夜视视频序列的彩色化方法研究
|
摘要
由于夜视图像为对比度较低的单色图像,灰度等级有限,彩色化的夜视图像可通过人眼的色彩感知获取更丰富的场景信息,从而改善场景的深度感知,提高目标识别和探测效率,减少视觉疲劳和判断时间。因此彩色夜视技术成为当前国内外夜视领域的研究热点,在军用及民用方面都有广泛应用。和静止的夜视图像相比,动态的夜视视频序列中隐藏着运动信息,将夜视视频序列彩色化可以更有效的将夜视技术服务于军用及民用。本课题在静态夜视图像彩色化的基础上,研究动态夜视视频序列的彩色化技术,从而扩大彩色夜视的实用性。
论文首先对夜视图像的成像原理给予了阐述,并介绍了夜视图像不同于普通灰度图像的特征。对夜视图像的经典彩色化算法进行了总结和探讨。
其次,针对同时获取的同一场景的红外(>700nm)和微光(<700nm)图像,提出基于颜色查找表的双波段视频彩色化算法。首先由微光与红外图像融合后通过色彩传递的方法,得到具有突出目标和清晰背景细节的自然感彩色图像,建立初步的颜色查找表,然后采用色彩修补的方式得到完整的颜色查找表。此后的双波段视频序列,在查找表中找到对应的色彩值,实现快速彩色化。由于使用颜色查找表,省去了空间转换和匹配传递的过程,计算量大大减少。并且颜色表中的颜色值是由色彩传递得到的,彩色化后的图像具有较真实的自然感。
最后,针对车载红外视频序列,提出一种快速彩色化的方法,利用轮廓特征点跟踪来获取每帧物体类别的轮廓区域,采用类别特征色彩对各区域传递色彩。首先构建各景物样本特征色彩集,以各类景物在自然彩色图像中表现出来的特征色彩,作为夜视图像中对应景物的色彩；利用改进的高效K-Means方法对红外关键帧进行聚类,得到较好的分割区域,提取轮廓特征点；通过KLT算法跟踪特征点,得到其在下一帧中的位置并及时修正,采用B样条插值进行轮廓复原,得到该帧的各类别轮廓区域。对每帧区分好的类别区域,将特征色彩按类别赋予该区域,从而给物体着上合适的颜色,实现红外视频序列的快速彩色化。实验结果表明,该方法提高了处理的速度,能够得到较理想的效果。
Natural sense of color night vision can be perceived by the human eye for richer scene information to improve the depth perception of the scene, to improve target identification and detection efficiency, to reduce visual fatigue and to determine the time. Therefore, color night vision technology has become the night vision research focus in the military and civilian aspects that widely used. Compared to static night vision image, dynamic night vision video sequence hide motion information, colorization of the night vision video sequence can be more effective serve military and civilian. This issue mainly research color night vision video sequences of dynamic technology on the basis of color of night vision image, thus expanding the usefulness of color night vision.
Firstly, this paper gives a detailed exposition on night vision imaging process, and thus a detailed explanation of night-vision image which different from the normal gray-scale image features. The classic colorization algorithms of night vision image are summarized and discussed.
Secondly, while access to the same scene for the infrared(>700nm) and low light (<700nm) images is proposed based on the color lookup table algorithm dual-band color video. First, by the low light and infrared image fusion method, after passing through the color to get outstanding goals and a clear sense of the background details of the natural color images, the establishment of the initial color lookup table, and then use color fix way to get the full color lookup table. After the dual-band video sequence, in the lookup table to find the corresponding color value, fast color-based. Then use of color lookup tables, eliminating the need for space conversion and matching transfer process, the calculation is greatly reduced. And the color values in the color table are obtained by the color transfer, color of the image with a more realistic natural sense.
Finally, we proposed a fast method to colorize the vehicle infrared video, using contour feature points to track objects in each frame to get the outline of the regional categories with category colors to transfer color for each region. First, we build the color set of each sample scene, to various types of scenery in a natural color image color characteristics shown, which corresponding to the scene as night vision color; then use of improved and efficient K-Means clustering method to segment infrared key frame, get a better partition and extract the contour feature points; by KLT feature point tracking algorithms to get their positions in the next frame and timely corrected, use B-spline interpolation to recover contours, get the frame outline of each category area. Lastly, colorize each characteristic region by category colors. Experimental results show that this method improves the processing speed and can get more satisfactory effect.
