請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/70239完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 徐宏民(Winston Hsu) | |
| dc.contributor.author | Yu-An Chen | en |
| dc.contributor.author | 陳俞安 | zh_TW |
| dc.date.accessioned | 2021-06-17T04:24:39Z | - |
| dc.date.available | 2020-09-29 | |
| dc.date.copyright | 2020-09-29 | |
| dc.date.issued | 2020 | |
| dc.date.submitted | 2020-09-25 | |
| dc.identifier.citation | [1] M. Afifi and M. S. Brown. What else can fool deep learning? addressing color constancy errors on deep neural network performance. In The IEEE International Conference on Computer Vision (ICCV), October 2019. [2] T. Brooks, B. Mildenhall, T. Xue, J. Chen, D. Sharlet, and J. T. Barron. Unprocessing images for learned raw denoising. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 11036–11045, 2019. [3] Y.-L. Chang, Z. Y. Liu, K.-Y. Lee, and W. Hsu. Free-form video inpainting with 3d gated convolution and temporal patchgan. In Proceedings of the International Conference on Computer Vision (ICCV), 2019. [4] C. Chen, Q. Chen, M. N. Do, and V. Koltun. Seeing motion in the dark. In Proceedings of the IEEE International Conference on Computer Vision, pages 3185–3194, 2019. [5] C. Chen, Q. Chen, J. Xu, and V. Koltun. Learning to see in the dark. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 3291– 3300, 2018. [6] M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results. http://www.pascal-network.org/challenges/VOC/voc2012/workshop/index.html. [7] R. Girshick. Fast r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 1440–1448, 2015. 24 [8] R. Girshick, J. Donahue, T. Darrell, and J. Malik. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 580–587, 2014. [9] C. Godard, K. Matzen, and M. Uyttendaele. Deep burst denoising. In The European Conference on Computer Vision (ECCV), September 2018. [10] X. Guo, Y. Li, and H. Ling. Lime: Low-light image enhancement via illumination map estimation. IEEE Transactions on Image Processing, 26(2):982–993, 2016. [11] S. Hasinoff, D. Sharlet, R. Geiss, A. Adams, J. T. Barron, F. Kainz, J. Chen, and M. Levoy. Burst photography for high dynamic range and low-light imaging on mobile cameras. SIGGRAPH Asia, 2016. [12] K. He, G. Gkioxari, P. Dollár, and R. Girshick. Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 2961–2969, 2017. [13] 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, pages 770–778, 2016. [14] M. Jaderberg, K. Simonyan, A. Zisserman, et al. Spatial transformer networks. In Advances in neural information processing systems, pages 2017–2025, 2015. [15] H. Jiang and Y. Zheng. Learning to see moving objects in the dark. In Proceedings of the IEEE International Conference on Computer Vision, pages 7324–7333, 2019. [16] K. Johnson. Capturing linear images. http://people.csail.mit.edu/kimo/blog/linear.html. [17] T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár. Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision, pages 2980–2988, 2017. [18] T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. L. Zitnick. Microsoft coco: Common objects in context. In European conference on computer vision, pages 740–755. Springer, 2014. 25 [19] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C. Berg. Ssd: Single shot multibox detector. In European conference on computer vision, pages 21–37. Springer, 2016. [20] K. G. Lore, A. Akintayo, and S. Sarkar. Llnet: A deep autoencoder approach to natural low-light image enhancement. Pattern Recognition, 61:650–662, 2017. [21] F. Lv, F. Lu, J. Wu, and C. Lim. Mbllen: Low-light image/video enhancement using cnns. In BMVC, page 220, 2018. [22] Omid-Zohoor, Alex, Ta, David, Murmann, and Boris. Pascalraw: Raw image database for object detection, 2014. [23] A. Omid-Zohoor, C. Young, D. Ta, and B. Murmann. Toward always-on mobile object detection: Energy versus performance tradeoffs for embedded hog feature extraction. IEEE Transactions on Circuits and Systems for Video Technology, 28(5):1102–1115, 2017. [24] S. Ratnasingam. Deep camera: A fully convolutional neural network for image signal processing. In Proceedings of the IEEE International Conference on Computer Vision Workshops, pages 0–0, 2019. [25] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi. You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 779–788, 2016. [26] J. Redmon and A. Farhadi. Yolo9000: better, faster, stronger. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 7263–7271, 2017. [27] J. Redmon and A. Farhadi. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767, 2018. 26 [28] S. Ren, K. He, R. Girshick, and J. Sun. Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems, pages 91–99, 2015. [29] O. Ronneberger, P. Fischer, and T. Brox. U-net: Convolutional networks for biomedical image segmentation. ArXiv, abs/1505.04597, 2015. [30] E. Schwartz, R. Giryes, and A. M. Bronstein. Deepisp: Toward learning an end-toend image processing pipeline. IEEE Transactions on Image Processing, 28(2):912–923, 2018. [31] J. A. Stark. Adaptive image contrast enhancement using generalizations of histogram equalization. IEEE Transactions on image processing, 9(5):889–896, 2000. [32] N.-S. Syu, Y.-S. Chen, and Y.-Y. Chuang. Learning deep convolutional networks for demosaicing. arXiv preprint arXiv:1802.03769, 2018. [33] C. Wei, W. Wang, W. Yang, and J. Liu. Deep retinex decomposition for low-light enhancement. arXiv preprint arXiv:1808.04560, 2018. [34] X. Xu, Y. Ma, and W. Sun. Towards real scene super-resolution with raw images. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1723–1731, 2019. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/70239 | - |
