3D with Kinect

By Jan Smisek, Michal Jancosek, Tomás Pajdla. IEEE International Conference on Computer Vision, 2011

615 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Geology

View Paper: https://www.semanticscholar.org/paper/7fc96e218f20ad68b9a83d869294a943f974da43

How researchers see this paper

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

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Geology

Citations in the corpus

ConvNets-Based Action Recognition from Depth Maps through Virtual Cameras and Pseudocoloring (2015, neutral): “For Kinect-v1 cameras, fx = fy = 580 [9].”
The role of RGB-D benchmark datasets: an overview (2013, background): “A tabular overview about the corresponding publications for each dataset can found in Table 1.”
BigBIRD: A large-scale 3D database of object instances (2014, background): “Although this is a relatively well-studied problem [30], [25], obtaining strong results is still nontrivial due to multiple details about the Carmines that are not well documented.”
Accuracy and robustness of Kinect pose estimation in the context of coaching of elderly population (2012, positive): “The 3D depth accuracy of the Kinect camera has been evaluated quite extensively [3], [4] showing that after calibration, the camera can provide accuracy of depth reconstruction in the order of 1-4 cm at the range of 1-4 m.”
Unsupervised Intrinsic Calibration of Depth Sensors via SLAM (2013, neutral): “The works of Smisek et al. [19] and Herrera C. et al. [10] discuss vertical banding in the depth distortion, which we recover here in all the sensors we tested.”
Elastic Fragments for Dense Scene Reconstruction (2013, background): “The recent commercialization of consumergrade range cameras promises to enable almost anyone to reliably create detailed three-dimensional models of their environments [27, 16, 7, 35].”
Action Recognition From Depth Maps Using Deep Convolutional Neural Networks (2016, positive): “For Kinect-V1 cameras, fx = fy = 580 [24].”
A benchmark for the evaluation of RGB-D SLAM systems (2012, methodology): “A detailed analysis of Kinect calibration and the resulting accuracy has been recently published by Smisek et al. [43].”
Joint Depth and Color Camera Calibration with Distortion Correction (2012, background): “[13] improves the reprojection error for data sets A1 and A2.”
Kinect range sensing: Structured-light versus Time-of-Flight Kinect (2015, methodology): “[47] present a geometric method to calibrate the systematic error of the Kinect.”
Modeling Kinect Sensor Noise for Improved 3D Reconstruction and Tracking (2012, background): “Researchers have begun to explore the sensor noise characteristics of the Kinect [5, 9] and shown an increased variance in reported depth as the distance between the sensor and observed surface increases.”
Range-Sample Depth Feature for Action Recognition (2014, background): “58 [mm] (z is depth with unit meter according to [15]).”
Nonparametric Calibration for Depth Sensors (2015, background): “stated [9] different Kinect devices shows different radial distortion patterns.”
Deep Bilinear Learning for RGB-D Action Recognition (2018, background): “Firstly, it can capture depth maps, which was shown useful for geometric modeling [32].”
Range sensor and silhouette fusion for high-quality 3D Scanning (2015, methodology): “While KinectFusion-style approaches can perform well in the “concavity and low-texture” regime, they fail when working with objects that are translucent, transparent, or highly specular; the visual hull can provide better shape estimates here [22], [26].”