论文首先对夜视图像的成像原理给予了阐述,并介绍了夜视图像不同于普通灰度图像的特征。对夜视图像的经典彩色化算法进行了总结和探讨。
其次,针对同时获取的同一场景的红外(>700nm)和微光(<700nm)图像,提出基于颜色查找表的双波段视频彩色化算法。首先由微光与红外图像融合后通过色彩传递的方法,得到具有突出目标和清晰背景细节的自然感彩色图像,建立初步的颜色查找表,然后采用色彩修补的方式得到完整的颜色查找表。此后的双波段视频序列,在查找表中找到对应的色彩值,实现快速彩色化。由于使用颜色查找表,省去了空间转换和匹配传递的过程,计算量大大减少。并且颜色表中的颜色值是由色彩传递得到的,彩色化后的图像具有较真实的自然感。
最后,针对车载红外视频序列,提出一种快速彩色化的方法,利用轮廓特征点跟踪来获取每帧物体类别的轮廓区域,采用类别特征色彩对各区域传递色彩。首先构建各景物样本特征色彩集,以各类景物在自然彩色图像中表现出来的特征色彩,作为夜视图像中对应景物的色彩；利用改进的高效K-Means方法对红外关键帧进行聚类,得到较好的分割区域,提取轮廓特征点；通过KLT算法跟踪特征点,得到其在下一帧中的位置并及时修正,采用B样条插值进行轮廓复原,得到该帧的各类别轮廓区域。对每帧区分好的类别区域,将特征色彩按类别赋予该区域,从而给物体着上合适的颜色,实现红外视频序列的快速彩色化。实验结果表明,该方法提高了处理的速度,能够得到较理想的效果。
Natural sense of color night vision can be perceived by the human eye for richer scene information to improve the depth perception of the scene, to improve target identification and detection efficiency, to reduce visual fatigue and to determine the time. Therefore, color night vision technology has become the night vision research focus in the military and civilian aspects that widely used. Compared to static night vision image, dynamic night vision video sequence hide motion information, colorization of the night vision video sequence can be more effective serve military and civilian. This issue mainly research color night vision video sequences of dynamic technology on the basis of color of night vision image, thus expanding the usefulness of color night vision.
Firstly, this paper gives a detailed exposition on night vision imaging process, and thus a detailed explanation of night-vision image which different from the normal gray-scale image features. The classic colorization algorithms of night vision image are summarized and discussed.
Secondly, while access to the same scene for the infrared(>700nm) and low light (<700nm) images is proposed based on the color lookup table algorithm dual-band color video. First, by the low light and infrared image fusion method, after passing through the color to get outstanding goals and a clear sense of the background details of the natural color images, the establishment of the initial color lookup table, and then use color fix way to get the full color lookup table. After the dual-band video sequence, in the lookup table to find the corresponding color value, fast color-based. Then use of color lookup tables, eliminating the need for space conversion and matching transfer process, the calculation is greatly reduced. And the color values in the color table are obtained by the color transfer, color of the image with a more realistic natural sense.
Finally, we proposed a fast method to colorize the vehicle infrared video, using contour feature points to track objects in each frame to get the outline of the regional categories with category colors to transfer color for each region. First, we build the color set of each sample scene, to various types of scenery in a natural color image color characteristics shown, which corresponding to the scene as night vision color; then use of improved and efficient K-Means clustering method to segment infrared key frame, get a better partition and extract the contour feature points; by KLT feature point tracking algorithms to get their positions in the next frame and timely corrected, use B-spline interpolation to recover contours, get the frame outline of each category area. Lastly, colorize each characteristic region by category colors. Experimental results show that this method improves the processing speed and can get more satisfactory effect.
引文
[1]李才平,邹永星,杨松龄.基于微光与红外的夜视技术[J].国外电子元器件,2006,2：72-75.
[2]张敬贤,李玉丹,金伟其.微光与红外成像技术[M].北京：北京理工大学出版社,1995.
[3]卫正统.夜视技术的研究[J].中国科技信息(基础及前沿研究),2007,20：282-283.
[4]马乐梅,由大德,吴晓飞,程树昌.夜视技术的应用发展及对策[J].光电子技术与信息,1996,9(1)：34-38.
[5]Hogervorst M A, Toet A. Fast Natural Color Mapping for Night-time Imagery[J]. Information Fusion,2009, 11(1):1016-1020.
