尋求目標（安全著陸點）是空中機器人的關鍵問題。然而，常規的非人工智能方法受到一些嚴重的限制，感知混疊（例如，不同的位置/對象可能看起來相同），遮擋（例如，訪問之間的位置/對像外觀變化），季節/光照變化，大視點變化本文提出了一種基於機器學習和視覺的感知模塊，並比較了AlexNet、VGGNet和ResNet這三種模型中哪一種更適合有效，高效地選擇使用四旋翼無人機的安全著陸點。實施並驗證具有評估指標的各種機器學習框架，以選擇最佳模型。通過度量標準（模型速度，準確性，精確度，召回率，精確召回曲線，接收器工作特性曲線，F1得分）評估模型對安全著陸點的預測的各種機器學習算法。 VGGNet顯示了所有算法之間的最佳權衡。

Goal seeking (safe landing site) is a key issue in the aerial robot. However, the conventional non-artificial intelligence approach suffers from some serious limitations, perceptual aliasing (e.g., different places/objects can appear identical), occlusion (e.g., place/object appearance changes between visits), seasonal / illumination changes, large viewpoint changes, etc. This thesis proposes a machine learning and visual-based perception module and compares which of the three models AlexNet, VGGNet, and ResNet are more suitable for the effective and efficient selection of safe landing sites using quadrotor Unmanned Aerial Vehicles. Various machine learning frameworks with evaluation metrics are implemented and validated for the selection of the best model. Various machine-learning algorithms on model's predictions for safe landing site are evaluated via the metrics (model speed, accuracy, precision, recall, precision-recall curve, receiver operating characteristic curve, F1 score). The VGGNet shows the best trade-off among all algorithms.

[1] M. R. Lee, S. Su, J. E. Yeah, H. Huang and J. Chen, "Autonomous landing system for aerial mobile robot cooperation," in proc. 2014 Joint 7th International Conference on Soft Computing and Intelligent Systems (SCIS) and 15th International Symposium on Advanced Intelligent Systems (ISIS), 2014, pp. 1306-1311.
[2] G. Wang, Z. Liu, X. Wang, " UAV Autonomous Landing using Visual Servo Control based on Aerostack," in proc. CSAE 2019: Proceedings of the 3rd International Conference on Computer Science and Application Engineering, 2019, pp.1-6.
[3] I. Funahashi, Y. Umeki, T. Yoshida and M. Iwahashi, "Safety-level Estimation of Aerial Images based on Convolutional Neural Network for Emergency Landing of Unmanned Aerial Vehicle," in proc. 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2018, pp. 886-890.
[4] N. P. Santos, V. Lobo and A. Bernardino, "Autoland project: Fixed-wing UAV Landing on a Fast Patrol Boat using Computer Vision," in proc. OCEANS 2019 MTS/IEEE SEATTLE, 2019, pp. 1-5.
[5] W. Kong, D. Zhang, X. Wang, Z. Xian and J. Zhang, "Autonomous landing of an UAV with a ground-based actuated infrared stereo vision system," in proc. 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2013, pp. 2963-2970.
[6] K. Pluckter, S. Scherer, "Precision UAV Landing in Unstructured Environments, "2020.
[7] P. H. Nguyen, K. W. Kim, Y. W. Lee, and K. R. Park, “Remote Marker-Based Tracking for UAV Landing Using Visible-Light Camera Sensor,” Sensors, vol. 17, no. 9, p. 1987, Aug. 2017.
[8] B. Ayhan and C. Kwan, "A Comparative Study of Two Approaches for UAV Emergency Landing Site Surface Type Estimation," in proc. IECON 2018 - 44th Annual Conference of the IEEE Industrial Electronics Society, 2018, pp. 5589-5593.
[9] A. Ben-Cohen, E. Klang, M. M. Amitai, J. Goldberger and H. Greenspan, "Anatomical data augmentation for CNN based pixel-wise classification," in proc. 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Washington, 2018, pp. 1096-1099.
[10] Y. Wang, J. Zhang, Y. Cao and Z. Wang, "A deep CNN method for underwater image enhancement," in proc. 2017 IEEE International Conference on Image Processing (ICIP), Beijing, 2017, pp. 1382-1386.
[11] H. Shin et al., "Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning," in proc. IEEE Transactions on Medical Imaging, vol. 35, no. 5, pp. 1285-1298, 2016.
[12] M. B. Bahadure and M. A. Shah, "Recognition of face photos on the basis of sketch using deep CNN and transfer learning," in proc. 2019 International Conference on Intelligent Computing and Control Systems (ICCS), 2019, pp. 1163-1165.
