研究生: |
張丞賦 Cheng-Fu Chang |
---|---|
論文名稱: |
以FPGA實現即時除霧系統 A Real-Time Dehazing System Implemented on FPGA |
指導教授: |
王乃堅
Nai-Jian Wang |
口試委員: |
呂學坤
Shyue-Kung Lu 鍾順平 Shun-Ping Chung 郭景明 Jing-Ming Guo 曾德峰 Der-Feng Tseng |
學位類別: |
碩士 Master |
系所名稱: |
電資學院 - 電機工程系 Department of Electrical Engineering |
論文出版年: | 2021 |
畢業學年度: | 109 |
語文別: | 中文 |
論文頁數: | 65 |
中文關鍵詞: | 影像除霧 、暗通道先驗 、FPGA 、即時 |
外文關鍵詞: | Dehaze, Dark Channel Prior, FPGA, Real-Time |
相關次數: | 點閱:217 下載:0 |
分享至: |
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 |
隨著科技迅速的發展,電腦視覺輔助系統已在生活中越來越普遍,以自動駕駛無人車為例,自駕車上裝載著影像感應器,並藉由影像感應器所拍攝到的畫面進行偵測與分類辨識,而若自駕車行駛於惡劣的環境下,可能因為鏡頭拍攝擷取到的畫面不夠清晰,行車電腦對分辨物體的能力下降導致判斷錯誤。因此為了使感測系統提高辨識正確率並隨時擁有一張清晰的場景影像,讓錯誤判讀導致事故的發生率降至最低成了一件重要的研究課題。
對於影像前處理的方面,探討如何從一個有霧的環境,將拍攝後的影像做到即時除霧並反饋於使用者。在做除霧前,我們必須得到一張有霧的圖像,並從圖像中分析因大氣懸浮粒子所產生的介質穿透率圖,再去估計整張圖片大氣光線的來源,最後將上述三者都帶入到大氣散射模型當中,便能從物理角度上還原出無霧圖像。
本篇論文會以色彩衰減先驗的方法,去訓練一組線性模型的係數,最後將除霧演算法實現在FPGA(Field Programmable Gate Array)上,當硬體接收到影像序列的輸入,首先將影像序列做縮小,並由序列中計算深度圖,從深度圖的資訊還原介質穿透率,在透過大氣光線的估計,並藉由大氣散射模型將一幅有霧圖像還原成去霧圖像。
實驗結果顯示此方法可成功從攝影鏡頭輸入並將除霧後的影像顯示輸出至螢幕上,實驗結果顯示了本系統使用了19,877(17%)個邏輯元件和3,133,376(79%)bits內部記憶體,且處理速度達到每秒175張影像(NTSC Input)。
Computer vision assistance systems have become more and more common in life. For example, the smart car is equipped with an image sensor, and the image captured by the image sensor is used for detection. If a smart car is driving in a harsh environment, it may be that the captured image is not clear enough, and the ability to distinguish objects may be reduced, resulting in judgment errors. Therefore, in order to make the sensing system have a clear scene image, improving the recognition accuracy and reducing the probability of accidents have become an important issue.
Before dehazing, we must obtain a haze image, and analyze the medium transmission map caused by atmospheric suspended particles from the image. Estimate the source of atmospheric light in the entire image, and brought into the atmospheric scattering model, then the haze-free image can be recovered.
This paper will use the color attenuation prior method to train a set of linear model coefficients. The dehazing algorithm will be displayed on the FPGA (Field Programmable Gate Array). When the hardware receives the input of the image sequence, and the depth map is calculated from the image sequence. The medium transmission map is restored from the information of the depth map. After the estimation of atmospheric light, a haze image is restored by the atmospheric scattering model.
Experimental results show that this method can successfully input from the camera and output the dehazed image to the screen, and the processing speed can reach 175 frames per second (NTSC Input).
[1] K. He, J. Sun, and X. Tang, “Single image haze removal using dark channel prior,” IEEE transactions on pattern analysis and machine intelligence, vol. 33, no. 12, pp. 2341–2353, 2010.
[2] T. K. Kim, J. K. Paik, and B. S. Kang, “Contrast enhancement system using spatially adaptive histogram equalization with temporal filtering,” IEEE Transactions on Consumer Electronics, vol. 44, no. 1, pp. 82–87, 1998.
[3] J. A. Stark, “Adaptive image contrast enhancement using generalizations of histogram equalization,” IEEE Transactions on image processing, vol. 9, no. 5, pp. 889–896, 2000.
[4] J.-Y. Kim, L.-S. Kim, and S.-H. Hwang, “An advanced contrast enhance- ment using partially overlapped sub-block histogram equalization,” IEEE transactions on circuits and systems for video technology, vol. 11, no. 4, pp. 475–484, 2001.
