• Corpus ID: 13215906

Kinect Depth Sensor Evaluation for Computer Vision Applications

@inproceedings{Andersen2012KinectDS,
  title={Kinect Depth Sensor Evaluation for Computer Vision Applications},
  author={Michael Riis Andersen and Thomas Jensen and Pavel Lisouski and Anders Krogh Mortensen and Mikkel Kragh Hansen and Torben Gregersen and Peter Ahrendt},
  year={2012}
}
This technical report describes our evaluation of the Kinect depth sensor by Microsoft for Computer Vision applications. [] Key Method The basic technique of the depth sensor is to emit an infrared light pattern (with an IR laser diode) and calculate depth from the reflection of the light at different positions (using a traditional IR sensitive camera). In this report, we perform an extensive evaluation of the depth sensor and investigate issues such as 3D resolution and precision, structural noise, multi…
Measuring depth accuracy in RGBD cameras
TLDR
The properties of the two depth sensors were investigated by conducting a series of experiments evaluating the accuracy of the sensors under various conditions, which shows the advantages and disadvantages of both Microsoft Kinect and Asus Xtion sensors.
Depth analysis of kinect v2 sensor in different mediums
TLDR
An analysis of the error in the depth measurement as well as calculation of Depth Entropy given by Kinect v2 sensor in different mediums has been done and the findings from error analysis are used to make an error compensation model which can correct depth at each pixel of the image.
Accuracy and reliability of optimum distance for high performance Kinect Sensor
TLDR
An investigation of the quality of depth data obtained by Kinect sensor is presented and a theoretical accuracy, precision and reliability analysis is presented, which provides an insight into the factors influencing the accuracy of the data.
Kinect Depth Data Calibration
TLDR
In this work, a modified wavelet filter is applied to reduce the nose of the signal that will be processed for the generation of depth data, and the accuracy is improved by three main steps, showing that a cleaner depth image can be obtained when the proposed filter is implemented.
On Maximum Geometric Finger-Tip Recognition Distance Using Depth Sensors
TLDR
The maximum distance that allows for recognizing finger-tips of an average-sized hand using three popular depth cameras using two geometric algorithms and a manual image analysis is explored, finding that recognition works reliably up to 1.5 m (SR4000, Kinect) and 2.4 m (Kinect 2).
Kinect unbiased
TLDR
It is shown how Kinect's Block Matching implementation is limited by the dot density of the pattern, and a significant spatial bias is introduced as a result, and an efficient approach to estimate the disparity of each dot is proposed, allowing us to produce a point cloud with better spatial resolution than Block matching algorithms.
Kinect Unleashed: Getting Control over High Resolution Depth Maps
TLDR
An algorithm is proposed that can estimate the output of Kinect from the raw infrared camera data and, using this algorithm, the internal reference calibration image from Kinect can be obtained and is used to model Kinect as a standard stereo camera, where alternative stereo algorithms can be used increasing the versatility of Kinect.
Kinect sensor depth data filtering
  • Vagiz R. DuseevA. Malchukov
  • Engineering
    2014 International Conference on Mechanical Engineering, Automation and Control Systems (MEACS)
  • 2014
TLDR
An approach based on the Kalman filter and image in-painting techniques in order to improve the temporal stability of the depth map and fill occlusion areas is proposed.
Environment-Dependent Depth Enhancement with Multi-modal Sensor Fusion Learning
  • K. TakamiTaeyoung Lee
  • Computer Science
    2018 Second IEEE International Conference on Robotic Computing (IRC)
  • 2018
TLDR
A new learning based multimodal sensing paradigm within a probabilistic framework to improve the depth image measurements of an RGB-D camera and laser range finder using convolutional neural network approximation within a Probabilistic inference framework is presented.
ROI Based Post Image Quality Assessment Technique on Multiple Localized Filtering Method on Kinect Sensor
TLDR
The ROI Image Quality Assessment model is used to measure image quality on Kinect sensor capture result used in Mobile HD Robot after applying Multiple Localized Filtering Technique, and there is no effect on the image quality generated by the sensor.
...
...

References

SHOWING 1-9 OF 9 REFERENCES
Accuracy analysis of kinect depth data
TLDR
Experimental results show that the random error of depth measurement increases with increasing distance to the sensor, and ranges from a few millimetres up to about 4 cm at the maximum range of the sensor.
Kind of static method and system for object reconstruction
TLDR
A method and system for reconstruction static objects, applied to the field of graphic image processing techniques, can be successfully rebuilt static objects when the depth data collected by the depth camera is missing or damaged.
Evaluation of the Kinect™ sensor for 3-D kinematic measurement in the workplace.
  • T. Dutta
  • Computer Science
    Applied ergonomics
  • 2012
Comparative Evaluation of Range Sensor Accuracy in Indoor Environments
3D range sensing is one of the important topics in robotics, as it is often a component in vital autonomous subsystems like collision avoidance, mapping and semantic perception. The development of ...
Markerless Motion Capture using multiple Color-Depth Sensors
TLDR
This work systematically evaluates the concurrent use of one to four Kinects, including calibration, error measures and analysis, and presents a time-multiplexing approach on reducing or mitigating the detrimental effects of multiple active light emitters, thereby allowing motion capture from all angles.
Analysis of kinect for mobile robots
  • Analysis of kinect for mobile robots
  • 2011
Analysis of kinect for mobile robots. Technical report, Department of Electrical Engineering, Technical University of Denmark, march
  • Department of Engineering Aarhus University Edison, Finlandsgade
  • 2011
Finlandsgade 22 8200 Aarhus N Denmark Tel
  • Finlandsgade 22 8200 Aarhus N Denmark Tel