國立臺灣師範大學博碩士論文全文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	沈方靖 Shen, Fang-Jing
論文名稱：	結合雙AI晶片與熱成像溫測模組之自動目標搜索與溫度量測系統 Automatic Target Searching and Temperature Measurement System Using Dual AI Chips and Thermal Imaging Module
指導教授：	王偉彥 Wang, Wei-Yen
口試委員：	王偉彥 Wang, Wei-Yen 許陳鑑 Hsu, Chen-Chien 翁慶昌 Wong, Ching-chang 盧明智 Lu, Ming-Chih 呂成凱 Lu, Cheng-Kai
口試日期：	2022/08/17
學位類別：	碩士 Master
系所名稱：	電機工程學系 Department of Electrical Engineering
論文出版年：	2022
畢業學年度：	110
語文別：	中文
論文頁數：	62
中文關鍵詞：	終端型AI晶片、卷積神經網路、物件偵測、熱成像測溫
英文關鍵詞：	edge AI chip, convolutional neural network (CNN), object detection, temperature measurement with Thermal Imaging
研究方法:	實驗設計法
DOI URL：	http://doi.org/10.6345/NTNU202201599
論文種類：	學術論文
相關次數：	點閱：87 下載：0
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

本論文提出一種自動搜索目標系統，使用雙人工智慧邊緣型運算處理器結合紅外線熱成像感測器，並透過步控制進馬達來實現自動搜索目標且掃瞄範圍擴增的人體溫度測量設備。本文首先回顧深度學習及類神經網路對於影像辨識的起源以及其應用性，並探討邊緣型處理器對於人形偵測的可行性，再根據此基礎發想出測量人體溫度之應用。而後介紹本論文主要系統架構及硬體設備，使用Mipy深度學習AI開發板配合多種感測裝置，來達成AI目標辨識及環境訊息的測量。本系統架構建立於模型本身的可靠性，針對模型訓練的部分有加強描述：從目標圖片的選取及拍攝、訓練過程的流程改善及參數調整、及最後模型在實驗環境的誤判修正。接著將訓練好的模型載入雙Mipy深度學習AI開發板，並制定一套演算法，協調各微處理器間的交互關係，達成快速掃描且穩定測溫的功能。最後針對多個實際場景，驗證本論文所描述之目標以及該架構反應速度與正確性。

This thesis presents an automatic target searching system using dual AI chips combining an thermal imaging module and stepping control to implement a temperature measuring device that can automatically search for targets and increase the scanning range. This thesis firstly reviews the origin and application of deep learning and neural network for image recognition. We explored the feasibility of the edge processor for human detection. We developed the application for measuring human temperature. This thesis introduces the main system architecture and hardware devices. Mipy development board combines various sensors to complete AI target recognition and collection of environmental information. The system framework is built on the reliability of the model, so we enhance the description for model training, such as the selection and capture of the target, the improvement of the training process and the adjustment of parameters, and the correction of model false positives in the experiment. We load the trained model into the dual AI development board and develop an algorithm to coordinate the interaction between the microprocessors to achieve fast scanning and stable temperature measurement. Finally, the application was validated against several practical scenarios to accomplish the objectives described in this thesis, and the framework was responsive and effective

第一章 緒論	1
1 研究動機與背景	1
2 文獻探討	2
2.1 卷積神經網路	2
2.2 Mipy深度學習AI開發板之人形偵測應用	4
3 論文架構	6
第二章 硬體架構與設計	7
1 系統架構	7
2 硬體架構	9
3 Mipy深度學習AI開發板	10
4 熱成像溫度測量裝置	12
5 步進馬達迴旋機構	13
第三章 Mipy模型及網路訓練框架	16
1 AI模型	16
1.1 一號人形模型	16
1.2 二號人臉模型	17
2 Mipy深度學習AI開發板之開發套件	18
2.1 資料集創造工具	19
2.2 推論工具	19
2.3 訓練工具	21
3 訓練流程	21
3.1 搜集訓練資料：	22
3.2 生成訓練集和測試集：	24
3.3 預訓練模型：	26
3.4 輸入模型並搜集偽正面的圖像	26
3.5 計算資料集信賴分數及設定強化訓練區間	27
3.6 迴圈訓練模型	28
3.7 影片測試誤判效果	29
3.8 利用Mipy深度學習AI開發板進行環境測試	29
3.9 調整影像偵測參數	30
第四章 目標追蹤系統	32
1 偵測框產生機制	32
1.1 目標框選	33
1.2 偵測框合併	33
1.3 偵測框移除	35
2 驅動馬達原理及控制	37
3 控制流程及原點回歸	38
3.1 搜索目標	40
3.2 目標微調	40
第五章 實驗結果與分析	41
1 雙AI模型訓練結果與分析	41
1.1 人形模型	42
1.2 人臉模型	43
2 實驗規劃	46
3 實驗一(大廳場景測試)	47
3.1 實驗設計	47
3.2 實驗環境介紹	48
3.3 測溫實驗	49
4 實驗二(多通道場景測試)	52
4.1 實驗設計	52
4.2 實驗環境介紹	53
4.3 測溫實驗	54
5 實驗討論	58
第六章 結論與未來展望	59
1 結論	59
2 未來展望	59
參考文獻	60
                                