[6]武江伟,孙韶媛,张春潜.一种用于夜视视频的彩色化方法[J].微计算机信息,2010,26(10)：188-189.
[7]腾升华.黑白影像的彩色化研究[D].北京：中国科学院电子学研究所,2006(5).
[8]李志永.黑白影像彩色化研究[D].北京：中国科学院电子学研究所,2007(5).
[9]Liron Yatziv, Guillermo Sapiro. Fast image and video colorization using chrominance blending[J]. IEEE Transactions on Image Processing,2006,15(5): 1120-1129.
[10]范之国,高隽,胡良梅.夜视图像自适应彩色化融合算法[J].仪器仪表学报,2006,27(6)：732-735.
[11]郝彦斌.基于视频序列图像的运动目标检测与跟踪[D].辽宁：大连理工大学,2008(12).
[12]滕升华,谌安军.一种改进的基于过度分割的图像彩色化方法[J].电子与信息学报,2006,28(7)：1160-1164.
[131滕升华,谌安军,邹谋炎.一种基于拉普拉斯方程的图像彩色化方法[J].中国图像图形学报,2006,11(4)：545-548.
[14]白冰,吴昊,徐丹.色彩传递算法的研究[J].云南大学学报,2006,28(S2)：20-24.
[15]蔡梦.色彩转移算法的研究与实现[D].山东：山东大学,2007(4).
[16]陈昭炯,叶东毅.色彩传递中的两种源图选择算法[J].小型微型计算机系统,2006,27(5)：889-892.
[17]Yue jian, Guo Hong Li, Wei Zhang, Yao Xiang. Multi-source Color Transfer Based on Multi-labeled Decision Tree. The 9th International Conference for Young Computer Scientists.
[18]李建明,叶飞,等.一种快速灰度图像彩色化算法[J].中国图象图像学报,2007,12(3)：536-540.
[19]刘勇.关于彩色化灰度图像的算法研究及实现[D].山东：山东大学,2007.
[20]张引,饶娜,张三元,叶修梓.自动采集样本的图像颜色传递算法[J].中国图象图形学报,2005,10(10)：1258-1264.
[21]金伟其,王岭雪,赵源萌,史世明,王霞.彩色夜视成像处理算法的新进展[J].红外与激光工程,2008,37(1)：147-150.
[22]骆媛,王岭雪,金伟其,等.微光(可见光)/红外彩色夜视技术处理算法及系统进展[J].红外技术,2010,32(6)：337-344.
[23]ITT Night Vision:Enhanced night vision goggle(ENVG)AN/PSQ20-ENVG www.nightvision.com/products/military/product_pages/an_psq20_ENVG.html.2 009.
[24]Anat Levin, Dani Lisehinski, Yair Weiss. Colorization using Optimization Proceedings of ACM SIGGRAPH,2004:689-694.
[25]Guillermo Spiro. Inpainting the colors. IEEE Computer graphics and app,2005.
[26]Yan W Q, Kankanhalli M S. Colorizing infrared home videos[C]. Proceedings of the 2003 International Conference on Multimedia and ExPo,2003,2:97-100.
[27]Zhigeng Pan, Zhaohua Dong, Mingmin Zhang. A new algorithm for adding color to Video or animation Clips. The 12th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision'2004.
[28]Wang C M, Huang Y H. A novel color transfer algorithm for image sequences[J]. Journal of information Science and Engineering,2004,20(6):1039-1056.
[29]倪国强,肖蔓君,等.近自然彩色图像融合算法及其实时处理系统的发展[J].光学学报,2007,27(12)：2101-2109.
[30]史世明,王岭雪,王霞,等.一种彩色夜视实时图像融合系统[J].红外与激光工程,2006,35(S)：360-365.
[31]王岭雪,史世明,金伟其.基于YUV空间的双通道视频图像色彩传递及实时系统[J].北京理工大学学报,2007,20(3)：189-191.
[32]王岭雪,金伟其,石俊生,等.基于拮抗视觉特性的多波段彩色夜视融合方法研究[J].红外与毫米波学报,2006,25(6)：455-459.
[33]张闯.单通道双谱微光彩色夜视技术研究[D].江苏：南京理工大学,2007(12).
[34]汤红霞.单通道双谱微光融合彩色夜视方法研究[D].江苏：南京理工大学,2005(6).
