無人機在地形繪製、災害調查、環境監測、坡度檢測、旅遊和娛樂等多個領域找到了廣泛的應用。它們具有價格效益高、機動性強以及對惡劣天氣條件的抵抗力，使它們在具有挑戰性的地形中特別有價值，用於數據收集。在本研究中，深度學習中的卷積神經網路模型(CNN)與飛時點雲數據(TOF)感測器相結合，用於識別和測量目標物體的體積。CNN模型使用包含1,614個不同大小的目標物及非目標物圖像數據集進行預測的訓練，並將數據集分成訓練集1,290張以及測試集324張。實驗結果顯示CNN模型訓練及預測之準確度為訓練集100.00%，在測試集上的準確度為98.13%。同時，TOF感測器以低4.39%的誤差率測量目標物體的體積。通過將CNN模型和TOF感測器結合，未來有望通過將目標圖像替換為其他物體，並透過CNN模型訓練，隨後使用TOF感測器來測量該物體之體積。這種集成方法使這兩種方法能夠應用於不同的場景和物體，確保體積測量任務的多功能性和適應性。進而達成該方法在提高效率和降低人力成本方面的有效性。

Unmanned aerial vehicles (UAVs) have found widespread applications in diverse fields such as terrain mapping, disaster surveys, environmental monitoring, slope inspections, tourism, and recreation. Their cost-effectiveness, maneuverability, and resilience to weather conditions make them particularly valuable for data collection in challenging terrains. In this study, a combination of a convolutional neural network (CNN) model within deep learning and the time-of-flight (TOF) sensor is utilized to identify and measure the volume of target objects. The CNN model is trained using a dataset consisting of 1,614 shapes of varying sizes for shape prediction. The dataset is divided into a training set (1,290 shapes) and a test set (324 shapes). Experimental results reveal that the CNN model achieves a training set accuracy of 100.00 % and a test set accuracy of 98.13 %. Concurrently, the TOF sensor measures the volume of the target object with a low error rate of 4.39 %. By integrating the CNN model and TOF sensors, the future potential emerges to measure various objects by replacing the target image in the CNN model and subsequently employing the TOF sensor. This integrated approach enables the application of these two methods to diverse scenarios and objects, ensuring versatility and adaptability in volume measurement tasks. These findings demonstrate the effectiveness of the integrated approach in improving efficiency and reducing human costs.

[1] Collobert, R. and Weston, J. “A Unified Architecture for Natural Language Processing: Deep Neural Networks with Multitask Learning.” The 25th International Conference on Machine Learning, pp. 160-167, 2008.
[2] Van den Oord, A., Dieleman, S. and Schrauwen, B. “Deep Content-Based Music Recommendation.” Advances in Neural Information Processing Systems, pp. 2643-2651, 2013.
[3] Huang, H. M., Wang, X. J., Yi, Z. J., X. and Ma, X. X. “A Character Recognition Based on Feature Extraction.” Journal of Chongqing University, 23, pp. 66-69, 2000.
[4] Avilov, O., Rimbert, S., Popov, A. and Bougrain, L. “Deep Learning Techniques to Improve Intraoperative Awareness Detection from Electroencephalographic Signals.” IEEE Xplore, pp. 142-145, 2020.
[5] Lu, W., Li, J., Li, Y., Sun, A., and Wang, J. “A CNN-LSTM-based Model to Forecast Stock Prices.” Complexity, pp. 1-10, 2020.
[6] Fang, W., Zhang, F., Sheng, V. S. and Ding, Y. “A Method for Improving CNN-Based Image Recognition Using DCGAN.” Tech Science Press, 57(1), pp. 167-178, 2018.
[7] Yann, L. C., Yoshua, B., Geoffery, H. “Deep Learning.” Nature, 521, pp. 436-444, 2015.
[8] Hao, W., Bie, R., Guo, J., Meng, X. and Wang, S. “Optimized CNN Based Image Recognition Through Target Region Selection.” Optik, 156, pp. 772-777, 2018.
[9] Kong, Q., Cao, Y., Iqbal, T., Wang, Y., Wang, W. and Plumbley, M. D. “Panns: Large-scale Pretrained Audio Neural Networks for Audio Pattern Recognition.” IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28, pp. 2880-2894, 2020.
[10] Traore, B. B., Kamsu-Foguem, B. and Tangara, F. “Deep Convolution Neural Network for Image Recognition.” Ecological Informatics, 48, pp. 257-268, 2018.
[11] Tai, L. and Liu, M. “Mobile Robots Exploration through CNN-based Reinforcement Learning.” Robotics and Biomimetics, 3, pp. 1-8, 2016.
[12] Ou, S., Park, H. and Lee, J. “Implementation of an Obstacle Recognition System for the Blind.” Applied Science, 10(1), pp. 282-292, 2020.
[13] Francis, S. L. X., Anavatti, S. G., Garratt, M. and Shim, H. “A TOF Camera as a 3D Vision Sensor for Autonomous Mobile Robotics.” International Journal of Advanced Robotic Systems, 12(11), pp. 156-170, 2015.