[13] W. Chen, T. Qu, Y. Zhou, K. Weng, G. Wang and G. Fu, "Door recognition and deep learning algorithm for visual based robot navigation," in proc. 2014 IEEE International Conference on Robotics and Biomimetics (ROBIO 2014), 2014, pp. 1793-1798.
[14] A. Kasagi, T. Tabaru and H. Tamura, "Fast algorithm using summed area tables with unified layer performing convolution and average pooling," in proc. 2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP), 2017, pp. 1-6.
[15] Q. Zhang, C. Qi, C. Wang and B. Xiao, "Aggregation and ensemble of fully connected and convolutional activations for image retrieval," in proc. 2016 2nd International Conference on Control, Automation and Robotics (ICCAR), 2016, pp. 308-311.
[16] S. Arya and R. Singh, "A Comparative Study of CNN and AlexNet for Detection of Disease in Potato and Mango leaf," in proc. 2019 International Conference on Issues and Challenges in Intelligent Computing Techniques (ICICT), 2019, pp. 1-6.
[17] A. Titoriya and S. Sachdeva, "Breast Cancer Histopathology Image Classification using AlexNet," in proc. 2019 4th International Conference on Information Systems and Computer Networks (ISCON), 2019, pp. 708-712.
[18] S. B., A. Lesle A., B. Diwakar, K. R. and G. M., "Evaluating Performance of Deep Learning Architectures for Image Classification," in proc. 2020 5th International Conference on Communication and Electronics Systems (ICCES), 2020, pp. 917-922.
[19] G. Cheng, C. Ma, P. Zhou, X. Yao and J. Han, "Scene classification of high resolution remote sensing images using convolutional neural networks," in proc. 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2016, pp. 767-770.
[20] X. Han, Y. Sun and Y. Chen, "Residual Component Estimating CNN for Image Super-Resolution," in proc. 2019 IEEE Fifth International Conference on Multimedia Big Data (BigMM), 2019, pp. 443-447.
[21] C. Chen and F. Qi, "Single Image Super-Resolution Using Deep CNN with Dense Skip Connections and Inception-ResNet," in proc. 2018 9th International Conference on Information Te[1] M. R. Lee, S. Su, J. E. Yeah, H. Huang and J. Chen, "Autonomous landing system for aerial mobile robot cooperation," in proc. 2014 Joint 7th International Conference on Soft Computing and Intelligent Systems (SCIS) and 15th International Symposium on Advanced Intelligent Systems (ISIS), 2014, pp. 1306-1311.
[2] G. Wang, Z. Liu, X. Wang, " UAV Autonomous Landing using Visual Servo Control based on Aerostack," in proc. CSAE 2019: Proceedings of the 3rd International Conference on Computer Science and Application Engineering, 2019, pp.1-6.
[3] I. Funahashi, Y. Umeki, T. Yoshida and M. Iwahashi, "Safety-level Estimation of Aerial Images based on Convolutional Neural Network for Emergency Landing of Unmanned Aerial Vehicle," in proc. 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2018, pp. 886-890.
[4] N. P. Santos, V. Lobo and A. Bernardino, "Autoland project: Fixed-wing UAV Landing on a Fast Patrol Boat using Computer Vision," in proc. OCEANS 2019 MTS/IEEE SEATTLE, 2019, pp. 1-5.
[5] W. Kong, D. Zhang, X. Wang, Z. Xian and J. Zhang, "Autonomous landing of an UAV with a ground-based actuated infrared stereo vision system," in proc. 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2013, pp. 2963-2970.
[6] K. Pluckter, S. Scherer, "Precision UAV Landing in Unstructured Environments, "2020.
[7] P. H. Nguyen, K. W. Kim, Y. W. Lee, and K. R. Park, “Remote Marker-Based Tracking for UAV Landing Using Visible-Light Camera Sensor,” Sensors, vol. 17, no. 9, p. 1987, Aug. 2017.
[8] B. Ayhan and C. Kwan, "A Comparative Study of Two Approaches for UAV Emergency Landing Site Surface Type Estimation," in proc. IECON 2018 - 44th Annual Conference of the IEEE Industrial Electronics Society, 2018, pp. 5589-5593.
[9] A. Ben-Cohen, E. Klang, M. M. Amitai, J. Goldberger and H. Greenspan, "Anatomical data augmentation for CNN based pixel-wise classification," in proc. 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Washington, 2018, pp. 1096-1099.