[35]朱栋.双通道彩色夜视技术[D].江苏：南京理工大学,2003(3).
[36]张颖新.双通道融合彩色夜视技术研究[D].江苏：南京理工大学,2005(6).
[37]代中华,孙韶媛,许真,谷小婧.一种车载红外视频彩色化算法[J].红外技术,2010,32(10)：595-600.
[38]孙韶媛.夜视图像基于小波分析的压缩编码与融合处理研究[D].江苏：南京理工大学,2002(6).
[39]马大伟,敬忠良,孙韶媛.基于彩色传递的红外与可见光图像融合方法[J].计算机工程,2006,32(14)：172-173.
[40]D.L. Ruderman, T.W. Cronin, and C.C. Chiao. Statistics of Cone Responses to Natural Images:Implications for Visual Coding. J.Optical Soc. of America, 1998,15(8):2036-2045.
[41]Erik Reinhard, Michael Ashikhmin, Bruce Gooch, Peter Shirley. Color Transfer between Images, IEEE Computer Graphics and Applications,2001,21(5):34-41.
[42]A. Toet. Natural colour mapping for multiband nightvision imagery, Information Fusion.2003,14:155-166.
[43]T.Welsh, M. Ashikhmin, K. Mueller. Transferring color to grayscale Images[C]//Proc. ACM SIGGRAPH 2002 ACM Transactions on Graphics(Tog), 2002,21(3):277-280.
[44]A. Toet. Colorizing single band intensified nightvision images. Displays.2005, 26(1):15-21.
[45]马爽.基于融合与色彩传递的夜视图像增强技术[D].上海：东华大学,2009(1).
[46]Xiaojing Gu, Shaoyuan Sun, Jian'an Fang. Real-time color night-vision for visible and themal images, International Symposium on Intelligent Information Technology Application Workshops.2008, pp.612-615.
[47]Maarten A. Hogervorst, et al. Method for applying daytime colors to nighttime imagery in realtime[C]//Proc of SPIE,2008:697403.
[48]章毓晋.图像分割[M].北京：科学出版社,2001.
[49]王岭雪,金伟其,赵源萌,骆媛.基于颜色查找表的双波段视频快速自然感彩色融合方法.中国,专利号：201010209534.
[50]Gary Bradski & Adrian Kaebler著.于仕琪,刘瑞祯译.学习OpenCV(中文版)[M].北京：清华大学出版社,2009.
[51]Huang Kaiqi, Wang Liangsheng, Tan Tieniu. A real time object detecting and tracking system for outdoor night surveillance [J]. Pattern Recognition,2008,41 (1):432-444.
[52]崔会卿.基于聚类和距离变换的数字图像彩色化技术[D].河北：河北师范大学,2009(6).
[53]汽车夜视系统.http://www.fx.edu.sh.cn/2001tese/200213/night.htm.
[54]Alain Tremeau, Shoji Tominaga, and Konstantin's N. Plataniotis. Color in Image and Video Processing:Most Recent Trends and Future Research Directions. 2008.
[55]Dr.H.B.Kekre Sudeep D. Thepade. Color Traits Transfer to Grayscale Images. First International Conference on Emerging Trends in Engineering and Technology.
[56]Alexander Toet, Maarten A Hogervorst. Portable Real-Time Color Night Vision. Proceedings of SPIE-The International Society for Optical Engineering.2008, Vol.6974,697402.
[57]陈国群,付冬梅.基于灰度聚类算法的红外图像增强研究[J].应用光学,2007,28(2)：142-145.
[58]Tomasi C, Kanade T. Detection and tracking of point features. Carnegie Mellon University Technical Report CMU-CS-91-132, April 1991.
[59]Jianbo Shi, Carlo Tomasi. Good features to track[C]//IEEE Conference on Computer Vision and Pattern Recognition, Seattle,1994, 1(21-23):593-600.
[60]李涛.单目视图与多目视图的深度图恢复方法研究[D].北京：清华大学,2009(6).
[61]Sudipta N Sinha, Janmichael Frahm, Marc Pollefeys, etal. GPU based video feature tracking and matching:TR 06-012[R]. University of North Carolina, USA,2006.
[2]张敬贤,李玉丹,金伟其.微光与红外成像技术[M].北京：北京理工大学出版社,1995.
[3]卫正统.夜视技术的研究[J].中国科技信息(基础及前沿研究),2007,20：282-283.
