A METRIC BASED NOVEL CLASSIFICATION APPROACH TO KINECT POINT CLOUD DATA

Yıl 2016, Cilt: 11 Sayı: 4, 153 - 170, 13.10.2016

ERDAL Özbay , AHMET Çınar

Öz

Object classification in 3D point cloud data is an emerging topic attracting increasing research interest. Object detection is one of the most important challenges in computer vision. This paper proposes a novel method for the efficient detection of the real objects with respect to 3D point cloud data. The real object detection is performed using a technique based on mean shift clustering algorithm. The efficiency of the method is verified comparative official 3D data and real 3D point cloud data. We embed presented approach in a framework that combination of extracts shape and point cloud data metric information to improve the outcome of the classification stage. For this aim, classification of 3D point cloud data allows robust segmentation and feature descriptions into different objects by significantly reducing the error. Performed mean shift classification algorithm on the raw data and metric data classification with mean shift algorithm implementation are automatically compared to for evaluation the accuracy of the classification of metric classification algorithm. The results obtained metric classification algorithm and mean shift algorithm on automatic classification of simple planimetric object shapes with the surface of the point cloud show that proposed method is an efficient process.

Anahtar Kelimeler

Classification, Point Cloud, Mean-Shift, Object Detection, Kinect

KINECT NOKTA BULUTU VERİSİNE METRİK TABANLI YENİ BİR SINIFLANDIRMA YAKLAŞIMI

Öz

3B nokta bulutu verileri ile nesne sınıflandırma araştırma alanında gelişmekte çalışmalarında en önemli sorunlardan biridir. Bu yazıda 3B nokta bulutu verilerine göre gerçek nesnelerin etkin şekilde tespiti için yeni bir metriksel yöntem önermekteyiz. Gerçek nesnelerin algılanması ortalama kayma (mean-shift) sınıflandırma algoritmasına dayalı bir yöntemle yapılmaktadır. Yöntemin verimliliği karşılaştırmalı resmi 3B verileri ve gerçek 3B nokta bulutu verileri ile doğrulanmaktadır. Nokta bulutu verileri ve metrik bilgilerin kombinasyonu bir yazılım çerçevesinde uygulanarak sınıflandırma aşamasının sonuçlarını iyileştirilmektedir. Bu amaçla, 3B nokta bulutu verilerinin sınıflandırılması önemli ölçüde hata azaltılarak farklı nesneler içine sağlam segmentasyon ve özellik çıkarımları değerlendirilmiştir. Ham veri üzerine uygulanan ortalama kayma algoritması ile metrik sınıflandırma gerçekleştirilmiş veri üzerine ortalama kayma algoritması uygulaması otomatik olarak karşılaştırılarak metrik sınıflandırma algoritmasının doğruluğu değerlendirilmektedir. Sonuçlar metrik sınıflandırma algoritmasının basit düzlemsel şekle sahip farklı nesnelerin otomatik olarak sınıflandırılmasına verimli bir sürece sahip olduğu göstermektedir