[1] Y. LeCun et al., "Backpropagation applied to handwritten zip code recognition," Neural computation, vol. 1, no. 4, pp. 541-551, 1989.
[2] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, 1998.
[3] NVIDIA. "Jetson TX2." https://www.nvidia.com/zh-tw/autonomous-machines/embedded-systems/jetson-tx2/ (accessed Aug. 09, 2022).
[4] Intel. "Intel® Movidius™ 視覺處理器 (VPU)." https://www.intel.com.tw/content/www/tw/zh/products/details/processors/movidius-vpu.html (accessed Aug. 09, 2022).
[5] F.-J. Shen, J.-H. Chen, W.-Y. Wang, D.-L. Tsai, L.-C. Shen, and C.-T. Tseng, "A CNN-Based Human Head Detection Algorithm Implemented on Edge AI Chip," in 2020 International Conference on System Science and Engineering (ICSSE), 2020: IEEE, pp. 1-5.
[6] 視芯有限公司. "視芯AVSdsp | AI晶片與應用模組開發 " https://sites.google.com/avsdsp.com/avsdsp/ (accessed Aug. 30, 2022).
[7] 視芯有限公司. "視芯AVSdsp | Mipy AI 簡易應用發展系統." https://sites.google.com/avsdsp.com/avsdsp/module/mipy-system (accessed Aug. 30, 2022).
[8] Wikipedia. "Stepper motor." https://en.wikipedia.org/wiki/Stepper_motor (accessed Aug. 11, 2022).
[9] STMicroelectronics. "VL53L1X." https://www.st.com/en/imaging-and-photonics-solutions/vl53l1x.html (accessed Aug. 10, 2022).
[10] Wikipedia. "Hall effect sensor." https://en.wikipedia.org/wiki/Hall_effect_sensor (accessed Aug. 11, 2022).
[11] Wikipedia. "UART." https://zh.wikipedia.org/zh-tw/UART (accessed Aug. 11, 2022).
[12] Wikipedia. "I²C." https://zh.wikipedia.org/zh-tw/I%C2%B2C (accessed Aug. 11, 2022).
[13] H. Ibrahim and N. S. P. Kong, "Brightness preserving dynamic histogram equalization for image contrast enhancement," IEEE Transactions on Consumer Electronics, vol. 53, no. 4, pp. 1752-1758, 2007.
[14] I. Allegro MicroSystems. "A3144EU Datasheet." https://www.mpja.com/download/a3144eul.pdf (accessed Aug. 11, 2022).
[15] HuaNing. "24BYJ48 Datasheet." https://datasheet4u.com/datasheet-pdf/HuaNing/24BYJ48/pdf.php?id=1419818 (accessed Aug. 11, 2022).
[16] Y. Yoshitomi, S.-I. Kim, T. Kawano, and T. Kilazoe, "Effect of sensor fusion for recognition of emotional states using voice, face image and thermal image of face," in Proceedings 9th IEEE International Workshop on Robot and Human Interactive Communication. IEEE RO-MAN 2000 (Cat. No. 00TH8499), 2000: IEEE, pp. 178-183.
[17] K. Fukushima and S. Miyake, "Neocognitron: A self-organizing neural network model for a mechanism of visual pattern recognition," in Competition and cooperation in neural nets: Springer, 1982, pp. 267-285.
[18] I. Masi, A. T. Trần, T. Hassner, G. Sahin, and G. Medioni, "Face-specific data augmentation for unconstrained face recognition," International Journal of Computer Vision, vol. 127, no. 6, pp. 642-667, 2019.
[19] G. Huang, M. Mattar, H. Lee, and E. Learned-Miller, "Learning to align from scratch," Advances in neural information processing systems, vol. 25, 2012.
[20] M. Yan, M. Zhao, Z. Xu, Q. Zhang, G. Wang, and Z. Su, "Vargfacenet: An efficient variable group convolutional neural network for lightweight face recognition," in Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, 2019, pp. 0-0.
[21] D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization," arXiv preprint arXiv:1412.6980, 2014.
[22] M. P. Systems(MPS). "Stepper Motors Basics: Types, Uses, and Working Principles." https://www.monolithicpower.com/en/stepper-motors-basics-types-uses (accessed Aug. 11, 2022).
[23] Wikipedia. "Confusion matrix." https://en.wikipedia.org/w/index.php?title=Confusion_matrix&oldid=1088688630 (accessed Aug. 11, 2022).
[24] S. R. Reza, X. Dong, and L. Qian, "Robust Face Mask Detection using Deep Learning on IoT Devices," in 2021 IEEE International Conference on Communications Workshops (ICC Workshops), 2021: IEEE, pp. 1-6.
[25] NVIDIA. "NVIDIA Jetson Nano." https://www.nvidia.com/zh-tw/autonomous-machines/embedded-systems/jetson-nano/ (accessed Aug. 30, 2022).
[26] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, "Mobilenetv2: Inverted residuals and linear bottlenecks," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 4510-4520.
[27] K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770-778.
[28] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, "Rethinking the inception architecture for computer vision," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 2818-2826.
[29] K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," in ICLR, San Diego, CA, USA, 2015.

電子全文延後公開
2027/03/27

簡易檢索 / 詳目顯示

相關論文