Identify the Object’s Shape using Augmented Reality Marker-based Technique.

Charlee Kaewrat, Poonpong Boonbrahm


At present, new technology affects daily life in both direct and indirect ways. Internet technology can connect people around the world through social networks. It can facilitate online shopping or e-commerce, which is the popular culture of today business. Contents provided in the online shopping must be in the form that customer can interact with, i.e., it must be converted from analog data to digital information. For apparel or clothing business, only picture and information of the dresses, such as size, color, etc., may not be enough, since the customer did not know whether it will fit their bodies or not. To make sure that the dress they wanted to buy fit their body, the body size of the customers must be known. With the known body size, generating the 3D model of the customer to try on the 3D virtual model of the dress is possible, and the decision to buy is possible. There are many ways to find the exact body size and generate a 3D model of the customers i.e. using 3D scanner, using Photogrammetry technique (merging many photographs of the customers’ bodies to create the 3d model) or generating 3D model with known information using 3d computer graphic software such as Autodesk Maya, 3D max. The techniques mentioned above have some drawback because it required either an expensive device or expert to create a 3D model which may take a long time. Therefore in this research, we present the technique using marker-based Augmented Reality to acquire the shape of the objects. By wrapping the markers around the surface of the object that we want to measure, each marker’s position can be identified, and when combined, the shape and sizes of the object can be created. This technique takes a shorter time than other method and does not require any sophisticated device but still give good results. We separate the experiment into three groups, group one, testing the concept with five objects with different sizes and shapes with one row markers and group two, testing cylindrical objects with four row markers, and group three, testing with a mannequin to find the shape of human’s body. we have found that the shape and size of the objects that we have created are very close to the real one with the maximum error of less than 5%. It possible to generate the whole 3D object which can be adjusted to support virtual fitting room.


augmented reality; marker-base technique; measurement.

Full Text:



Adikari, A. M. S. B., N. G. C. Ganegoda, and W. K. I. L. Wanniarachchi. "Non-contact human body parameter measurement based on Kinect sensor." IOSR Journal of Computer Engineering 19.3 (2017): 80-85.

Alexiadis, Dimitrios S., Dimitrios Zarpalas, and Petros Daras. “Real-time, full 3-D reconstruction of moving foreground objects from multiple consumer depth camerasâ€. in IEEE Transactions on Multimedia 15.2, pages 339-358, 2012.

Allen, B., Curless, B., & Popović, Z. “The space of human body shapes: reconstruction and parameterization from range scans.†In ACM transactions on graphics Vol. 22, No. 3, pages. 587-594. ACM, July 2003.

Lee, Kyoung-Rok, and Truong Nguyen. "Realistic surface geometry reconstruction using a hand-held RGB-D camera." Machine Vision and Applications 27.3 (2016): 377-385.

Newcombe, Richard A., et al. "KinectFusion: Real-time dense surface mapping and tracking." 2011 IEEE International Symposium on Mixed and Augmented Reality. IEEE, 2011.

Nguyen, Chuong V., Shahram Izadi, and David Lovell. "Modeling kinect sensor noise for improved 3d reconstruction and tracking." 2012 second international conference on 3D imaging, modeling, processing, visualization & transmission. IEEE, 2012.

Se, Stephen, and Piotr Jasiobedzki. "Photo-realistic 3D model reconstruction." Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006. IEEE, 2006.

Tong, J., Zhou, J., Liu, L., Pan, Z., & Yan, H. “Scanning 3d full human bodies using kinectsâ€. IEEE transactions on visualization and computer graphics, 18(4), 643-650. 2012.

Xu, Di, et al. "Kinect-based easy 3d object reconstruction." Pacific-Rim Conference on Multimedia. Springer, Berlin, Heidelberg, 2012.

Yoshino, Naoyuki, Stephen Karungaru, and Kenji Terada. "Body Physical Measurement Using Kinect for Vitual Dressing Room." 2017 6th IIAI International Congress on Advanced Applied Informatics (IIAI-AAI). IEEE, 2017.

Yousef, Khalil M. Ahmad, Bassam J. Mohd, and AL-Omari Malak. "Kinect-Based Virtual Try-on System: A Case Study." 2019 IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology (JEEIT). IEEE, 2019.

Yu, Tao, et al. "Doublefusion: Real-time capture of human performances with inner body shapes from a single depth sensor." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018.

Yun, SangUn, Dongbo Min, and Kwanghoon Sohn. "3D scene reconstruction system with hand-held stereo cameras." 2007 3DTV Conference. IEEE, 2007.

Zollhöfer, M., Nießner, M., Izadi, S., Rehmann, C., Zach, C., Fisher, M., ... & Stamminger, M. “Real-time non-rigid reconstruction using an RGB-D cameraâ€. ACM Transactions on Graphics. 2014.



  • There are currently no refbacks.

Published by INSIGHT - Indonesian Society for Knowledge and Human Development