[14] Jung, J., Lee, J. Y., Jeong, Y. and Kweon, I. S. “Time-of-Flight Sensor Calibration for a Color and Depth Camera Pair.” IEEE transactions on pattern analysis and machine intelligence, 37(7), pp. 1501-1513, 2015.
[15] Millar, T. C., Sarhangnejad, N. and Katic, N. “The Effect of Pinned Photo Diode Shape on Time-of-Flight Demodulation Contrast.” IEEE Transactions on Electron Devices, 64(5), pp. 2244-2250, 2017.
[16] Adam, A., Dann, C. and Yair, O. “Bayesian Time-of-Flight for Realtime Shape, Illumination and Albedo.” IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(5), pp. 851-864, 2017.
[17] Garduno-Ramon, M. A., Terol-Villalobos, I. R. and Osornio-Rios, R. A. “A New Method for in Painting of Depth Maps from Time-of-Flight Sensors Based on a Modified Closing by Reconstruction Algorithm.” Journal of Visual Communication and Image Representation, 47(1), pp. 36-47, 2017.
[18] Eichhardt, I., Chetverikov, D. and Jankó, Z. “Image-Guided TOF Depth Up sampling: A Survey.” Machine Vision and Applications, 28(3-4), pp. 267-282, 2017.
[19] Horaud, R., Hansard, M., Evangelidis, G. and Ménier, C. “An Overview of Depth Cameras and Range Scanners Based on Time-of-Flight Technologies.” Machine Vision and Applications, 27, pp. 1005-1020, 2016.
[20] He, Y., Liang, B., Zou, Y., He, J. and Yang, J. “Depth Errors Analysis and Correction for Time-of-Flight (TOF) Cameras.” Sensors, 17(1), pp. 92, 2017.
[21] Trong, N. N., Huu, H. H. and Jean, M. “3D Reconstruction with Time-of-Flight Depth Camera and Multiple Mirrors.” IEEE Access, 6, pp. 38106-38114, 2018.
[22] Conde, M. H., Kagaw, K., Kokado, T., Kawahito, S. and Loffeld, O. “Single-Shot Real-Time Multiple-Path Time-of-Flight Depth Imaging for Multi-aperture and Micropixel Sensors.” IEEE Xplore, pp. 1469-1473, 2020.
[23] Lanzisera, S., Zats, D. and Pister, K. S. J. “Radio Frequency Time-of-Flight Distance Measurement for Low-Cost.” IEEE Sensors Journal, 11, pp. 837-845, 2011.
[24] Ferstl, D., Reinbacher, C., Riegler, G., Rüther, M. and Bischof, H. “Learning Depth Calibration of Time-of-Flight Camera.” In Proceedings of the British Machine Vision Conference, 7(10), pp. 1-12, 2015.
[25] Chen, Z., Liu, P., Wen, F., Wang, J. and Ying, R. “Restoration of Motion Blur in Time-of-Flight Depth Image Using Data Alignment.” IEEE Xplore, pp. 820-828, 2020.
[26] Koener, L. J. “Models of Direct Time-of-Flight Sensor Precision that Enable Optimal Design and Dynamic Configuration.” IEEE Transactions on Instrumentation and Measurement, 70, pp. 1-9, 2021.
[27] Zheng, Z., Ding, Y., Tang, X., Cai, Y., Li, D., Zang, M., Xie, H. and Li, X. “Iterative Error Removal for Time-of-Flight Depth Imaging.” International Conference on Artificial Neural Networks, pp. 92-105, 2021.
[28] Szilard, M., Benjamin, K. and Levente, T. “Feature Pyramid Network Based Efficient Normal Estimation and Filtering for Time-of-Flight Depth Cameras.” Sensors, 21(18), pp. 6257, 2021.
[29] Chugunov, I., Baek, S. H., Fu, Q., Heidrich, W. and Heide, F. “Mask-TOF: Learning Microlens Masks for Flying Pixel Correction in Time-of-Flight Imaging.” IEEE Computer Vision and Pattern Recognition (CVPR), pp. 9116-9126, 2021.
[30] Abd-elqader, Y. S., Fawaz, D. E. M. and Hamdy, A. M. “Evaluation Study of GNSS Technology and Traditional Surveying in DEM Generation and Volumes Estimation.” Australian Journal of Basic and Applied Sciences, 14, pp. 18-25, 2020.
[31] Raeva, P. L., Filipova, S. L. and Filipov, D. G. “Volume Computation of a Stockpile—A Study Case Comparing GPS and UAV Measurements in an Open Pit Quarry.” The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, pp. 999-1004, 2016.
[32] Urban, R., Štroner, M. and Kuric, I. “The Use of Onboard UAV GNSS Navigation Data for Area and Volume Calculation.” Acta Montanistica Slovaca, 25(3), pp. 361-374, 2020.
[33] Arango, C. and Morales, C. A. “Comparison between Multicopter UAV and Total Station for Estimating Stockpile Volumes.” The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 30, pp.131-135, 2015.