[4]马乐梅,由大德,吴晓飞,程树昌.夜视技术的应用发展及对策[J].光电子技术与信息,1996,9(1)：34-38.
[5]Hogervorst M A, Toet A. Fast Natural Color Mapping for Night-time Imagery[J]. Information Fusion,2009, 11(1):1016-1020.
[6]武江伟,孙韶媛,张春潜.一种用于夜视视频的彩色化方法[J].微计算机信息,2010,26(10)：188-189.
[7]腾升华.黑白影像的彩色化研究[D].北京：中国科学院电子学研究所,2006(5).
[8]李志永.黑白影像彩色化研究[D].北京：中国科学院电子学研究所,2007(5).
[9]Liron Yatziv, Guillermo Sapiro. Fast image and video colorization using chrominance blending[J]. IEEE Transactions on Image Processing,2006,15(5): 1120-1129.
[10]范之国,高隽,胡良梅.夜视图像自适应彩色化融合算法[J].仪器仪表学报,2006,27(6)：732-735.
[11]郝彦斌.基于视频序列图像的运动目标检测与跟踪[D].辽宁：大连理工大学,2008(12).
[12]滕升华,谌安军.一种改进的基于过度分割的图像彩色化方法[J].电子与信息学报,2006,28(7)：1160-1164.
[131滕升华,谌安军,邹谋炎.一种基于拉普拉斯方程的图像彩色化方法[J].中国图像图形学报,2006,11(4)：545-548.
[14]白冰,吴昊,徐丹.色彩传递算法的研究[J].云南大学学报,2006,28(S2)：20-24.
[15]蔡梦.色彩转移算法的研究与实现[D].山东：山东大学,2007(4).
[16]陈昭炯,叶东毅.色彩传递中的两种源图选择算法[J].小型微型计算机系统,2006,27(5)：889-892.
[17]Yue jian, Guo Hong Li, Wei Zhang, Yao Xiang. Multi-source Color Transfer Based on Multi-labeled Decision Tree. The 9th International Conference for Young Computer Scientists.
[18]李建明,叶飞,等.一种快速灰度图像彩色化算法[J].中国图象图像学报,2007,12(3)：536-540.
[19]刘勇.关于彩色化灰度图像的算法研究及实现[D].山东：山东大学,2007.
[20]张引,饶娜,张三元,叶修梓.自动采集样本的图像颜色传递算法[J].中国图象图形学报,2005,10(10)：1258-1264.
[21]金伟其,王岭雪,赵源萌,史世明,王霞.彩色夜视成像处理算法的新进展[J].红外与激光工程,2008,37(1)：147-150.
[22]骆媛,王岭雪,金伟其,等.微光(可见光)/红外彩色夜视技术处理算法及系统进展[J].红外技术,2010,32(6)：337-344.
[23]ITT Night Vision:Enhanced night vision goggle(ENVG)AN/PSQ20-ENVG www.nightvision.com/products/military/product_pages/an_psq20_ENVG.html.2 009.
[24]Anat Levin, Dani Lisehinski, Yair Weiss. Colorization using Optimization Proceedings of ACM SIGGRAPH,2004:689-694.
[25]Guillermo Spiro. Inpainting the colors. IEEE Computer graphics and app,2005.
[26]Yan W Q, Kankanhalli M S. Colorizing infrared home videos[C]. Proceedings of the 2003 International Conference on Multimedia and ExPo,2003,2:97-100.
[27]Zhigeng Pan, Zhaohua Dong, Mingmin Zhang. A new algorithm for adding color to Video or animation Clips. The 12th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision'2004.
[28]Wang C M, Huang Y H. A novel color transfer algorithm for image sequences[J]. Journal of information Science and Engineering,2004,20(6):1039-1056.
[29]倪国强,肖蔓君,等.近自然彩色图像融合算法及其实时处理系统的发展[J].光学学报,2007,27(12)：2101-2109.
[30]史世明,王岭雪,王霞,等.一种彩色夜视实时图像融合系统[J].红外与激光工程,2006,35(S)：360-365.
[31]王岭雪,史世明,金伟其.基于YUV空间的双通道视频图像色彩传递及实时系统[J].北京理工大学学报,2007,20(3)：189-191.
[32]王岭雪,金伟其,石俊生,等.基于拮抗视觉特性的多波段彩色夜视融合方法研究[J].红外与毫米波学报,2006,25(6)：455-459.
