نوع مقاله : مقاله پژوهشی

نویسندگان

1 کارشناسی ارشد علوم تصمیم و مهندسی دانش، دانشگاه خوارزمی، تهران

2 دانشیار گروه مدیریت عملیات و فنّاوری اطلاعات، دانشگاه خوارزمی، تهران

3 استادیار مرکز مطالعات سنجش از دور و GIS، دانشگاه شهید بهشتی، تهران

چکیده

مجموعة داده‌های ابر نقاط لیدار و مدل‌های سه‌بعدی (3-D) در استخراج عوارض شهری، مدیریت جنگل‌داری، شهری و گردشگری، رباتیک، تولید بازی‌های رایانه‌ای و موارد دیگر کاربرد گسترده‌ای دارد. از سویی، وجود نقاط پرت در ابر نقاط لیدار اجتناب‌ناپذیر است؛ بنابراین تشخیص نقاط پرت و حذف آن‌ از ابر نقاط لیدار به‌منزلة گامی ضروری در پردازش ابر نقاط لیدار شناخته شده است. طی دهه‌های گذشته، چندین تکنیک تشخیص نقاط پرت در منابع این موضوع معرفی شده است اما بیشتر آنها از نظر زمانی هزینه‌برند و به نیروی متخصص انسانی نیاز دارند. به‌منظور کاهش این محدودیت‌ها، این مقاله رویکرد خودکار جدیدی برای تشخیص نقاط پرت، با استفاده از تکنیک میدان تصادفی شرطی برپایة ماشین بردار پشتیبان (SVM-CRF) و روش نمودار جعبه‌ای، معرفی کرده است. رویکرد نمودار جعبه‌ای بردار انرژی خروجی SVM-CRF را برای تشخیص نقاط پرت تجزیه و تحلیل می‌کند. این روش‌ به‌کمک مجموعه دادة محک ISPRS که برای مجموعه دادة وهینگن، با هدف طبقه‌بندی سه‌بعدی و بازسازی سه‌بعدی ساختمان ایجاد شده بود، ارزیابی شد. به‌منظور ارزیابی این روش، ابتدا نقاط پرتی به‌صورت دستی به مجموعه داده افزوده شد؛ با این تمرکز که این نقاط جزء نقاط پرت چسبیده به اشیا باشند. سپس مراحل تحقیق برای ارزیابی توانایی روش پیشنهادی در تشخیص نقاط پرت انجام شد. نتایج این تحقیق عملکرد مدل پیشنهادی را با دقت کلی 62% نشان داد. اگرچه الگوریتم RANSAC عملکردی بهتر از مدل پیشنهادی دارد، تکنیک زمان‌بر و پرهزینه‌تری در مقایسه با تکنیک تشخیص نقاط پرت پیشنهادی است.

کلیدواژه‌ها

عنوان مقاله [English]

SVM-CRF Method and Box Plot Technique for Outlier Detection of Lidar Point Cloud

نویسندگان [English]

  • Farzaneh Aghighi 1
  • Omid Mahdi Ebadati E. 2
  • Hossein Aghighi 3

1 Sc. in Knowledge Engineering and Decision Science, Kharazmi University, Tehran

2 Associate Prof., Dept. Operation Management & Information Technology, Kharazmi University, Tehran

3 Assistant Prof., Research Center of Remote Sensing and GIS, Shahid Beheshti University, Tehran

چکیده [English]

Lidar point cloud dataset and 3-D models are widely used in urban feature extraction, forest, urban and tourism management, robotics, computer game production etcetera. On the other hand, The existence of outliers in the lidar point cloud is inevitable. Therefore, outlier detection and removing them from lidar point cloud data have been known as necessary steps in lidar point cloud processing. Over the past decade, several outlier detection techniques have been introduced in the literature; however, most of them are time-consuming, expensive, and computationally complicated. For overcoming these limitations, this article introduces a new automatic approach for outlier detection using a support vector machine-based conditional random field (SVM-CRF) technique and box plots methods. In this approach, a box plot analyzes the output energyvector of SVM-CRF to recognize outliers. The methods were evaluated using ISPRS benchmark datasets of Vaihingen provided in order to urban classification and 3D building reconstruction. To evaluate this method, first of all, outliers, that are almost closed to objects, were added to the data set manually. Then the research steps were done to evaluate the proposed method's ability for detecting outliers. The evaluation of this research showed an overall accuracy of 62% as the performance of the proposed model. Although the RANSAC algorithm has better performanc, it is a more costly and time-consuming technique than the proposed outlier detection technique.