[34] Ajayi, O. G. and Ajulo, J. “Investigating the Applicability of Unmanned Aerial Vehicles (UAV) Photogrammetry for the Estimation of the Volume of Stockpiles.” Quaestiones Geographicae, 40(1), pp. 25-38, 2021.
[35] Stalin L. J. and Gnanaprakasam R. P. C. “Volume Calculation from UAV Based DEM.” International Journal of Engineering Research & Technology, 6(6), pp.126-128, 2017.
[36] Idrees, A. and Heeto, F. “Evaluation of UAV-Based DEM for Volume Calculation.” Journal of University of Duhok, 23(1), pp. 11-24, 2020.
[37] Shahbazi, M., Sohn, G., Théau, J. and Ménard, P. “UAV-based Point Cloud Generation for Open-pit Mine Modelling.” The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 40(1), pp. 313-320, 2015.
[38] Tucci, G., Gebbia, A., Conti, A., Fiorini, L. and Lubello, C. “Monitoring and Computation of the Volumes of Stockpiles of Bulk Material by Means of UAV Photogrammetric Surveying.” Remote Sensing, 11(12)-1471, 2019.
[39] Ulvi, A. “Analysis of the Utility of the Unmanned Aerial Vehicle UAV in Volume Calculation by Using Photogrammetric Techniques.” International Journal of Engineering and Geosciences, 3(2), pp. 43-49, 2018.
[40] Biçici, S. and Zeybek, M. “An Approach for the Automated Extraction of Road Surface Distress from a UAV-derived Point Cloud.” Automation in Construction, 122(103475), 2021.
[41] Zeybek, M., Sanlıog˘lu, I. “Point Cloud Filtering on UAV Based Point Cloud.” Measurement, 133, pp. 99-111, 2019.
[42] Hubel, D. H. and Wiesel, T. N. “Receptive Fields and Functional Architecture of Monkey Striate Cortex.” The Journal of Physiology, 195(1), pp. 215-243, 1968.
[43] Fukushima, K. “Neocognitron: A Self-Organizing Neural Network Model for a Mechanism of Pattern Recognition Unaffected by Shift in Position.” Biological Cybernetics, 36(4), pp.193-202, 1980.
[44] Fukushima, K. “Neocognitron.” Scholarpedia, 2(1), pp. 1717, 2007.
[45] Convolutional Neural Networks (LeNet)-Deep Learning 0.1 Documentation, Retrieved from LISA Lab, 2013.
[46] Aghdam, H. H. and Heravi, E. J. “Guide to Convolutional Neural Networks: A Practical Application to Traffic-Sign Detection and Classification.” Springer, 2017.
[47] Ciresan, D. C., Meier, U., Masci, J., Gambardella, L. M. and Schmidhuber, J. “Flexible, High Performance Convolutional Neural Networks for Image Classification.” The 22nd International Joint Conference on Artificial Intelligence, Barcelona, pp. 1237-1242, 2011.
[48] Yamaguchi, K., Sakamoto, K., Akabane, T. and Fujimoto, Y. “A Neural Network for Speaker-Independent Isolated Word Recognition.” The 1st International Conference on Spoken Language Processing, Kobe pp. 1077-1080, 1990.
[49] Ciregan, D., Meier, U. and Schmidhuber, J. “Multi-Column Deep Neural Networks for Image Classification.” IEEE Conference on Computer Vision and Pattern Recognition, Providence, pp. 3642-3649, 2012.
[50] Mittal, S. “A Survey of FPGA-Based Accelerators for Convolutional Neural Networks.” Neural Computing and Applications, 32(4), pp. 1109-1139, 2018.
[51] He, K., Zhang, X., Ren, S. and Sun, J. “Deep Residual Learning for Image Recognition.” IEEE Conference on Computer Vision and Pattern Recognition, pp. 770-778, 2016.
[52] Srivastava, R. K., Greff, K. and Schmidhuber, J. “Highway Networks.” International Conference on Machine Learning, arXiv preprint arXiv:1505.00387, 2015.
[53] Ripley, B. D. “Pattern Recognition and Neural Networks.”, Cambridge University Press, United Kingdom, pp.5-51, 2007.
[54] Nair, V. and Hinton, G. E. “Rectified Linear Units Improve Restricted Boltzmann Machines.” International Conference on Machine Learning, 2010.
[55] Murphy, K. P. Machine Learning: A Probabilistic Perspective, MIT Press, United Kingdom, 2012.
[56] Shore, J. and Johnson, R. “Axiomatic Derivation of the Principle of Maximum Entropy and the Principle of Minimum Cross-Entropy.” IEEE Transactions on Information Theory, 26(1), pp. 26-37, 1980.
[57] Stehman, S. V. “Selecting and Interpreting Measures of Thematic Classification Accuracy.” Remote Sensing of Environment, 62(1), pp. 77-89, 1997.
[58] He, Y., Liang, B., Yang, J., Li, S. and He, J. “An Iterative Closest Points Algorithm for Registration of 3D Laser Scanner Point Clouds with Geometric Features.” Sensors, 17(8), pp. 1862, 2017.