[10] Y. Wang, J. Zhang, Y. Cao and Z. Wang, "A deep CNN method for underwater image enhancement," in proc. 2017 IEEE International Conference on Image Processing (ICIP), Beijing, 2017, pp. 1382-1386.
[11] H. Shin et al., "Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning," in proc. IEEE Transactions on Medical Imaging, vol. 35, no. 5, pp. 1285-1298, 2016.
[12] M. B. Bahadure and M. A. Shah, "Recognition of face photos on the basis of sketch using deep CNN and transfer learning," in proc. 2019 International Conference on Intelligent Computing and Control Systems (ICCS), 2019, pp. 1163-1165.
[13] W. Chen, T. Qu, Y. Zhou, K. Weng, G. Wang and G. Fu, "Door recognition and deep learning algorithm for visual based robot navigation," in proc. 2014 IEEE International Conference on Robotics and Biomimetics (ROBIO 2014), 2014, pp. 1793-1798.
[14] A. Kasagi, T. Tabaru and H. Tamura, "Fast algorithm using summed area tables with unified layer performing convolution and average pooling," in proc. 2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP), 2017, pp. 1-6.
[15] Q. Zhang, C. Qi, C. Wang and B. Xiao, "Aggregation and ensemble of fully connected and convolutional activations for image retrieval," in proc. 2016 2nd International Conference on Control, Automation and Robotics (ICCAR), 2016, pp. 308-311.
[16] S. Arya and R. Singh, "A Comparative Study of CNN and AlexNet for Detection of Disease in Potato and Mango leaf," in proc. 2019 International Conference on Issues and Challenges in Intelligent Computing Techniques (ICICT), 2019, pp. 1-6.
[17] A. Titoriya and S. Sachdeva, "Breast Cancer Histopathology Image Classification using AlexNet," in proc. 2019 4th International Conference on Information Systems and Computer Networks (ISCON), 2019, pp. 708-712.
[18] S. B., A. Lesle A., B. Diwakar, K. R. and G. M., "Evaluating Performance of Deep Learning Architectures for Image Classification," in proc. 2020 5th International Conference on Communication and Electronics Systems (ICCES), 2020, pp. 917-922.
[19] G. Cheng, C. Ma, P. Zhou, X. Yao and J. Han, "Scene classification of high resolution remote sensing images using convolutional neural networks," in proc. 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2016, pp. 767-770.
[20] X. Han, Y. Sun and Y. Chen, "Residual Component Estimating CNN for Image Super-Resolution," in proc. 2019 IEEE Fifth International Conference on Multimedia Big Data (BigMM), 2019, pp. 443-447.
[21] C. Chen and F. Qi, "Single Image Super-Resolution Using Deep CNN with Dense Skip Connections and Inception-ResNet," in proc. 2018 9th International Conference on Information Technology in Medicine and Education (ITME), 2018, pp. 999-1003.
[22] W. Yangping, Y. jiu, Z. Zhengping and G. Decheng, "Augmented Reality Tracking Registration Based on Improved KCF Tracking and ORB Feature Detection," in proc. 2019 7th International Conference on Information, Communication and Networks (ICICN), 2019, pp. 230-233.
[23] C. Cai, X. Liang, B. Wang, Y. Cui and Y. Yan, "A Target Tracking Method Based on KCF for Omnidirectional Vision," in proc. 2018 37th Chinese Control Conference (CCC), 2018, pp. 2674-2679.
[24] K. ZHANG, H. REN, Y. WEI and J. GONG, "Multi-target vehicle detection and tracking based on video," in proc. 2020 Chinese Control And Decision Conference (CCDC), 2020, pp. 3317-3322.
chnology in Medicine and Education (ITME), 2018, pp. 999-1003.
[22] W. Yangping, Y. jiu, Z. Zhengping and G. Decheng, "Augmented Reality Tracking Registration Based on Improved KCF Tracking and ORB Feature Detection," in proc. 2019 7th International Conference on Information, Communication and Networks (ICICN), 2019, pp. 230-233.
[23] C. Cai, X. Liang, B. Wang, Y. Cui and Y. Yan, "A Target Tracking Method Based on KCF for Omnidirectional Vision," in proc. 2018 37th Chinese Control Conference (CCC), 2018, pp. 2674-2679.
[24] K. ZHANG, H. REN, Y. WEI and J. GONG, "Multi-target vehicle detection and tracking based on video," in proc. 2020 Chinese Control And Decision Conference (CCDC), 2020, pp. 3317-3322.