摘要 i
ABSTRACT ii
誌 謝 iii
目錄 iv
圖目錄 vi
表目錄 viii
第一章 序論 1
1.1 研究動機 1
1.2 論文架構 2
第二章 文獻探討 2
2.1 行人辨識 ( Person Re-identification ) 2
2.1.1 基於顏色名辨識(Color Names) 3
2.1.2 基於距離度量學習(Metric Learning) 4
2.1.3 基於生成影像(Generative image) 5
2.1.4 基於局部特徵(Local feature) 6
2.2 物件偵測(Object Detection) 8
2.2.1 You Only Look Once: Unified, Real-Time Object Detection 8
2.3 實例分割(Instance Segmentation) 10
2.3.1 YOLACT: Real-time Instance Segmentation 10
2.4無監督領域自適應（Unsupervised Domain Adaptation） 12
2.4.1 Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification 12
2.5 三重損失（Triplet loss） 15
第三章 研究方法 17
3.1系統架構 18
3.1.1 行人偵測 (Person detection) 18
3.1.2 行人辨識(Person Re-identification) 19
3.1.2.1 原場域訓練(source domain training) 20
3.1.2.2 特徵提取與分群分類(Feature extraction and cluster) 21
3.1.2.3 時間資訊(Time-stamp) 22
3.2 訓練流程 23
3.2.1 訓練資料集 23
3.2.1.1 NKUST-ReID 23
3.2.1.2 Market1501 25
3.2.2 訓練過程與損失函數 26
第四章 實驗結果 27
4.1 實驗環境 27
4.2 實驗資料集 27
4.2.3 DukeMTMC-reID 27
4.2.3 MSMT17 28
4.2.4 MSMT17 Lite 28
4.3 評估方法 29
4.4 實驗結果 29
4.5行人路徑追蹤系統實作 34
第五章 結論 36
第六章 參考文獻 37

[1]D. Yi , Z. Lei , S. Liao and Stan Z. Li, “Deep Metric Learning for Person Re-identification”, ICPRS. 2014.
[2]G. Koch, R. Zemel and R. Salakhutdinov, “Siamese Neural Networks for One-shot Image Recognition”, ICML. 2015.
[3]Z. Zheng, X. Yang, Z. Yu, L. Zheng, Y. Yang and J. Kautz “Joint Discriminative and Generative Learning for Person Re-identification,” CVPR, 2019.
[4]Ian J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, Aaron Courville and Y. Bengio, “Generative Adversarial Networks,” arXiv:1406.2661, 2014.
[5]Y. Sun, L. Zheng, Y. Yang, Q. Tian and S. Wang, “Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline),” ECCV, 2017.
[6]K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” CVPR, pp. 770-778, 2016.
[7]R. Girshick, J. Donahue, T. Darrell and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” CVPR, 2014.
[8]S. Ren, K. He, R. Girshick and J. Sun, “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.,” arXiv:1506.01497, 2015.
[9]J. Redmon, S. Divvala, R. Girshick and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” arXiv:1506.02640, 2015.
[10]Andrew G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto and H. Adam, “T MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications,” arXiv:1704.04861, 2017.
[11]Z. Zou, Z. Shi, Y. Guo, and J.Ye, “Object Detection in 20 Years: A Survey Senior Member,” IEEE, 2019.
[12]C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, A. Rabinovich, “Going Deeper with Convolutions,” arXiv:1409.4842, 2014.
[13]D. Bolya, C. Zhou, F. Xiao and Y. Jae Lee, “YOLACT: Real-time Instance Segmentation,” ICCV, 2019.
[14]K. He, G. Gkioxari, P. Dollár and R. Girshick, “Mask R-CNN,” arXiv:1703.06870, 2017.
[15]W. Deng, L. Zheng, Q. Ye, Y. Yang, J. Jiao, “Similarity-preserving Image-image Domain Adaptation for Person Re-identification,” arXiv:1811.10551, 2018.
[16]E. Ristani, F. Solera, Roger S. Zou, R. Cucchiara, C. Tomasi, “Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking,” ECCV, 2016.
[17]J. Y. Zhu, T. Park, P. Isola, A. A. Efros, “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks” ICCV, 2017.
[18]L. Zheng, L. Shen, L. Tian, S. Wang, J. Wang and Q. Tian, “Scalable Person Re-Identification: A Benchmark,” ICCV, 2015.
[19]Y. Fu, Y. Wei, G. Wang, Y. Zhou, H. Shi and T. Huang, “Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification,” ICCV, 2019.
[20]E. Hoffer and N. Ailon, “Deep metric learning using Triplet network,” arXiv:1412.6622, 2014.
[21]L. Wei, S. Zhang, W. Gao, Q. Tian, “Person Transfer GAN to Bridge Domain Gap for Person Re-Identification,” CVPR, 2018.
[22]F. Schroff, D. Kalenichenko and J. Philbin, “FaceNet: A Unified Embedding for Face Recognition and Clustering,” IEEE, 2015.
[23]M. Ester, H. P. Kriegel, J. Sander, X. Xu, “A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise,” AAAI, 1996.
[24]D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” arXiv:1412.6980, 2015.
[25]S. Yeung, O. Russakovsky, G. Mori, and L. FeiFei, “Accelerating SGD with momentum for over-parameterized learning,” arXiv:1810.13395, 2018.
[26]Y. Yang, J. Yang, J. Yan, S. Liao, D. Yi and S. Z. Li, “Salient Color Names for Person Re-identification,” ECCV, 2014