A metrological characterization of the Kinect V2 time-of-flight camera

Corti, Andrea; Giancola, Silvio; Mainetti, Giacomo; Sala, R.

doi:10.1016/j.robot.2015.09.024

Cited by 116 publications

(67 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Kinect V2 is built upon the ToF principle, which means that it is a range finder with active IR illumination. The IR illumination follows a light cone distribution [35], which is not uniformly distributed. Thus, less-well-illuminated areas (e.g., corners, far objects) deliver inaccurate depth measurements.…”

Section: Discussionmentioning

confidence: 99%

“…The stereo camera and structured light camera use parallax theory to calculate depth, while the ToF camera is based on a beam distance measurement principle, calculating the distance from the travel time of a modulated beam between sensor and object. Among the mainstream ToF camera models, including Microsoft Kinect V2 [57], CubeEye [58], SwissRanger SR4000 [58], and PMD CamCube [59], the Kinect V2 is selected as the sensor array component in this paper for its wider FOV, higher resolution, longer ranging [35], and easier accessibility.…”

Section: Rgb-d Camera Array System Setupmentioning

confidence: 99%

“…The main reason is that the measurements derived from SL/ToF based RGB-D cameras are distorted by several phenomena. Considering especially the ToF based KinectV2 used in this paper, the analysis of related error sources is reported in existing surveys [35,36]. The IR and color optical sensors inside the Kinect V2 could be modeled using the pinhole camera model and solved by well-established RGB camera calibration methods [9,34,37].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Calibrate Multiple Consumer RGB-D Cameras for Low-Cost and Efficient 3D Indoor Mapping

et al. 2018

View full text Add to dashboard Cite

Abstract:Traditional indoor laser scanning trolley/backpacks with multi-laser scanner, panorama cameras, and an inertial measurement unit (IMU) installed are a popular solution to the 3D indoor mapping problem. However, the cost of those mapping suits is quite expensive, and can hardly be replicated by consumer electronic components. The consumer RGB-Depth (RGB-D) camera (e.g., Kinect V2) is a low-cost option for gathering 3D point clouds. However, because of the narrow field of view (FOV), its collection efficiency and data coverages are lower than that of laser scanners. Additionally, the limited FOV leads to an increase of the scanning workload, data processing burden, and risk of visual odometry (VO)/simultaneous localization and mapping (SLAM) failure. To find an efficient and low-cost way to collect 3D point clouds data with auxiliary information (i.e., color) for indoor mapping, in this paper we present a prototype indoor mapping solution that is built upon the calibration of multiple RGB-D sensors to construct an array with large FOV. Three time-of-flight (ToF)-based Kinect V2 RGB-D cameras are mounted on a rig with different view directions in order to form a large field of view. The three RGB-D data streams are synchronized and gathered by the OpenKinect driver. The intrinsic calibration that involves the geometry and depth calibration of single RGB-D cameras are solved by homography-based method and ray correction followed by range biases correction based on pixel-wise spline line functions, respectively. The extrinsic calibration is achieved through a coarse-to-fine scheme that solves the initial exterior orientation parameters (EoPs) from sparse control markers and further refines the initial value by an iterative closest point (ICP) variant minimizing the distance between the RGB-D point clouds and the referenced laser point clouds. The effectiveness and accuracy of the proposed prototype and calibration method are evaluated by comparing the point clouds derived from the prototype with ground truth data collected by a terrestrial laser scanner (TLS). The overall analysis of the results shows that the proposed method achieves the seamless integration of multiple point clouds from three Kinect V2 cameras collected at 30 frames per second, resulting in low-cost, efficient, and high-coverage 3D color point cloud collection for indoor mapping applications.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Rgb-d Camera Array System Setupmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Calibrate Multiple Consumer RGB-D Cameras for Low-Cost and Efficient 3D Indoor Mapping

et al. 2018

View full text Add to dashboard Cite

show abstract

“…structured light for Kinect v1 and TOF for Kinect v2, are based on IR signals. These algorithms may be affected by errors if the monitored area is characterized by a reflective surface [72], and this uncertainty in the evaluation of depth data can generate an error in the joint estimation process [73]. Even when some corrections may be required, depth data extracted from Kinect can be used to design algorithms with performance comparable to gold-standard systems, as discussed in [74].…”