| dc.description.abstract | 物件偵測被廣泛運用在監視器、自動駕駛等領域。近來來受益於深度學習，物件偵測技術有突破性的進展，然而低光環境會對此技術造成的不良影響，使得現存在JPG圖片上的方法容易失敗，導致既有的應用的成效不彰。為此我們提出第一個在RAW圖片上的端對端訓練物件偵測模型。並且基於影像訊息處理流水線提出新穎的架構—— ConvISP，透過預測影像訊息處理的參數，來達到最適化低光環境的影像處理流程。廣泛的實驗結果說明此架構使得物件偵測在不同程度低光環境仍能成功運作。 | zh_TW |
| dc.description.abstract | Object detection has been applied in many areas, including security, surveillance, automated vehicle systems, and so on. In recent years, the deep learning-based approaches for solving objection detection have achieved great success. However, the performance deterioration under low-light conditions, which makes the existing algorithms trained on JPG images prone to fail, is inevitable in real-world applications (e.g., adverse weather conditions). To this end, we propose the first end-to-end trainable object detection model on RAW images. Inspired by the Image Signal Processing (ISP) pipeline, we design one novel component called \emph{ConvISP}, which aims at predicting ISP parameters. Extensive experimental results demonstrate that the proposed framework works well under low light conditions in different degrees. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-17T04:24:39Z (GMT). No. of bitstreams: 1 U0001-1608202014371700.pdf: 6133238 bytes, checksum: d57f4f84a36b643658f8d25a3628593c (MD5) Previous issue date: 2020 | en |
| dc.description.tableofcontents | 誌謝 iii 摘要 iv Abstract v 1 Introduction 1 2 Related Works 4 2.1 CNN-based Object Detection . . . . . . . . . . . . . . . . . . . . . . . . 4 2.2 Low Light Image Enhancement . . . . . . . . . . . . . . . . . . . . . . . 4 2.3 Image Enhancement on RAW Images . . . . . . . . . . . . . . . . . . . 5 2.4 Image Signal Processing (ISP) . . . . . . . . . . . . . . . . . . . . . . . 6 3 Proposed Method 7 3.1 Low-light RAW Object Detection Framework . . . . . . . . . . . . . . . 7 3.2 ConvISP . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 3.3 Parameter Prediction Network . . . . . . . . . . . . . . . . . . . . . . . 8 3.3.1 ConvGain . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 3.3.2 ConvWB . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 3.3.3 ConvCCM . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 3.4 Loss Functions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 3.4.1 Classification Loss . . . . . . . . . . . . . . . . . . . . . . . . . 10 3.4.2 Regression Loss . . . . . . . . . . . . . . . . . . . . . . . . . . 10 3.4.3 Training Procedure . . . . . . . . . . . . . . . . . . . . . . . . . 10 4 Experiments 11 4.1 Datasets . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 4.1.1 PASCALRAW . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 4.1.2 COCO-photoscan-tiny . . . . . . . . . . . . . . . . . . . . . . . 11 4.1.3 Synthetic Global/Local Low Light Data . . . . . . . . . . . . . . 11 4.2 Implementation Detail . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 4.3 Quantitative Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 4.3.1 Performance of Detection between RAW and JPG on PASCALRAW / COCO-photoscan-tiny . . . . . . . . . . . . . . . . . . . 13 4.3.2 Address Low Light Detection Difficulty . . . . . . . . . . . . . . 13 4.3.3 Light Augmentation as a Solution to Reduce Low-light Domain Gap . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 4.3.4 Low Light Image Enhancement Methods as a Solution to Low Light Detection . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 4.3.5 Learning-based ISP Architecture Comparison . . . . . . . . . . . 16 4.3.6 Speed and VRAM Comparison . . . . . . . . . . . . . . . . . . 16 4.3.7 Comparison between ConvISP and JPG Encoder . . . . . . . . . 16 4.4 Gernalizability Test . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 4.5 Failure Case . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 5 Conclusion and Future Work 23 Bibliography 24 | |
| dc.language.iso | en | |
| dc.subject | 低光圖像增強 | zh_TW |
| dc.subject | 物件偵測 | zh_TW |
| dc.subject | 影像訊息處理 | zh_TW |
| dc.subject | Object Detection | en |
| dc.subject | Low-light Image Enhancement | en |
| dc.subject | Image Signal Processing | en |
| dc.title | 使用原始圖檔於低光環境物件偵測 | zh_TW |
| dc.title | Towards Robust Low-light Object Detection on RAW Images | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 109-1 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 陳文進(Wen-Chin Chen),葉梅珍(Mei-Jhen Ye) | |
| dc.subject.keyword | 物件偵測,低光圖像增強,影像訊息處理, | zh_TW |
| dc.subject.keyword | Object Detection,Low-light Image Enhancement,Image Signal Processing, | en |
| dc.relation.page | 27 | |
| dc.identifier.doi | 10.6342/NTU202003580 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2020-09-25 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-1608202014371700.pdf 未授權公開取用 | 5.99 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。