This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination. IEEE TRANSACTIONS ON CYBERNETICS 1 Enhanced Computer…

Subfields: Computer Vision and Pattern Recognition

Citations in the corpus

• NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis (2016, background): “Recent development of depth sensors enabled us to obtain effective 3D structures of the scenes and objects [13].”
• NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding (2019, neutral): “T HE development of depth sensors, e.g. , Microsoft Kinect, Intel RealSense, and Asus Xtion, enables us to obtain effective 3D structure information of the objects and scenes [1].”
• An Incremental Self-Organizing Architecture for Sensorimotor Learning and Prediction (2017, methodology): “Moreover, it offers an efficient and markerless body tracking method [47] which makes the interface less invasive.”
• Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos (2016, background): “Range sensors provide depth information of the scene and objects, which helps in solving problems that are considered hard for RGB inputs [15].”
• RGB-D datasets using microsoft kinect or similar sensors: a survey (2016, background): “RGB-D images/videos can facilitate a wide range of application areas, such as computer vision, robotics, construction and medical imaging [33].”
• Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, background): “[17] described the Kinect sensor and its general application in computer vision and machine intelligence.”
• Skeleton-Based Online Action Prediction Using Scale Selection Network (2019, methodology): “The 3D skeleton information can be easily and effectively acquired in real-time with the low-cost depth sensors [8], such as Microsoft Kinect and Asus Xtion.”
• Skeleton-Based Human Action Recognition With Global Context-Aware Attention LSTM Networks (2017, background): “We evaluate our proposed method on the NTU RGB+D [52], UT-Kinect [44], SYSU-3D [68], SBU-Kinect Interaction [69], and Berkeley MHAD [70] datasets.”
• Interpretable 3D Human Action Analysis with Temporal Convolutional Networks (2017, background): “Even without the context information and visual cues, early work [17] in biological perception and more recent methods [9, 10, 31] provide strong evidence that encoding humans as a 3D skeleton yields both a discriminative and a robust representation for activity analysis.”
• Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks (2016, background): “nd low-cost depth sensors such as MS Kinect sensors, human action recognition from RGB-D (Red, Green, Blue and Depth) data has attracted increasing attention and many applications have been developed [22] in recent years, due to the advantages of depth information over conventional RGB video, e.g. b”
• Self-organizing neural integration of pose-motion features for human action recognition (2015, background): “In the last half decade, the use of low-cost depth sensing devices such as the Microsoft Kinect and ASUS Xtion has led to a great number of vision-based applications using depth information instead of, or in combination with, brightness and color information (for a review see Han et al., 2013).”
• Impact assessment of reinforced learning methods on construction workers' fall risk behavior using virtual reality (2019, background): “It can be used for either detecting a user's motions or navigating in a virtual environment [22,39].”
• Kinect range sensing: Structured-light versus Time-of-Flight Kinect (2015, methodology): “[17] on the Kinect as well as to the survey on Time-of-Flight cameras by Kolb et al.”
• Working Together: A Review on Safe Human-Robot Collaboration in Industrial Environments (2017, background): “Hence, the study and application of this type of sensor have been the object of research such as [144], which presents a review of Kinect-based computer vision algorithms and applications.”
• Structure-Preserving Binary Representations for RGB-D Action Recognition (2016, background): “D sensors such as Kinect receive increasing attention in the computer vision community [1].”
• Local structure preserving discriminative projections for RGB-D sensor-based scene classification (2015, background): “Using Microsoft Kinect, researchers can easily achieve high-quality synchronized videos that possess both color and depth, which facilitates tasks previously hindered by tradition two-dimensional visual images.”
• Human Action Recognition by Shape Analysis of Motion Trajectories on Riemannian Manifold (2014, background): “A recent review of kinect-based computer vision applications can be found in [7].”
• Leveraging Hierarchical Parametric Networks for Skeletal Joints Based Action Segmentation and Recognition (2014, background): “…such joint positions from an image sequence is a difficult task and the traditionally vision community used MoCap systems for pose tracking until the advent of Kinect [25, 9] when consumer price device can be readily available for human body joints extraction in real time with reasonable accuracy.”