Hierarchical recurrent neural network for skeleton based action recognition (2015, methodology): “[3] and Vemula-palli et al .”
Fusion of Inertial and Depth Sensor Data for Robust Hand Gesture Recognition (2014, background): “The application of depth sensors, in particular Kinect [9], has been steadily growing for body movement measurements and recognition.”
Human Action Recognition From Various Data Modalities: A Review (2020, methodology): “to the success of DMM, several other HAR methods [260], [261], [262] were also proposed based on it.”