Section: Referencesmentioning

confidence: 99%

Radar and RGB-Depth Sensors for Fall Detection: A Review

et al. 2017

View full text Add to dashboard Cite

Abstract-This paper reviews recent works in the literature on the use of systems based on Radar and RGB-Depth sensors for fall detection, and discusses outstanding research challenges and trends related to this research field. Systems to detect reliably fall events and promptly alert carers and first responders have gained significant interest in the past few years in order to address the societal issue of an increasing number of elderly people living alone, with the associated risk of them falling and the consequences in terms of health treatments, reduced well-being, and costs. The interest in radar and RGB-D sensors is related to their capability to enable contactless and non-intrusive monitoring, which is an advantage for practical deployment and users' acceptance and compliance, compared with other sensor technologies such as video-cameras, or wearables. Furthermore, the possibility of combining and fusing information from heterogeneous types of sensors is expected to improve the overall performance of practical fall detection systems. Researchers from different fields can benefit from multidisciplinary knowledge and awareness of the latest developments in radar and RGB-D sensors that this paper is discussing.

show abstract

“…Also, as using IR light source, they can mitigate the effect of ambient light. Among the Microsoft Kinect v2, CubeEye and PMD CamCube of the main types of TOF cameras, the Kinect v2 is selected as sensor array components for its wider FOV, higher resolution and longer ranging (Corti et al, 2016) Compared to outdoor environment, the indoor data collection with depth camera is often impeded by more fend, shorter distance and smaller space, therefore, both horizontal movement and vertical pitch are required to make data complete, which lead to higher risk of tracking lost and more data processing workload. Besides, most RGB-D reconstruct method use the visual odometry to build relatively transformation between frames, which does not work properly in no texture region or regions with repetitive textures which are quite common for indoor images (Yousif et al, 2014).…”

Section: Hardwarementioning

confidence: 99%

Low Cost and Efficient 3d Indoor Mapping Using Multiple Consumer RGB-D Cameras

Chen¹,

Wang²,

Song³

2016

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Commission I, WG I/3KEY WORDS: Indoor Mapping, RGB-D Camera, Kinect, Calibration ABSTRACT:Driven by the miniaturization, lightweight of positioning and remote sensing sensors as well as the urgent needs for fusing indoor and outdoor maps for next generation navigation, 3D indoor mapping from mobile scanning is a hot research and application topic. The point clouds with auxiliary data such as colour, infrared images derived from 3D indoor mobile mapping suite can be used in a variety of novel applications, including indoor scene visualization, automated floorplan generation, gaming, reverse engineering, navigation, simulation and etc. State-of-the-art 3D indoor mapping systems equipped with multiple laser scanners product accurate point clouds of building interiors containing billions of points. However, these laser scanner based systems are mostly expensive and not portable. Low cost consumer RGB-D Cameras provides an alternative way to solve the core challenge of indoor mapping that is capturing detailed underlying geometry of the building interiors. Nevertheless, RGB-D Cameras have a very limited field of view resulting in low efficiency in the data collecting stage and incomplete dataset that missing major building structures (e.g. ceilings, walls). Endeavour to collect a complete scene without data blanks using single RGB-D Camera is not technic sound because of the large amount of human labour and position parameters need to be solved. To find an efficient and low cost way to solve the 3D indoor mapping, in this paper, we present an indoor mapping suite prototype that is built upon a novel calibration method which calibrates internal parameters and external parameters of multiple RGB-D Cameras. Three Kinect sensors are mounted on a rig with different view direction to form a large field of view. The calibration procedure is three folds: 1, the internal parameters of the colour and infrared camera inside each Kinect are calibrated using a chess board pattern, respectively; 2, the external parameters between the colour and infrared camera inside each Kinect are calibrated using a chess board pattern; 3, the external parameters between every Kinect are firstly calculated using a pre-set calibration field and further refined by an iterative closet point algorithm. Experiments are carried out to validate the proposed method upon RGB-D datasets collected by the indoor mapping suite prototype. The effectiveness and accuracy of the proposed method is evaluated by comparing the point clouds derived from the prototype with ground truth data collected by commercial terrestrial laser scanner at ultra-high density. The overall analysis of the results shows that the proposed method achieves seamless integration of multiple point clouds form different RGB-D cameras collected at 30 frame per second.

show abstract

A metrological characterization of the Kinect V2 time-of-flight camera

Cited by 116 publications

References 19 publications

Calibrate Multiple Consumer RGB-D Cameras for Low-Cost and Efficient 3D Indoor Mapping

Calibrate Multiple Consumer RGB-D Cameras for Low-Cost and Efficient 3D Indoor Mapping

Radar and RGB-Depth Sensors for Fall Detection: A Review

Low Cost and Efficient 3d Indoor Mapping Using Multiple Consumer RGB-D Cameras

Contact Info

Product

Resources

About