臺灣博碩士論文加值系統

由於現代人對於行車安全的重視度日益提升，在台灣的行車人員都會在車上安裝行車紀錄，紀錄日常行車或是肇事事故，台灣日常生活中大多以機車作為短程市區的代步工具，在車水馬龍的台灣街道，機車是時常穿梭在車陣當中，對於汽車駕駛來說對於機車的出現難以預測，本論文對行車紀錄器的機車車輛進行偵測及辨識畫框提醒駕駛人機車確切位置，以R.Girshick[1]論文作為基礎，修改Fast R-CNN[2]與RPN架構，並調整其學習演算法。對於R-CNN[3]的架構原作者是使用VGG16[4]與ZF Net[5] ，此論文使用此兩種類神經網路，並修改其RPN類別數量及相關參數。本文透過增加特殊樣本，及調教其參數，使此網路架構達到最佳化的成果。

Due to the attention of modern people on the increasing importance of traffic safety, drivers in Taiwan install driving recorder which record daily traffic or accident. Taiwanese usually use scooter as commuter vehicle. Riders in Taiwan are often shuttle in the traffic jam, it is very dangerous for car driver to detect the riders. It is usually to cause car accidents. In this paper, we propose a system to remind car drivers to avoid the danger of rider in the traffic jam or street .The system will draw rectangles on the driving recorder to mark the interested object on the video, namely car, scooter, bus, person and bicycle. We based on R .Girshick [1] as a basis for modifying Fast R-CNN [2] with the RPN architecture and adjusting its learning algorithms. For the R-CNN [3] architecture, the original author uses VGG16 [4] and ZF Net [5], which uses these two types of neural networks and modifies the number of RPN categories and related parameters. This paper makes the optimization of the network architecture by adding special samples and tuning its parameters.

目錄
誌謝
摘要
目錄
圖目錄
表目錄
第一章 緒論
1.1 研究動機
1.2 論文架構
第二章 相關研究
2.1 MULTILAYER PERCEPTRONS AND GRADIENT DECENT ALGORITHM
2.1.1 Region with Convolution Neural Networks
2.2 FASTER REGION CONVOLUTION NEURAL NETWORK
2.3 TENSOR FLOW
2.3.1 Tensor Flow 特性
2.3.2 Docker
第三章 研究方法
3.1 基於REGION CONVOLUTION NEURAL NETWORKS的機車辨識系統
3.2 FAST R-CNN
3.3 REGION PROPOSAL NETWORK
3.3.1 Anchor
3.3.2 RPN Loss Function
3.3.2 Bounding Box Regression
3.3.3 Training RPN
3.4 SHARING FEATURES FOR RPN AND FAST R-CNN
第四章 實驗
4.1 電腦系統環境與開發環境
4.1.1 電腦系統環境架設
4.2 實驗列表
4.3 實驗結果圖
4.3 實驗結果總結
第五章 結論
參考文獻

[1]Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol.pp, Issue.99 , 2016.
[2]Ross Girshick, “Fast Region-based Convolutional Network method (Fast R-CNN) for object detection,” ICCV 2015, 2015.
[3]Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik, “Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation,” IEEE Conference on Computer Vision and Pattern Recognition., vol. 2, no. 1, pp. 580–587, 2014.
[4]K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,”International Conference on Learning Representations, 2015.
[5]M. D. Zeiler and R. Fergus. “T Visualizing and understanding convolutional neural networks” in European Conference on Computer Vision (ECCV), 2014.
[6]D. Griffin and J. S. Lim, “Text Detection and Recognition on Traffic Panels From Street-Level Imagery Using Visual Appearance,” IEEE Transactions on Intelligent Transportation Systems, Vol.15, pp.228-238, 2014.
[7]Jack Greenhalgh; Majid Mirmehdi, “Recognizing Text-Based Traffic Signs,” IEEE Transactions on Intelligent Transportation Systems, vol. 16, pp. 1360–1369, 2015.
[8]Yuanyuan Wu, Xiaohai He, Truong Q. Nguyen, “Moving Object Detection With a Freely Moving Camera via Background Motion Subtraction,” C IEEE Transactions on Circuits and Systems for Video Technology, pp. 236–248, 2017
[9]Ce Liu et al, “Beyond pixels: exploring new representations and applications for motion analysis,” Ph.D. thesis, Massachusetts Institute of Technology, 2009.
[10]Zhen Dong, Yuwei Wu, Mingtao Pei, Yunde Jia, “Vehicle Type Classification Using a Semisupervised Convolutional Neural Network,” IEEE Transactions on, vol. 16, no 4, pp. 2247-2256, 2015.
[11]Simon Haykin, Feedforward Neural Networks: An Introduction, Wiley, 1998.
[12]Paul J. Werbos, “Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences,” PhD thesis, Harvard University, 1974.
[13]J. Uijlings, K. van de Sande, T. Gevers, and A. Smeulders, “Selective search for object recognition,” IJCV, 2013.
[14]Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, “Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence., vol. 37, pp. 1904–1916, 2015.
[15]J. Hosang, R. Benenson, P. Doll´ar, and B. Schiele, “What makes for effective detection proposals,”　IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2015.
[16]J. Hosang, R. Benenson, and B. Schiele, “How good are detection proposals, really?” British Machine Vision Conference, 2014.
[17]Y. Hu, P. C. Loizou, "Subjective comparison and evaluation of speech enhancement algorithms," Speech communication 49 (7) (2007) 588-601.
[18]Martin Riedmiller and Heinrich Braun. “A direct adaptive method for faster backpropagation learning: The RPROP algorithm,” Proceedings of the IEEE International Conference on Neural Networks, San Francisco, CA, April 1993.
[19]J. Dai, K. He, and J. Sun, “Instance-aware semantic segmentation via multi-task network cascades, ” arXiv:1512.04412, 2015
[20]J. Tchorz and B. Kollmeier, “SNR estimation based on amplitude modulation analysis with applications to noise suppression,” IEEE Trans. Speech Audio Process, vol. 11, no. 3, pp. 184–192, May 2003.
[21]A. Krizhevsky, I. Sutskever, and G. Hinton, “Imagenet classification with deep convolutional neural networks” Information Processing Systems (NIPS), 2012.