On the Use of a Low-Cost Thermal Sensor to Improve Kinect People Detection in a Mobile Robot

Susperregi, Loreto; Sierra, Basilio; Castrillón, Modesto; Lorenzo, Javier; Martínez-Otzeta, José María; Lazkano, Elena

doi:10.3390/s131114687

Cited by 13 publications

(9 citation statements)

References 41 publications

(47 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [ 1 ], for example, the Kinect is used to observe work processes of different workers in a manufacturing cell, with depth data from the sensor used as input for machine learning algorithms that infer worker activity. In robot vision, Cho et al [ 2 ] use Kinect as an aide for a human-robot interface, and Susperrigi et al [ 3 ] use Kinect in conjunction with a thermal sensor to improve the detection of human presence. Rapid 3D modeling of objects is also benefiting from the use of the Kinect.…”

Section: Introductionmentioning

confidence: 99%

Statistical Analysis-Based Error Models for the Microsoft KinectTM Depth Sensor

Choo

Landau

DeVore

et al. 2014

Sensors

View full text Add to dashboard Cite

The stochastic error characteristics of the Kinect sensing device are presented for each axis direction. Depth (z) directional error is measured using a flat surface, and horizontal (x) and vertical (y) errors are measured using a novel 3D checkerboard. Results show that the stochastic nature of the Kinect measurement error is affected mostly by the depth at which the object being sensed is located, though radial factors must be considered, as well. Measurement and statistics-based models are presented for the stochastic error in each axis direction, which are based on the location and depth value of empirical data measured for each pixel across the entire field of view. The resulting models are compared against existing Kinect error models, and through these comparisons, the proposed model is shown to be a more sophisticated and precise characterization of the Kinect error distributions.

show abstract

Section: Introductionmentioning

confidence: 99%

Statistical Analysis-Based Error Models for the Microsoft KinectTM Depth Sensor

Choo

Landau

DeVore

et al. 2014

Sensors

View full text Add to dashboard Cite

show abstract

“…To significantly improve the robustness of people detection on mobile robots, light coding cameras have been combined with thermal sensors and mounted on the top of a mobile platform in [ 99 ], since humans have a distinctive thermal profile compared to non-living objects. This approach also combines classifiers created using supervised learning.…”

Section: Robot Guidance In Industrial Environmentsmentioning

confidence: 99%

Robot Guidance Using Machine Vision Techniques in Industrial Environments: A Comparative Review

Pérez

Rodríguez

et al. 2016

Sensors

259

122

View full text Add to dashboard Cite

In the factory of the future, most of the operations will be done by autonomous robots that need visual feedback to move around the working space avoiding obstacles, to work collaboratively with humans, to identify and locate the working parts, to complete the information provided by other sensors to improve their positioning accuracy, etc. Different vision techniques, such as photogrammetry, stereo vision, structured light, time of flight and laser triangulation, among others, are widely used for inspection and quality control processes in the industry and now for robot guidance. Choosing which type of vision system to use is highly dependent on the parts that need to be located or measured. Thus, in this paper a comparative review of different machine vision techniques for robot guidance is presented. This work analyzes accuracy, range and weight of the sensors, safety, processing time and environmental influences. Researchers and developers can take it as a background information for their future works.

show abstract

“…To combine thermal images with color images is effective to increase information. Several researches had presented human detection using a thermal camera with color camera [3,4], or with Kinect sensor [5]. Thermal image is also useful for 3D mapping of the building combining with color and depth information [6,7].…”

Section: Introductionmentioning

confidence: 99%

Compact coaxial thermal and color imaging system with silicon-glass hybrid lens

Takahata

Matsumoto

Shimoyama

2016

2016 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Detecting human is one of the most important functions of service robots assisting human lives. Thermal images are useful to detect human. Since the number of pixels of the thermal imagers is smaller than that of color imagers, thermal images get more useful combined with corresponding color images. In this paper, we propose a compact optical system to obtain both thermal and color images simultaneously. The key is to use a silicon-glass hybrid lens, with which visible and far-infrared light can be focused. The focused light was split by a silicon plate. The thermal and color images were taken by a thermal and color imager, respectively. We experimentally showed that the focal plane was tuned by the position of the lens keeping the correspondence of thermal and color images.

show abstract

On the Use of a Low-Cost Thermal Sensor to Improve Kinect People Detection in a Mobile Robot

Cited by 13 publications

References 41 publications

Statistical Analysis-Based Error Models for the Microsoft KinectTM Depth Sensor

Statistical Analysis-Based Error Models for the Microsoft KinectTM Depth Sensor

Robot Guidance Using Machine Vision Techniques in Industrial Environments: A Comparative Review

Compact coaxial thermal and color imaging system with silicon-glass hybrid lens

Contact Info

Product

Resources

About