Anahtar Kelimeler

Sınıflandırma, Nokta Bulutu, Mean-Shift, Nesne tanıma, Kinect

Kaynakça

• Eskandari, A.R. and Kouchaki, Z., (2012). Regular Shapes
• Detection in Satellite Images, Malaysian Journal of Computer
• Science, vol:25, no:1, pp:56-66.
• Lai, K. and Fox, D., (2010). Object Recognition in 3D Point
• Clouds Using Web Data and Domain Adaptation, The International
• Journal of Robotics Research, vol:29, no:8, pp:1019-1037.
• Schnabel, R., Wahl, R., Klein, R., (2007). Efficient RANSAC for
• Point-Cloud Shape Detection, Computer Graphics Forum,
• vol:26, no: 2, pp:214-226.
• Hao, W., Wang, Y., Ning, X., Zhao, M., Zhang, J., Shi, Z.,
• and Zhang, X., (2013). Automatic Building Extraction from
• Terrestrial Laser Scanning Data, Advances in Electrical and
• Computer Engineering, vol:13, no:3, pp:11-16.
• Zhang, Z., (2012). Microsoft Kinect Sensor and Its Effect,
• MultiMedia, IEEE, vol:19, no:2, pp:4-12.
• Zhang, M., Zhang, Z., Chang, Y., Esche, S. K., Chassapis, C.,
• (2015). Kinect-based Universal Range Sensor and its Application
• in Educational Laboratories, International Journal of Online
• Engineering (IJOE), vol:11, no:2, pp:26-35.
• Khoshelham, K. and Elberink, S.O., (2012). Accuracy and
• Resolution of Kinect Depth Data for Indoor Mapping Applications,
• Sensors, Vol:12, No:2, pp:1437-1454.
• Ozbay, E. and Cinar, A., (2013). 3D Reconstruction Technique
• With Kinect and Point Cloud Computing, in Proc. 3rd World
• Conference on Information Technology, vol:3, pp:1748-1754.
• Ozbay, E., Cinar, A., (2013). A Novel Approach to Smoothing on
• d Structured Adaptive Mesh of The Kinect-Based Models, in Proc.
• th International Conference on Advanced Information
• Technologies and Applications, pp:13-22.
• Atmosukarto, I. and Shapiro, L.G., (2008). A Learning Approach
• to 3D Object Representation for Classification, in Proc.
• Structural, Syntactic, and Statistical Pattern Recognition,
• Pp:267-276.
• Wei, X., Phung, S.L., and Bouzerdoum, A., (2014). Object
• segmentation and classification using 3-D range camera, Journal
• of Visual Communication and Image Representation, Vol:25, No:1,
• pp:74-85.
• Berger, K., Ruhl, K., Schroeder, Y., Bruemmer, C., Scholz, A.,
• and Magnor, M.A., (2011). Markerless Motion Capture using
• multiple Color-Depth Sensors, In VMV pp:317-324.
• Zalevsky, Z., Shpunt, A., Malzels, A., and Garcia, J., (2013).
• Method and system for object reconstruction” Patent No
• ,400,494, Washington Patent and Trademark Office.
• Smisek, J., Jancosek, M., Pajdla, T., (2013). 3D with Kinect,
• In Consumer Depth Cameras for Computer Vision Springer London,
• Pp:3-25.
• Rusu, R.B. and Cousins, S., (2011). 3D is here: Point Cloud
• Library (PCL), in Proc. 2011 IEEE International Conference on
• Robotics and Automation (ICRA), pp. 1-4.
• Khoshelham, K., (2011). Accuracy Analysis Of Kinect Depth Data.
• ISPRS workshop laser scanning, vol:38, no:5, in Proc.
• ISPRS Workshop Laser Scanning.
• Tombari, F. and Stefano, L.D., (2011). 3d Data Segmentation by
• Local Classification and Markov Random Fields, in Proc.
• International Conference on 3D Imaging, Modeling, Processing,
• Visualization and Transmission, pp:212-219.
• Weinberger, K.Q., Blitzer, J., and Saul, L.K., (2005). Distance
• Metric Learning for Large Margin Nearest Neighbor
• Classification. The Journal of Machine Learning Research,
• vol:10, pp:207-244.
• Altman, N.S., (1992). An Introduction to Kernel tnd Nearest-
• Neighbor Nonparametric Regression, The American Statistician,
• vol:46, no:3, pp:175-185.
• Cheng, Y., (1995). Mean Shift, Mode Seeking, and Clustering,
• Pattern Analysis and Machine Intelligence, IEEE Transactions,
• Vol:17, no:8, pp:790-799.
• Jaskowiak, P.A. and Campello, R.J.G.B., (2011). Comparing
• Correlation Coefficients as Dissimilarity Measures for Cancer
• Classification in Gene Expression Data, in Proc. Brazilian
• Symposium on Bioinformatics, pp. 1-8.
• Rottensteiner, F., Sohn, G., Jung, J., Gerke, M., Baillard, C.,
• Benitez, S., and Breitkopf, U., (2012). The ISPRS Benchmark on
• Urban Object Classification and 3d Building Reconstruction,
• ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci, Vol:1, No:3,
• pp:293-298.
• Klasing, K., Wollherr, D., and Buss, M., (2008). A Clustering
• Method for Efficient Segmentation of 3d Laser Data, in Proc.
• IEEE International Conference on Robotics and Automation (ICRA),
• , pp:4043-4048.
• Kim, T.K., Kee, S.C., and Kim, S.R., (2001). Real-time
• Normalization and Feature Extraction of 3D Face Data Using
• Curvature Characteristics, in Proc. 10th IEEE International
• Workshop on Robot and Human Interactive Communication,
• Pp:74-79.
• Hwang, J.P., Baek, J., Choi, B., and Kim, E., (2015). A Novel
• Part-Based Approach to Mean-Shift Algorithm for Visual Tracking,
• International Journal of Control, Automation and Systems,
• Vol:13, No:2, pp:443-453.
• Talu, M.F., Türkoğlu, İ., and Cebeci, M., (2010). Real-time
• Kernel Based Object Tracking Using Mean Shift, in Proc. 18th
• IEEE Signal Processing and Communications Applications (SIU),
• Pp:328-331.
• Yao, W., Hinz, S., and Stilla, U., (2009). Object Extraction
• Based on 3D-segmentation of Lidar Data by Combining Mean Shift
• with Normalized Cuts: Two Examples from Urban Areas, in Proc.
• IEEE Urban Remote Sensing Event, pp:1-6.