Robust human activity recognition from depth video using spatiotemporal multi-fused features

By Ahmad Jalal, Yeonho Kim, Yong-Joong Kim, S. Kamal, Daijin Kim. Pattern Recognition, 2017

362 citations recorded by the source corpus.

How researchers see this paper

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

Sensor-based and vision-based human activity recognition: A comprehensive survey (2020, methodology): “HAR is applied in surveillance systems [8,9] , behavior analysis [10] , gesture recognition [11–13] , patient monitoring systems [14,15] , ambient assisted living (AAL) [16,17] , and a variety of healthcare systems [18,19] that involve direct interaction or indirect interaction between human and…”
A Comprehensive Survey of Vision-Based Human Action Recognition Methods (2019, background): “[80] merged spatiotemporal features in RGB data and depth data, and Ni et al.”
Human Action Recognition From Various Data Modalities: A Review (2020, methodology): “[378] extracted multi-fused features consisting of four sets of joint features from skeleton sequences and one set of body shape features from depth sequences, and then adopted HMM for recognition.”