کلیدواژه‌ها [English]

  • Lidar Point Cloud
  • Outlier Detection
  • SVM-CRF
  • Box Plot
Aghighi, F., Aghighi, H., & Ebadati, O.M., 2020, Conditional Random Field for Airborne Lidar Point Cloud Classification in Urban Area, Journal of Geospatial Information Technology, 7(4).
Aghighi, F., Ebadati, O.M., & Aghighi, H., 2017, Classification of LiDAR cloud points by using Markov Random Field and machine learning techniques. Iranian Journal of Remote Sensing & GIS, 9, pp. 41-60.
Arekhi, S. & Adibnejad, M., 2011, Efficiency Assessment of the of Support Vector Machines FOR Land Use Classification Using Landsat Etm+ Data (Case Study: Ilam Dam Catchment), Iranian Journal of Range and Desert Research, 18(44), P. 420-440.
Boser, B.E., Guyon, I.M. & Vapnik, V.N., 1992, A Training Algorithm for Optimal Margin Classifiers, Proceeding of the 5th Annual ACM Workshop on Computational Learning Theory, 1839-44 self.
Chang, C.C. & Lin, C.J., 2011, LIBSVM: A Library for Support Vector Machines, ACM Transactions on Intelligent Systems and Technology (TIST), 2(3), P. 27.
Chen, S.Y., Tong, H. & Cattani, C., 2011, Markov Models for Image Labeling, Mathematical Problems in Engineering, 44(1).
Chen, S., Wang, J., Pan, W., Gao, SH., Wang, M. & Lu, X., 2022, Towards Uniform Point Distribution in Feature-Preserving Point Cloud Filtering, Computer Vision and Pattern Recognition (cs.CV). V2.
Congalton, R.G., 1991, A Review of Assessing the Accuracy of Classifications of Remotely Sensed Data, Remote Sensing of Environment, 37(1), PP. 35-46.
Cramer, M., 2010, The DGPF-Test on Digital Airborne Camera Evaluation–Overview and Test Design, Photogrammetrie-Fernerkundung-Geoinformation, 2, PP. 73-82.
David, J.M. & Balakrishnan, K., 2010, Significance of Classification Techniques in Prediction Oflearning Disabilities, Inter-national Journal of Artificial Intelligence & Applications, 1(4), PP. 111-120.
Fischler, M.A. & Bolles, R.C., 1981, Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography, Comunications of the ACM, 24(6), P. 381.
Foody, G.M., 2004, Thematic Map Comparison, Photogrammetric Engineering & Remote Sensing, 70(5), PP. 627-633.
Geng, J., 2013, Three-Dimentional Display Technologies, Adv Opt Photonics, 5(4), PP. 456-535.
Guislain, M., Julie, D., CHaine, R. & Monnier, G., 2017, Fine Scale Image Registration in Large-Scale Urban LIDAR Point Sets, Computer Vision and Image Understanding, 157, PP. 90-102.
Hujebry, b., Samadzadegan, F., & Arefi, H., 2014, Building Reconstruction Based On The Data Fusion Of Lidar Point Cloud And Aerial Imagery, Journal of Geomatics Science and Technology, 3(4), PP. 103-121.
Javidrad, F. & Nazari, M., 2017, A New Hybrid Particle Swarm and Simulated Annealing Stochastic Optimization Method, Applied Soft Computing, 60(c), PP. 634-654.
Kiani, R., & Montazeri, M., 2015, Review of Outlier Detection Methods, International Conference on Research in Science and Technology, Kualalumpour, Malaysia.
Kumar, S. & Hebert, M., 2003, Discriminative Random Fields: A Discriminative Framework for Contextual Interaction in Classification, Proceedings Ninth IEEE International Conference on Computer Vision.
Lafferty, J., McCallum, A. & Pereira, F.C.N., 2001, Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data, Department of Computer & Information Science, University of Pennsylvani.
Li, W., Xu, B., Song, Q., Liu, X., Xu, J. & Brookes, PH.C., 2014, The Identification of ‘Hotspots’ of Heavy Metal Pollution in Soil-Rice Systems at a Regional Scale in Eastern China, Science of the Total Environment, 472, PP. 407-420.
Lin, X. & Zhang, J., 2014, Segmentation-Based Filtering of Airborne LiDAR Point Clouds by Progressive Densification of Terrain Segments, Remote Sensing, 6(2), PP. 1294-1326.
Matas, J. & Chum, O., 2004, Randomized RANSAC with T d; d Test, Image and Vision Computing, 22(10), PP. 837-842.
Matkan, A.A., Hajeb, M., Mirbagheri, B., Sadeghian, S. & Ahmadi, M., 2014, Spatial Analysis for Outlier Removal from Lidar Data, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XL-2/W3.
Nguyen, A. & Le, B., 2013, 3D Point Cloud Segmentation: A Survey, 6th IEEE Conference on Robotics, Automation and Mechatronics (RAM).
Niemeyer, J., Mallet, C., Rottensteiner, F. & Sorgel, U., 2012a, Conditional Random Fields for the Classification of Lidar Point Clouds, International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, [ISPRS Hannover Workshop 2011: High-Resolution Earth Imaging For Geospatial Information] 38-4 (2011), Nr. W19, S. 209-214.
Niemeyer, J., Wegner, L.D., Mallet, C., Rottensteiner, F. & Soergel, U., 2011, Conditional Random Fields for Urban Scene Classication with Full Waveform LiDAR Data, ISPRS Conference on Photogrammetric Image Analysis.
Niemeyer, J., Rottensteiner, F. & Soergel, U., 2012b, Conditional Random Fields for Lidar Point Cloud Classification in Complex Urban Areas, ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 1(3), PP. 263-268.
Niemeyer, J., Rottensteiner, F. & Soergel, U., 2013, Conditional Random Fields for Lidar Point Cloud Classification in Complex Urban Areas, ISPRS Annals of the Photogrammetry, Urban Remote Sensing Event (JURSE).
Nurunnabi, A.A., 2014, Robust Statistical Approaches for Feature Extraction in Laser Scanning 3D Point Cloud Data. Ph.D. Thesis.
Ono, Y., Tsuji, A. & Noguchi, H., 2020, Probust Detection of Surface Anomaly Using Lidar Point Cloud with Intensity, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLIII(B2).
Pao, Y.H., 1989, Adaptive Pattern Recognition and Neural Networks, Addison-Wesley.
Peeters, A. & Etzion, Y., 2012, Automated Recognition of Urban Objects for Morphological Urban Analysis, Computer Environment and Urban Systems, 36(6), PP. 573-582.
Poli, D. & Caravaggi, I., 2013, 3D Modeling of Large Urban Areas with Stereo VHR Satellite Imagery: Lessons Learned, Natural Hazards, 68(1), PP. 53-78.
Raguram, R., Frahm, J.M. & Marc, P., 2008, A Comparative Analysis of RANSAC Techniques Leading to Adaptive Real-Time Random Sample Consensus, European Conference on Computer Vision–ECCV 2008, pp. 500-513.
Ramiya, A.M., Nidamanuri, R.R. & Krishnan, R., 2017, Segmentation Based Building Detection Approach from LiDAR Point Cloud, The Egyptian Journal of Remote Sensing and Space Science, 20(1), PP. 71-77.
Rexhepaj, E., Agnarsdóttir, M., Bergman, J., Edqvist, P.H., Bergqvist, M., Uhlén, M., Gallagher, W.M., Spreckels, V., Syrek, L. & Schlienkamp, A., 2010, DGPF-Project: Evaluation of Digital Photogrammetric Camera Systems–Stereoplotting, Photo-grammetrie- Fernerkundung-Geoinformation, 2, PP. 117-130.
Rwxhepaj, E., Agnarsdottir, M., Bergman, J., Edqvist, P.H., Bergqvist, M., Uhlen, M., Gallagher, W.M., Lundberg, E., Ponten, F., 2013, A Texture Based Pattern Recognition Approach to Distinguish Melanoma from Non-Melanoma Cells in Histopathological Tissue Microarray Sections, PLoS One. 17, 8(5), P. e62070.
Storer, M., Roth, P.M., Urschler, M., Bischof, H. & Birchbauer, J.A., 2009, Efficient Robust Active Appearance Model Fitting, International Conference on Computer Vision, Imaging and Computer Graphics.
Su, L., Xu, Y., Yuan, Y. & Yang, J., 2020, Combining Pixel Swapping and Simulated Annealing for Land Cover Mapping, Sensors (Basel), 20(5), P. 1503.
Torr, P.H.S. & Zisserman, A., 2000, MLESAC: A New Robust Estimator with Application to Estimating Image Geometry, Computer Vision and Image Understanding, 78(1), PP. 138-156.
Vetrivel, A., Gerke, M., Kerle, N. & Vosselman, G., 2015, Identification of Damage in Buildings Based On gaps in 3D Point Clouds from Very High Resolution Oblique Airborne Images, ISPRS Journal of Photogrammetry and Remote Sensing, 105, PP. 61-78.
Wang, V. & Feng, H-Y., 2015, Outlier Detection for Scaned Point Clouds Using Majority Voting, Computer-Aided Design, 62, PP. 31-43.
Xu, B., Jiang, W., Shan, J., Zhang, J. & Li, L., 2015, Investigation on the Weighted Ransac Approaches for Bulding Roof Plane Segmentation from Lidar Point Clouds, Remote Sensing, 8(1), P. 5.
Yuan, X., Chen, H. & Liu, B., 2020, Point Cloud Clustering and Outlier Detection Based on Spatial Neighbor Connected Region Labeling, Measurement and Control, 54(5-6), PP. 835-844.