Scene parsing method toward low-light-level/infrared color night vision
-
摘要: 彩色夜视技术可以将微光/红外双谱图像融合成一幅适于人眼观察的彩色图像，而恰当的场景解析方法能够对彩色夜视图像的内容做出自动化分析，进一步减轻人眼的观测负担。针对彩色夜视场景丰富多变、对算法灵活性要求高的特点，提出了一种可在线扩展的场景解析方法。该方法基于非参数模型，预测景物类别时不需要训练过程，只需要使用数据库中具有语义标记的样本图像， 通过将待解析图像与样本图像进行全局及局部匹配来实现语义标签的传递。而且，数据库可以根据应用场景的不同随时进行动态扩充。实验结果表明：该方法在包含城市、乡野等多种场景的夜视图像上，以及由统计色彩映射、TNO、NRL等多种融合方法得到的、具有不同色彩表征的彩色夜视图像上都具有令人满意的准确率。Abstract: Color night vision technology is able to fuse the dual-spectral image of low-light-level and infrared image into a color one suited to human observation. Furthermore, a appropriate scene parsing method on the color night vision image could additionally facilitate human observation by providing automatic content analysis. An online scalable scene parsing method was proposed aiming at the rich and changeable color night vision in practice which required algorithms with high flexibility. The proposed method was based on a non-parametric model that needed no training process when predicting scene categories. It matched the query image and the sample images in database using both global and local features, and then transfered semantic labels of the best-match samples to the query image. Moreover, the database can be dynamically expanded according to different usage scenarios. The experimental results show that proposed method achieves satisfactory accuracies on color night vision images that obtained by a variety of color night vision methods, including the statistical color mapping,TNO, and NRL, throughout diverse scenes, including cities, countryside and others.
-
Key words:
- color night vision /
- scene parsing /
- nonparametric model /
- superpixels feature /
- Markov random field
-
[1] Toet A, Ijspeert J K, Waxman A M, et al. Fusion of visible and thermal imagery improves situational awareness[J]. Displays, 1997, 18(2):85-95. [2] Zou X T, Bhanu B. Tracking humans using multi-modal fusion[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005. [3] Michael A, Irvine J M. Information fusion for feature extraction and the development of geospatial information[C]//Proceeding of the 7th International Conference on Information Fusion, 2004:976-982. [4] Bulanon D M, Burks T F, Alchanatis V. Image fusion of visible and thermal images for fruit detection[J]. Biosytems Engineering, 2009, 103(1):12-22. [5] Jiang Dong, Zhang Dafang, Huang Yaohuan, et al. Survey of multispectral image fusion techniques in remote sensing applications[C]//Image Fusion and Its Applications, 2011:1-22. [6] Daneshvar S, Ghassemian H. MRI and PET image fusion by combining IHS and retina-inspired models[J]. Information Fusion, 2010, 11(2):114-123. [7] He Xuming, Zemel R S, Carreira-Perpinan M A. Multiscale conditional random fields for image labeling[C]//Proceedings IEEE Conference Computer Vision and Pattern Recognition, 2004, 2:695-702. [8] Ladicky L, Sturgess P, Alahari K, et al. What, where and how many combining object detectors and CRFs[C]//Proceedings European Conference Computer Vision, 2010:424-437. [9] Galleguillos C, Mcfee B, Belongie S, et al. Multi-class object localization by combining local contextual interactions[C]//Proceedings IEEE Conference Computer Vision and Pattern Recognition, 2010:113-120. [10] Gould S, Fulton R, Koller D. Decomposing a scene into geometric and semantically consistent regions[C]//Proceedings IEEE International Conference Computer Vision, 2009:1-8. [11] Divvala S, Hoiem D, Hays J, et al. An empirical study of context in object detection[C]//Proceedings IEEE Conference Computer Vision and Pattern Recognition, 2009:1271-1278. [12] Felzenszwalb P, Mcallester D, Ramanan D A. Discriminatively trained multiscale deformable part model[C]//Proceedings IEEE Conference Computer Vision and Pattern Recognition, 2008:1-8. [13] Farabet C, Couprie C, Najman L, et al. Learning hierarchical features for scene labeling[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(8):1915-1929. [14] Rahul M. Deep deconvolutional networks for scene parsing[J]. Computer Science, 2014, ArXiv:1411. 4101. -
点击查看大图
计量
- 文章访问数: 528
- HTML全文浏览量: 86
- PDF下载量: 138
- 被引次数: 0
下载:
