臺灣博碩士論文加值系統

物件偵測技術是影像處理領域中重要的技術之一，由於影像中物件的交疊容易產生偵測錯誤而切割出錯誤的物件，因此本研究提出一個三維物件偵測方法，以解決物件交疊的切割與標記問題。本方法是以立體視覺為基礎，利用距離資訊作為連通物件標記演算法的判斷，同時以邊緣輪廓線段的封閉性和色彩的連續性作為物件合併的條件，切割出不同的交疊物件，並估算各物件的距離與外型尺寸，在不需依賴連續影像的動態資訊，也不用事先知道偵測物件的影像特性之下，達到在未知環境中物件偵測的目的。實驗結果驗證本演算法能有效的解決複雜交疊物件的偵測問題，且滿足不同距離的偵測需求，所切割出含有三維資訊的物件，可提供後續影像辨識的參考資訊，減少影像辨識所需的搜尋處理並降低辨識錯誤。

Object detection is one of the important technologies in the field of image processing. Because the overlapping objects may cause detection errors and the wrong object segmentation, this study proposes a three-dimensional object detection algorithm to solve the problem of the segmentation and labeling of overlapping objects. Based on stereo vision, the proposed algorithm uses the distance information as the judgment of the Connected Components Labeling Algorithms, the closure property and color continuity of the edge contour line segment as a condition for object merging to segment the different overlapping objects, and estimate the object’s distance and size to achieve the purpose of object detection in an unknown environment, without relying on the dynamic information of consecutive images and without obtaining the characteristics of the detected objects in advance. The experimental results verify that the algorithm can effectively solve the detection problem of complex overlapping objects, and meet the detection requirements of different distances. The segmentation objects containing 3D information can provide reference information for subsequent image recognition, reducing the search processing of image recognition and identification errors.

誌謝 ii
摘要 iii
Abstract iv
目錄 v
表目錄 vii
圖目錄 viii
1.緒論 1
1.1研究動機與背景 1
1.2研究目的 4
1.3論文架構 8
2.文獻探討 9
2.1.物件切割 9
2.1.1.動態切割 9
2.1.2.靜態切割 12
2.1.3.三維資訊物件切割 14
2.2.連通物件標記演算法 19
2.2.1.二維連通物件標記 19
2.2.2.三維連通物件標記 21
2.3.立體視覺 24
3.三維物件偵測演算法 26
3.1.紋理建構邊緣偵測演算法 28
3.2.距離連通物件標記演算法 34
3.3.物件延伸合併演算法 44
3.4.物件切割 57
4.實驗結果與討論 58
5.結論與未來研究方向 90
5.1.結論 90
5.2.未來研究方向 91
參考文獻 97
論文發表 103

[1]http://www.epochtimes.com/b5/14/3/11/n4103733.htm
[2]Guizzo, E., 2019, “By Leaps and Bounds: An Exclusive Look at How Boston Dynamics is Redefining Robot Agility,” IEEE Spectrum, vol. 56, no. 12, pp. 34-39.
[3]Kim, D., Carballo, D., Di Carlo, J., Katz, B., Bledt, G., Lim, B., and Kim, S., 2020, “Vision Aided Dynamic Exploration of Unstructured Terrain with a Small-Scale Quadruped Robot,” Proceedings of IEEE International Conference on Robotics and Automation, Paris, France, pp. 2464-2470.
[4]Yaqoob, I., Khan, L. U., Kazmi, S. M. A., Imran, M., Guizani, N., and Hong, C. S., 2019, “Autonomous Driving Cars in Smart Cities: Recent Advances, Requirements, and Challenges,” IEEE Network, vol. 34, no. 1, pp. 174-181.
[5]Arnold, E., Al-Jarrah, O. Y., Dianati, M., Fallah, S., Oxtoby, D., and Mouzakitis, A., 2019, “A Survey on 3D Object Detection Methods for Autonomous Driving Applications,” IEEE Transactions on Intelligent Transportation Systems, vol. 20, no. 10, pp. 3782-3795.
[6]Fu, Z., Chen, Y., Yong, H., Jiang, R., Zhang L., and Hua, X., 2019, “Foreground Gating and Background Refining Network for Surveillance Object Detection,” IEEE Transactions on Image Processing, vol. 28, no. 12, pp. 6077-6090.
[7]Huang, S. C., Liu, H., Chen, B. H., Fang, Z., Tan T. H., and Kuo, S. Y., 2019, “A Gray Relational Analysis-Based Motion Detection Algorithm for Real-World Surveillance Sensor Deployment,” IEEE Sensors Journal, vol. 19, no. 3, pp. 1019-1027.
[8]Wu, Y., Sui, Y., and Wang, G., 2017, “Vision-Based Real-Time Aerial Object Localization and Tracking for UAV Sensing System,” IEEE Access, vol. 5, pp. 23969-23978.
[9]Fäulhammer, T., Ambrus, R., Burbridge, C., Zillich, M., Folkesson, J., Hawes, N., Jensfelt, P., and Vincze, M., 2017, “Autonomous Learning of Object Models on a Mobile Robot,” IEEE Robotics and Automation Letters, vol. 2, no. 1, pp. 26-33.
[10]Girshick, R., Donahue, J., Darrell, T., and Malik, J., 2014, “Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation,” Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, pp. 580-587.
[11]Girshick, R., 2015, “Fast R-CNN,” Proceedings of IEEE International Conference on Computer Vision, Santiago, Chile, pp. 1440-1448.
[12]Ren, S., He, K., Girshick R., and Sun, J., 2017, “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 6, pp. 1137-1149.
[13]Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., and Berg, A. C., 2016, “SSD: Single Shot Multibox Detector,” Computer Vision, Springer: Cham, Switzerland, pp. 21-37.
[14]Redmon, J., Divvala, S., Girshick R., and Farhadi, A., 2016, “You Only Look Once: Unified, Real-Time Object Detection,” Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, pp. 779-788.
[15]Thys, S., Ranst, W. V., and Goedemé, T., 2019, “Fooling Automated Surveillance Cameras: Adversarial Patches to Attack Person Detection,” Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Long Beach, CA, USA, pp. 49-55.
[16]Wixson, L., 2000, “Detecting Salient Motion by Accumulating Directionally- Consistent Flow,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 774-780.
[17]Kalsotra, R. and Arora, S., 2019, “A Comprehensive Survey of Video Datasets for Background Subtraction,” IEEE Access, vol. 7, pp. 59143-59171.
[18]Chiu, C. C., Ku, M. Y., and Liang, L. W., 2010, “A Robust Object Segmentation System Using a Probability-based Background Extraction Algorithm,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 20, no. 4, pp. 518-528.
[19]Hati, K. K., Sa, P. K., and Majhi, B., 2013, “Intensity Range Based Background Subtraction for Effective Object Detection,” IEEE Signal Processing Letters, vol. 20, no. 8, pp. 759-762.
[20]Dirami, A., Hammouche, K., Diaf, M., and Siarry, P., 2013, “Fast Multilevel Thresholding for Image Segmentation through a Multiphase Level Set Method,” Signal Processing, vol. 93, no. 1, pp. 139-153.
[21]Li, J., Wang J., and Mao, J., 2014, “Color Moving Object Detection Method Based on Automatic Color Clustering,” Proceedings of 33rd Chinese Control Conference, Nanjing, China, pp. 7232-7235.
[22]Hassanat, A. B. A., Alkasassbeh, M., Al-awadi, M., and Alhasanat, E. A. A., 2016, “Color-Based Object Segmentation Method using Artificial Neural Network,” Simulation Modelling Practice and Theory, vol. 64, pp. 3-17.
[23]Chen, Y., Ma, Y., Kim, D. H., and Park, S. K., 2015, “Region-Based Object Recognition by Color Segmentation Using a Simplified PCNN,” IEEE Transactions on Neural Networks and Learning Systems, vol. 26, no. 8, pp.1682-1697.
[24]Fan, J., Yau, D. K. Y., Elmagarmid, A. K., and Aref, W. G., 2001, “Automatic Image Segmentation by Integrating Color-Edge Extraction and Seeded Region Growing,” IEEE Transactions on Image Processing, vol. 10, no. 10, pp.1454-1466.
[25]Zitnick, C. L. and Dollár, P., 2014, “Edge Boxes: Locating Object Proposals from Edges,” Computer Vision, Springer: Cham, Switzerland, pp. 391-405.
[26]Sun, L. and Shibata, T., 2014, “Unsupervised Object Extraction by Contour Delineation and Texture Discrimination Based on Oriented Edge Features,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 24, no. 5, pp. 780-788.
[27]Xie, Q., Remil, O., Guo, Y., Wang, M., Wei, M., and Wang, J., 2018, “Object Detection and Tracking Under Occlusion for Object-Level RGB-D Video Segmentation,” IEEE Transactions on Multimedia, vol. 20, no. 3, pp.580-592.
[28]Liu, C., Wang, W., Shen, J., and Shao, L., 2019, “Stereo Video Object Segmentation Using Stereoscopic Foreground Trajectories,” IEEE Transactions on Cybernetics, vol. 49, no. 10, pp.3665-3676.
[29]Sun, C. C., Wang, Y. H., and Sheu, M. H., 2017, “Fast Motion Object Detection Algorithm Using Complementary Depth Image on an RGB-D Camera,” IEEE Sensors Journal, vol. 17, no. 17, pp. 5728-5734.
[30]Gotardo, P. F. U., Bellon, O. R. P., Boyer, K. L., and Silva, L., 2004, “Range Image Segmentation into Planar and Quadric Surfaces Using an Improved Robust Estimator and Genetic Algorithm,” IEEE Transactions on Systems, Man, and Cybernetics—Part B: Cybernetics, vol. 34, no. 6, pp.2303-2316.
[31]Husain, F., Dellen, B., and Torras, C., 2015, “Consistent Depth Video Segmentation Using Adaptive Surface Models,” IEEE Transactions on Cybernetics, vol. 45, no. 2, pp.266-278.
[32]Rosenfeld, A. and Pfalts, J. L., 1966, “Sequential operations in digital picture processing,” Journal of the ACM, vol. 13, no. 4, pp. 471-494.
[33]He, L., Ren, X., Gao, Q., Zhao, X., Yao, B., and Chao, Y., 2017, “The Connected-Component Labeling Problem: A Review of State-of-the-Art Algorithms,” Pattern Recognition, vol. 70, pp. 25-43.
[34]Lumia, R., Shapiro, L., and Zungia, O., 1983, “A New Connected Components Algorithm for Virtual Memory Computers,” Computer Vision, Graphics, and Image Processing, vol. 22, no. 2, pp. 287-300.
[35]Hossam, M. M., Hassanien, A. E., and Shoman, M., 2010, “3D Brain Tumor Segmentation Scheme using K-Mean Clustering and Connected Component Labeling Algorithms,” Proceedings of 10th International Conference on Intelligent Systems Design and Applications, Cairo, Egypt, pp. 320-324.
[36]Brahim, W., Mestiri, M., Betrouni, N., and Hamrouni, K., 2016, “Semi-Automated Rib Cage Segmentation in CT Images for Mesothelioma Detection,” Proceedings of International Image Processing, Applications and Systems, Hammamet, Tunisia, pp. 1-6.
[37]Wongwaen, N. and Sinthanayothin, C., 2016, “Automatic Background Subtraction Algorithm for 3D Object by Using Connected-Component Labeling Algorithm,” Proceedings of International Symposium on Intelligent Signal Processing and Communication Systems, Phuket, Thailand, pp. 1-4.
[38]Barnard, S. T. and Fischler, M. A., 1982, “Computational Stereo,” ACM Computing Surveys. vol. 14, no. 4, pp. 553-572.
[39]Lo, W. C., Chiu, C. C., and Yang, J. H., 2022, “Three-Dimensional Object Segmentation and Labeling Algorithm Using Contour and Distance Information,” Applied Sciences, vol. 12, no. 13, 6602.
[40]Chen, S. C. and Chiu, C. C., 2019, “Texture Construction Edge Detection Algorithm,” Applied Sciences, vol. 9, no. 5, 897.
[41]Geiger, A., Lenz, P., Stiller, C., and Urtasun, R., 2013, “Vision meets Robotics: The KITTI Dataset,” International Journal of Robotics Research, vol. 32, no. 11, pp 1231-1237.
[42]Chiu, C. C. and Lo, W. C., 2020, “An Object Detection Algorithm with Disparity Values,” Proceedings of 4th International Conference on Imaging, Signal Processing and Communications, Kumamoto, Japan, pp. 20-23.
[43]Labayrade, R., Aubert, D., and Tarel, J. P., 2002, “Real Time Obstacle Detection in Stereovision on Non Flat Road Geometry Through "V-disparity" Representation,” Proceedings of Intelligent Vehicle Symposium, Versailles, France, pp. 646-651.
[44]Hough, P.V.C., 1962, “Method and Means for Recognizing Complex Patterns,” U.S. Patent 3,069,654.
[45]Papamarkos, N., Tzortzakis, J., and Gatos, B., 1996, “Determination of Run-Length Smoothing Values for Document Segmentation,” Proceedings of 3th International Conference on Electronics, Circuits, and Systems, Rhodes, Greece, pp. 684-687.
[46]Scharstein, D., Hirschmüller, H., Kitajima, Y., Krathwohl, G., Nesic, N., Wang, X., and Westling, P., 2014, “High-Resolution Stereo Datasets with Subpixel-Accurate Ground Truth,” Pattern Recognition, Springer: Cham, Switzerland, pp31-42.
[47]Tan, J., Gao, M., Yang, K., and Duan, T., 2021, “Remote Sensing Road Extraction by Road Segmentation Network,” Applied Sciences, vol. 11, no. 11, 5050.