[5] Y. Y. Schechner, S. G. Narasimhan, and S. K. Nayar, “Instant dehazing of images using polarization,” in Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, vol. 1. IEEE, 2001, pp. I-325-I-332.
[6] S. Shwartz, E. Namer, and Y. Y. Schechner, “Blind haze separation,” in 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’06), vol. 2. IEEE, 2006, pp. 1984–1991.
[7] Y. Y. Schechner, S. G. Narasimhan, and S. K. Nayar, “Polarization-based vision through haze,” Applied optics, vol. 42, no. 3, pp. 511–525, 2003.
[8] S. G. Narasimhan and S. K. Nayar, “Chromatic framework for vision in bad weather,” in Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No. PR00662), vol. 1. IEEE, 2000, pp. 598–605.
[9] S. K. Nayar and S. G. Narasimhan, “Vision in bad weather,” in Proceedings of the Seventh IEEE International Conference on Computer Vision, vol. 2. IEEE, 1999, pp. 820–827.
[10] S. G. Narasimhan and S. K. Nayar, “Contrast restoration of weather degraded images,” IEEE transactions on pattern analysis and machine intelligence, vol. 25, no. 6, pp. 713–724, 2003.
[11] “Interactive (de) weathering of an image using physical models,” in IEEE Workshop on color and photometric Methods in computer Vision, vol. 6, no. 6.4. France, 2003, p. 1.
[12] J.Kopf, B. Neubert, B. Chen, M. Cohen, D. Cohen-Or, O. Deussen, M. Uyttendaele, and D. Lischinski, “Deep photo: Model-based photo- graph enhancement and viewing,” ACM transactions on graphics (TOG), vol. 27, no. 5, pp. 1–10, 2008.
[13] R. T. Tan, “Visibility in bad weather from a single image,” in 2008 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2008, pp. 1–8.
[14] R. Fattal, “Single image dehazing,” ACM transactions on graphics (TOG), vol. 27, no. 3, pp. 1–9, 2008.
[15] K. B. Gibson, D. T. Vo, and T. Q. Nguyen, “An investigation of dehazing effects on image and video coding,” IEEE transactions on image processing, vol. 21, no. 2, pp. 662–673, 2011.
[16] J. Yu, C. Xiao, and D. Li, “Physics-based fast single image fog removal,” in IEEE 10th International Conference on Signal Processing Proceedings. IEEE, 2010, pp. 1048–1052.
[17] Q. Zhu, S. Yang, P. A. Heng, and X. Li, “An adaptive and effective single image dehazing algorithm based on dark channel prior,” in 2013 IEEE International Conference on Robotics and Biomimetics (ROBIO). IEEE, 2013, pp. 1796–1800.
[18] J.-P. Tarel and N. Hautiere, “Fast visibility restoration from a single color or gray level image,” in 2009 IEEE 12th International Conference on Computer Vision. IEEE, 2009, pp. 2201–2208.
[19] J.-P. Tarel and N. Hautiere, L. Caraffa, A. Cord, H. Halmaoui, and D. Gruyer “Vision enhancement in homogeneous and heterogeneous fog,” IEEE Intelligent Transportation Systems Magazine, vol. 4, no. 2, pp. 6–20, 2012.
[20] Q. Zhu, J. Mai, and L. Shao, “A fast single image haze removal algorithm using color attenuation prior,” IEEE transactions on image processing, vol. 24, no. 11, pp. 3522–3533, 2015.
[21] E. J. McCartney, “Optics of the atmosphere: scattering by molecules and particles,” New York, 1976.
[22] S.G.Narasimhan and S.K.Nayar, “Vision and the atmosphere,” International journal of computer vision, vol. 48, no. 3, pp. 233–254, 2002.
[23] S.G.Narasimhan and S.K.Nayar, “Removing weather effects from monochrome images,” in Pro- ceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, vol. 2. IEEE, 2001, pp. II-186-II-193.
[24] Codruta O.Ancuti, Cosmin Ancuti, Radu Timofte, Christophe De Vleeschouwer, "O-haze: a dehazing benchmark with real hazy and haze-free outdoor images." Proceedings of the IEEE conference on computer vision and pattern recognition workshops. 2018.
[25] Codruta O.Ancuti, Cosmin Ancuti, Radu Timofte, Christophe De Vleeschouwer, "I-HAZE: a dehazing benchmark with real hazy and haze-free indoor images." International Conference on Advanced Concepts for Intelligent Vision Systems. Springer, Cham, 2018.
[26] Terasic DE-115 datasheet URL:http://www.terasic.com.tw/tw/
[27] Sony EVI-D70 技術手冊 URL:http://pro.sony/en_GR/products/ptz-network-cameras/evi-d70-d70p-pal-