本論文的研究動機在於物件偵測與追蹤的運作探討與原理分析，研究目的主要在於行人的影像偵測與追蹤上，了解現有的物件分類的演算法及數據庫，同時改良出新演算法以達到的較高的物件匹配度。本文中所改良的物件辨識演算法主要以Faster R-CNN為主，對行人影像目標進行物件追蹤，過程中也會與現有的演算法做分析比較取得研究的可行性與可靠度。

The motivation of research of this paper lies in the discussion and principal analysis of the operation of object detection and tracking. The research purpose is mainly on pedestrian image detection and tracking, to understand the existing object classification algorithms and databases, and to improve new algorithms to Achieved higher object matching degree. The improved object recognition algorithm in this article is mainly based on Faster R-CNN, which performs object tracking on pedestrian image targets. In the process, it will also be analyzed and compared with existing algorithms to obtain the feasibility and reliability of the research.

[1] Zhengxia Zou, Keyan Chen, Zhenwei Shi, , Yuhong Guo, and Jieping Ye, “Object Detection in 20 Years: A Survey”, 2023 Computer Vision and Pattern Recognition (CV 2023), arXiv:1905.05055, 2023.
[2] Saad ALBAWI , Tareq Abed MOHAMMED, Saad AL-ZAWI, “Understanding of a Convolutional Neural Network”, 2017 International Conference on Engineering and Technology (ICET 2017), 2017.
[3] Navneet Dalal and Bill Triggs, “Histograms of oriented gradients for human detection”, 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR’05), vol. 1. IEEE, 2005.
[4] Renwei Tu, Zhongjie Zhu, and Yongqiang Bai, “Improved Pedestrian Detection Algorithm Based on HOG and SVM”, Computational Intelligence and Neuroscience, pp. 211-221, 2020.
[5] Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation”, 2014 Conference on Computer Vision and Pattern Recognition (CCVPR 2014), vol. 5, Oct 2014.
[6] C. Papageorgiou, M. Oren, and T. Poggio, “A general framework for object detection,” Proceedings of the IEEE International Conference on Computer Vision, 1998.
[7] D. G. Lowe, “Object recognition from local scale-invariant features,” Proceedings of the IEEE International Conference on Computer Vision, 1150-1157, 1999.
[8] C. Cortes, V. Vapnik, “Support-vector networks,” Machine Learning volume 20, 273–297, https://doi.org/10.1007/BF00994018, 1995.
[9] B. Alexe, T. Deselaers, and V. Ferrari, "Measuring the Objectness of Image Windows," in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 34, 2189-2202, 2012.
[10] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi et al, “You only look once: Unified, real-time object detection.” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
[11] Simon Varailhon, Masih Aminbeidokhti, Marco Pedersoli, Eric Granger, “Source-Free Domain Adaptation for YOLO Object Detection”, 2024 Computer Vision and Pattern Recognition (CV 2024), arXiv:2409.16538, 2024.
[12] N. Bodla, B. Singh, R. Chellappa, and L. S. Davis, “Soft-NMS – Improving Object Detection With One Line of Code,” in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
[13] Shahran Rahman Alve, “Deep Learning and Hybrid Approaches for Dynamic Scene Analysis, Object Detection and Motion Tracking”, 2024 Computer Vision and Pattern Recognition (CV 2024), arXiv:2412.05331 ,2024.
[14] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C. Y. Fu, and A. C. Berg, “SSD: Single Shot MultiBox Detector,” arXiv:1512.02325, 2016.
[15] S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards real-time object detection with region proposal networks.” arXiv:1506.01497v3, 2015.
[16] Xingxu Yao, Sicheng Zhao, Pengfei Xu, Jufeng Yang, “Multi-Source Domain Adaptation for Object Detection”, 2021 Computer Vision and Pattern Recognition (CV 2021), arXiv:2106.15793, 2021.
[17] R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” arXiv:1311.2524, 2014.
[18] J. R. R. Uijlings, K. E. A. van de Sande, T. Gevers, and A. W. Smeulders, “Selective search for object recognition,” International Journal of Computer Vision (IJCV), 2013.
[19] K. He; X. Zhang, S. Ren, and J. Sun, “Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition,” arXiv:1406.4729, 2015.
[20] R. Girshick, “Fast R-CNN.” Proceedings of the IEEE International Conference on Computer Vision, 1440-1448, 2015.
[21] S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards real-time object detection with region proposal networks.” arXiv:1506.01497v3, 2015.
[22] Jan Hosang, Rodrigo Benenson, and Bernt Schiele, “Learning non-maximum suppression” arXiv:1705.02950v2, 2017.
[23] K. Simonyan, A. Zisserman, “Very Deep Convolutional Networks for Large- Scale Image Recognition”, arXiv:1409.1556, 2014.
[24] A. Rosebrock, “Intersection over Union (IoU) for object detection,” Diambil kembali dari PYImageSearch, 2016.
[25] Biplov Paneru, Bishwash Paneru, Krishna Bikram Shah, “Analysis of Convolutional Neural Network-based Image Classifications: A Multi-Featured Application for Rice Leaf Disease Prediction and Recommendations for Farmers”, 2024 Computer Vision and Pattern Recognition (CV 2024), 2024.
[26] Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg, Li Fei-Fei, “ImageNet Large Scale Visual Recognition Challenge”, 2015 Computer Vision and Pattern Recognition (CV 2015), arXiv:1409.0575, 2015.
[27] Saining Xie, Ross Girshick, Piotr Dollár, Zhuowen Tu, Kaiming He, “Aggregated Residual Transformations for Deep Neural Networks”, Accepted to CVPR 2017, arXiv:1611.05431, 2016.
[28] Mattzheng, “for Dataset Caltech Pedestrian”, GitHub, https://github.com/mattzheng/forDataset_CaltechPedestrian, May 2017.