[33]张闯.单通道双谱微光彩色夜视技术研究[D].江苏：南京理工大学,2007(12).
[34]汤红霞.单通道双谱微光融合彩色夜视方法研究[D].江苏：南京理工大学,2005(6).
[35]朱栋.双通道彩色夜视技术[D].江苏：南京理工大学,2003(3).
[36]张颖新.双通道融合彩色夜视技术研究[D].江苏：南京理工大学,2005(6).
[37]代中华,孙韶媛,许真,谷小婧.一种车载红外视频彩色化算法[J].红外技术,2010,32(10)：595-600.
[38]孙韶媛.夜视图像基于小波分析的压缩编码与融合处理研究[D].江苏：南京理工大学,2002(6).
[39]马大伟,敬忠良,孙韶媛.基于彩色传递的红外与可见光图像融合方法[J].计算机工程,2006,32(14)：172-173.
[40]D.L. Ruderman, T.W. Cronin, and C.C. Chiao. Statistics of Cone Responses to Natural Images:Implications for Visual Coding. J.Optical Soc. of America, 1998,15(8):2036-2045.
[41]Erik Reinhard, Michael Ashikhmin, Bruce Gooch, Peter Shirley. Color Transfer between Images, IEEE Computer Graphics and Applications,2001,21(5):34-41.
[42]A. Toet. Natural colour mapping for multiband nightvision imagery, Information Fusion.2003,14:155-166.
[43]T.Welsh, M. Ashikhmin, K. Mueller. Transferring color to grayscale Images[C]//Proc. ACM SIGGRAPH 2002 ACM Transactions on Graphics(Tog), 2002,21(3):277-280.
[44]A. Toet. Colorizing single band intensified nightvision images. Displays.2005, 26(1):15-21.
[45]马爽.基于融合与色彩传递的夜视图像增强技术[D].上海：东华大学,2009(1).
[46]Xiaojing Gu, Shaoyuan Sun, Jian'an Fang. Real-time color night-vision for visible and themal images, International Symposium on Intelligent Information Technology Application Workshops.2008, pp.612-615.
[47]Maarten A. Hogervorst, et al. Method for applying daytime colors to nighttime imagery in realtime[C]//Proc of SPIE,2008:697403.
[48]章毓晋.图像分割[M].北京：科学出版社,2001.
[49]王岭雪,金伟其,赵源萌,骆媛.基于颜色查找表的双波段视频快速自然感彩色融合方法.中国,专利号：201010209534.
[50]Gary Bradski & Adrian Kaebler著.于仕琪,刘瑞祯译.学习OpenCV(中文版)[M].北京：清华大学出版社,2009.
[51]Huang Kaiqi, Wang Liangsheng, Tan Tieniu. A real time object detecting and tracking system for outdoor night surveillance [J]. Pattern Recognition,2008,41 (1):432-444.
[52]崔会卿.基于聚类和距离变换的数字图像彩色化技术[D].河北：河北师范大学,2009(6).
[53]汽车夜视系统.http://www.fx.edu.sh.cn/2001tese/200213/night.htm.
[54]Alain Tremeau, Shoji Tominaga, and Konstantin's N. Plataniotis. Color in Image and Video Processing:Most Recent Trends and Future Research Directions. 2008.
[55]Dr.H.B.Kekre Sudeep D. Thepade. Color Traits Transfer to Grayscale Images. First International Conference on Emerging Trends in Engineering and Technology.
[56]Alexander Toet, Maarten A Hogervorst. Portable Real-Time Color Night Vision. Proceedings of SPIE-The International Society for Optical Engineering.2008, Vol.6974,697402.
[57]陈国群,付冬梅.基于灰度聚类算法的红外图像增强研究[J].应用光学,2007,28(2)：142-145.
[58]Tomasi C, Kanade T. Detection and tracking of point features. Carnegie Mellon University Technical Report CMU-CS-91-132, April 1991.
[59]Jianbo Shi, Carlo Tomasi. Good features to track[C]//IEEE Conference on Computer Vision and Pattern Recognition, Seattle,1994, 1(21-23):593-600.
[60]李涛.单目视图与多目视图的深度图恢复方法研究[D].北京：清华大学,2009(6).
[61]Sudipta N Sinha, Janmichael Frahm, Marc Pollefeys, etal. GPU based video feature tracking and matching:TR 06-012[R]. University of North Carolina, USA,2006.