Fusion of information from multiple Kinect sensors for 3D object reconstruction

Ruchay, Alexey; Dorofeev, Konstantin; Колпаков, В. И.

doi:10.18287/2412-6179-2018-42-5-898-903

Cited by 27 publications

(8 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…More complicated applications for analysis of complex human movement sequences require to use multiple cameras to capture orthogonal views of the same subject in order to extract the motion information and assure an objective evaluation of the training progress. For example, the studies have reported the use of two [16], three [31,65,66], four [44,51], or even five [39] Kinect sensors for estimating joint positions.…”

Section: Related Workmentioning

confidence: 99%

Multiple Kinect based system to monitor and analyze key performance indicators of physical training

Ryselis

Petkus²,

Blažauskas

et al. 2020

Hum. Cent. Comput. Inf. Sci.

View full text Add to dashboard Cite

Using a single Kinect device for human skeleton tracking and motion tracking lacks of reliability required in sports medicine and rehabilitation domains. Human joints reconstructed from non-standard poses such as squatting, sitting and lying are asymmetric and have unnatural lengths while their recognition error exceeds the error of recognizing standard poses. In order to achieve higher accuracy and usability for practical smart health applications we propose a practical solution for human skeleton tracking and analysis that performs the fusion of skeletal data from three Kinect devices to provide a complete 3D spatial coverage of a subject. The paper describes a novel data fusion algorithm using algebraic operations in vector space, the deployment of the system using three Kinect units, provides analysis of dynamic characteristics (position of joints, speed of movement, functional working envelope, body asymmetry and the rate of fatigue) of human motion during physical exercising, and evaluates intra-session reliability of the system using test–retest reliability metrics (intra-class correlation, coefficient of variation and coefficient of determination). Comparison of multi-Kinect system vs single-Kinect system shows an improvement in accuracy of 15.7%, while intra-session reliability is rated as excellent.

show abstract

Section: Related Workmentioning

confidence: 99%

Multiple Kinect based system to monitor and analyze key performance indicators of physical training

Ryselis

Petkus²,

Blažauskas

et al. 2020

Hum. Cent. Comput. Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…Nowadays 3D high-quality model of real objects are needed in various areas such as medicine, agriculture, architecture, engineering, industrial metrology, cultural heritage preservation and restoration [1,2,3]. Accurate 3D object reconstruction is an important aspect for scene understanding, object retrieval, object tracking, object recognition, visualization and virtual maintenance [4,5,6].…”

Section: Introductionmentioning

confidence: 99%

Accuracy analysis of surface reconstruction from point clouds

Ruchay

Dorofeev

Kalschikov

et al. 2020

2020 International Conference on Information Technology and Nanotechnology (ITNT)

View full text Add to dashboard Cite

In this paper, we analyze the accuracy of surface reconstruction using point clouds. Various methods of surface reconstruction are tested and compared with respect to the reconstruction accuracy using real data. In order to improve the accuracy of 3D object reconstruction, an efficient method of surface reconstruction is designed. The presented results show an improvement in the accuracy of surface reconstruction using the proposed algorithm. Секция: Обработка изображений и дистанционное зондирование Земли VI Международная конференция и молодёжная школа «Информационные технологии и нанотехнологии» (ИТНТ-2020

show abstract

“…In this paper, we use for three-dimensional facial reconstruction and face alignment a resampling method based on a non-rigid ICP algorithm [8][9][10][11][12][13][14][15][16][17] instead of network-based methods. First, we convert a 3D scan to the "canonical form".…”

Section: Introductionmentioning

confidence: 99%

Facial recognition and 3D non-rigid registration

Makovetskii

Kober

Voronin

et al. 2020

2020 International Conference on Information Technology and Nanotechnology (ITNT)

View full text Add to dashboard Cite

The most efficient tool for human face recognition is neural networks. However, the result of recognition can be spoiled by facial expressions and other deviation from canonical face representation. In this paper, we propose a resampling method of human faces represented by 3D point clouds. The method is based on non-rigid Iterative Closest Point (ICP) algorithm. To improve the facial recognition performance we use a combination of the method and convolutional neural network (CNN). Computer simulation results are provided to illustrate the performance of the proposed approach.

show abstract

Fusion of information from multiple Kinect sensors for 3D object reconstruction

Cited by 27 publications

References 31 publications

Multiple Kinect based system to monitor and analyze key performance indicators of physical training

Multiple Kinect based system to monitor and analyze key performance indicators of physical training

Accuracy analysis of surface reconstruction from point clouds

Facial recognition and 3D non-rigid registration

Contact Info

Product

Resources

About