A Survey on Human Motion Analysis from Depth Data

By Mao Ye, Qing Zhang, Liang Wang, Jiejie Zhu, Ruigang Yang, Juergen Gall. 2013

243 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Human-Computer Interaction

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

1. Jun Liu
2. G. Wang
3. Luc Van Gool
4. Wanqing Li
5. Hossein Rahmani
6. Pichao Wang
7. Amir Shahroudy
8. Dacheng Tao

In Human-Computer Interaction

1. Pichao Wang
2. Wanqing Li
3. Jun Liu
4. Philip O. Ogunbona
5. Zhimin Gao
6. G. Wang
7. Amir Shahroudy
8. Hossein Rahmani

Citations in the corpus

• NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis (2016, background): “For a more extensive list of current 3D activity analysis datasets and methods, readers are referred to these survey papers [47, 1, 5, 12, 21, 45, 3].”
• NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding (2019, background): “Human actions can be represented by a combination of the movements of different body parts [29], [30], and the importance degrees of body parts’ motion are not equal for recognizing different action categories.”
• Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, background): “Several earlier surveys were also published to review methods to recognize human poses, motions, gestures, and activities [37], [38], [39], [40], [41], [42], [43], [44], [45], [46], [47], [48], as well as their applications [49], [50].”
• RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, background): “Several survey papers have summarized the research on human motion recognition using RGB-D data [14, 166, 3, 16, 172, 28, 100, 46].”
• Skeleton-Based Human Action Recognition With Global Context-Aware Attention LSTM Networks (2017, background): “motions of skeletal joints in 3D space [11], [12].”
• Cross-Modal Knowledge Distillation for Action Recognition (2019, background): “There is a large body of works on action recognition from 3D human pose data [13].”
• Embodied hands (2017, methodology): “This interest is increasing [Supančič III et al. 2015; Ye et al. 2013] in light of the recent advancements in consumer RGB-D sensors and virtual reality [Hamer et al. 2009; Leap 2017; Melax et al. 2013; Oberweger et al. 2015; Oikonomidis et al. 2011a, 2012; Romero et al. 2013; Schmidt et al. 2014;…”
• Efficient Pose-Based Action Recognition (2014, background): “The recent advances in both depth sensors and human pose estimation have recently rekindled interest in high level human representations for action and behavior analysis [13].”
• 3D-based Deep Convolutional Neural Network for action recognition with depth sequences (2016, background): “There are also many studies on action recognition using deep learning based on either 2D color image sequences [14, 15, 16, 17] or 3D depth video sequences [18, 19].”
• Accurate 3D action recognition using learning on the Grassmann manifold (2015, background): “Recent surveys [26, 27] are re-164 porting works on depth videos.”
• Capturing Hands in Action Using Discriminative Salient Points and Physics Simulation (2015, background): “With recent technology advancements of consumer RGB-D sensors, the research interest in this topic has increased in the last few years (Tompson et al, 2014; Ye et al, 2013).”
• Learning Clip Representations for Skeleton-Based 3D Action Recognition (2018, background): “2812099 changes [17], with human actions described as movements of the skeleton joints [18].”
• Fusion4D (2016, background): “However, despite remarkable progress in offline performance capture over the years (see [Theobalt et al. 2010; Ye et al. 2013; Smolic 2011] for surveys), real-time approaches have been incredibly rare, especially when considering high quality reconstruction of general shape and motion i.”
• Hierarchical recurrent neural network for skeleton based action recognition (2015, background): “A fully connected layer and a softmax layer are performed on the final representation to classify the actions. man skeleton joints in the 3D space [37].”
• Survey on 3D Hand Gesture Recognition (2016, background): “Considered as a kind of human motion [27] in our daily life, hand gestures have been investigated by human motion analysis [28]–[30], which pay more attention to full-body human poses and activities [31].”
• 3D Human pose estimation: A review of the literature and analysis of covariates (2016, background): “[27] published surveys on this topic recently which cover in detail the recent advances and trends in the field.”
• A Comprehensive Survey of Vision-Based Human Action Recognition Methods (2019, methodology): “[15], who summarized human action recognition methods using depth data and Presti et al.”
• Skeletal Quads: Human Action Recognition Using Joint Quadruples (2014, background): “For a recent detailed survey on human motion analysis from depth data, we refer the reader to [1], [22].”