A State of the Art Report on Kinect Sensor Setups in Computer Vision

Berger, Kai; Meister, Sarah; Nair, Rahul; Kondermann, Daniel

doi:10.1007/978-3-642-44964-2_12

Cited by 19 publications

(6 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2.3 we further refer to some key papers that deal with specific characteristics of SL and ToF range data. Additionally, we refer the reader to the surveys of Berger et al [3] and Han et al [17] on the Kinect SL as well as to the survey on Time-of-Flight cameras by Kolb et al [28]. Kuhnert and Stommel [30] demonstrate a first integration of ToF-and stereo cameras.…”

Section: Introduction and Related Workmentioning

confidence: 99%

Kinect range sensing: Structured-light versus Time-of-Flight Kinect

Sarbolandi

Lefloch

Kolb

2015

Computer Vision and Image Understanding

340

237

View full text Add to dashboard Cite

Recently, the new Kinect One has been issued by Microsoft, providing the next generation of real-time range sensing devices based on the Time-of-Flight (ToF) principle. As the first Kinect version was using a structured light approach, one would expect various differences in the characteristics of the range data delivered by both devices. This paper presents a detailed and in-depth comparison between both devices.In order to conduct the comparison, we propose a framework of seven different experimental setups, which is a generic basis for evaluating range cameras such as Kinect. The experiments have been designed with the goal to capture individual effects of the Kinect devices as isolatedly as possible and in a way, that they can also be adopted, in order to apply them to any other range sensing device. The overall goal of this paper is to provide a solid insight into the pros and cons of either device. Thus, scientists that are interested in using Kinect range sensing cameras in their specific application scenario can directly assess the expected, specific benefits and potential problem of either device.

show abstract

Section: Introduction and Related Workmentioning

confidence: 99%

Kinect range sensing: Structured-light versus Time-of-Flight Kinect

Sarbolandi

Lefloch

Kolb

2015

Computer Vision and Image Understanding

340

237

View full text Add to dashboard Cite

show abstract

“…It is necessary to solve certain problems like the position of the worker facing the sensor or lack of accuracy when a body part is hidden by an object or another part of the body. Recent studies try to solve these problems through the simultaneous use of several sensors placed in different sites (Asteriadis et al, 2013;Berger et al, 2013;Geiselhart et al, 2016;Zhang et al, 2012). However, the use of several sensors must deal with problems such as interference in the speckle patterns projected onto the scene or differences in the positions of the tracked joints of each sensor (Sarbolandi et al, 2015).…”

Section: Discussionmentioning

confidence: 99%

“…These situations are very common in real scenarios, where the worker could handle large objects that occult body parts to the camera, some part of the body could be behind other part or, simply, the worker moves outside the sensor field of view. Some researchers try to solve this problem using multiple sensors oriented at different angles relative to the tracked subject (Berger et al, 2013). On the other hand, body tracking may not accurately obtain lower body kinematic data (Yang et al, 2015), and joint rotations are not correctly captured or not captured at all for the peripheral limbs or the head.…”

Section: Introductionmentioning

confidence: 99%

Using RGB-D sensors and evolutionary algorithms for the optimization of workstation layouts

2017

View full text Add to dashboard Cite

RGB-D sensors can collect postural data in an automatized way. However, the application of these devices in real work environments requires overcoming problems such as lack of accuracy or body parts' occlusion. This work presents the use of RGB-D sensors and genetic algorithms for the optimization of workstation layouts. RGB-D sensors are used to capture workers' movements when they reach objects on workbenches. Collected data are then used to optimize workstation layout by means of genetic algorithms considering multiple ergonomic criteria. Results show that typical drawbacks of using RGB-D sensors for body tracking are not a problem for this application, and that the combination with intelligent algorithms can automatize the layout design process. The procedure described can be used to automatically suggest new layouts when workers or processes of production change, to adapt layouts to specific workers based on their ways to do the tasks, or to obtain layouts simultaneously optimized for several production processes.

show abstract

“…3D pose can be estimated from monocular images but making inferences about 3D kinematics from 2D images is a difficult problem and having additional depth information increases accuracy. The introduction of the Microsoft Kinect device was a breakthrough in the evolution of 3D human pose tracking algorithms and rehabilitation, whose (Kinect v1) features have been evaluated in [17][18][19] and a feasibility study for infant tracking was presented in [20]. However, limitations do exist.…”

Section: Related Workmentioning

confidence: 99%

Stereo 3D tracking of infants in natural play conditions

Shivakumar

Loeb

Bogen

et al. 2017

2017 International Conference on Rehabilitation Robotics (ICORR)

View full text Add to dashboard Cite

This paper describes the design and implementation of a multiple view stereoscopic 3D vision system and a supporting infant tracker pipeline to track limb movement in natural play environments and identify potential metrics to quantify movement behavior. So far, human pose estimation and tracking with 3D cameras has been focused primarily on adults and cannot be directly extended to infants because of differences in visual features such as shapes, sizes and appearance. With rehabilitation in mind, we propose a portable, compact, marker-less, low cost and high resolution 3D vision system and a tracking algorithm that exploits infant appearance attributes and depth information. This approach achieved a mean 3D tracking error of 8.21cm and a standard deviation of 8.75cm. We also identify two potential metrics for movement behavior analysis - approximate entropy and interaction events.

show abstract

A State of the Art Report on Kinect Sensor Setups in Computer Vision

Cited by 19 publications

References 62 publications

Kinect range sensing: Structured-light versus Time-of-Flight Kinect

Kinect range sensing: Structured-light versus Time-of-Flight Kinect

Using RGB-D sensors and evolutionary algorithms for the optimization of workstation layouts

Stereo 3D tracking of infants in natural play conditions

Contact Info

Product

Resources

About