{"title":"Focus measures for SFF-inspired relative depth estimation","authors":"R. Senthilnathan, R. Sivaramakrishnan","doi":"10.1109/MVIP.2012.6428791","DOIUrl":null,"url":null,"abstract":"Shape from Focus (SFF) is a method which recovers the 3D geometry of the scene based on a sequence of images taken from different focus distances between the camera and the object. Generally SFF techniques require parallel projection of the scene on to the image plane so that the corresponding pixels in the set of images taken are easily identified. This can be achieved by using a lens which does parallel projection such as a telecentric lens. Moreover the SFF method is widely applied for extremely small objects due to the limited range of magnification that can be maintained. This again is another manifestation of the fact depth of objects produce perspective shift (generally called as structure-dependent pixel motion) in the image plane. All these facts are applicable for situations which utilizes SFF for complete reconstruction of the scene. Applications involving shape information extracted from focus as a secondary cue need not require a complete dense reconstructed information from SFF. Such applications might allow usage of wide angle lenses where the projection is basically a perspective projection of the scene on to the image plane. The research work utilizes a wide angle lens for SFF based scene reconstruction consisting of a macroscopic object. The paper is an attempt to present 24 different focus measures used for quantifying image focus from which depth is interpolated using a standard function. Since the images in the sequence suffer from changes in magnification, finding the correspondence itself is an issue worth addressing. The pixel motion is tackled by a powerful corner detector and a robust matching algorithm. The knowledge of the right focus measure is very important since it is after all from the focus measure depth of the scene is interpolated. The focus measures presented in the paper are a collection from various applications such as microscopy imaging, auto focussing, holographic reconstructions etc., but applied to an image sequence containing variations in focus and magnification.","PeriodicalId":170271,"journal":{"name":"2012 International Conference on Machine Vision and Image Processing (MVIP)","volume":"58 36","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2012 International Conference on Machine Vision and Image Processing (MVIP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/MVIP.2012.6428791","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
Shape from Focus (SFF) is a method which recovers the 3D geometry of the scene based on a sequence of images taken from different focus distances between the camera and the object. Generally SFF techniques require parallel projection of the scene on to the image plane so that the corresponding pixels in the set of images taken are easily identified. This can be achieved by using a lens which does parallel projection such as a telecentric lens. Moreover the SFF method is widely applied for extremely small objects due to the limited range of magnification that can be maintained. This again is another manifestation of the fact depth of objects produce perspective shift (generally called as structure-dependent pixel motion) in the image plane. All these facts are applicable for situations which utilizes SFF for complete reconstruction of the scene. Applications involving shape information extracted from focus as a secondary cue need not require a complete dense reconstructed information from SFF. Such applications might allow usage of wide angle lenses where the projection is basically a perspective projection of the scene on to the image plane. The research work utilizes a wide angle lens for SFF based scene reconstruction consisting of a macroscopic object. The paper is an attempt to present 24 different focus measures used for quantifying image focus from which depth is interpolated using a standard function. Since the images in the sequence suffer from changes in magnification, finding the correspondence itself is an issue worth addressing. The pixel motion is tackled by a powerful corner detector and a robust matching algorithm. The knowledge of the right focus measure is very important since it is after all from the focus measure depth of the scene is interpolated. The focus measures presented in the paper are a collection from various applications such as microscopy imaging, auto focussing, holographic reconstructions etc., but applied to an image sequence containing variations in focus and magnification.
SFF (Shape from Focus)是一种基于相机与物体之间不同聚焦距离拍摄的一系列图像来恢复场景三维几何形状的方法。一般来说,SFF技术需要将场景平行投影到图像平面上,这样就可以很容易地识别出所拍摄的图像集合中的相应像素。这可以通过使用像远心透镜这样的平行投影透镜来实现。此外,由于可保持的放大倍率范围有限,SFF方法被广泛应用于极小物体。这也是物体深度在图像平面上产生透视位移(通常称为与结构相关的像素运动)的另一种表现。所有这些事实都适用于利用SFF完成场景重建的情况。从焦点中提取形状信息作为次要线索的应用程序不需要从SFF中获得完整的密集重构信息。这样的应用可能允许使用广角镜头,其中投影基本上是场景在图像平面上的透视投影。本研究利用广角镜头进行由宏观物体组成的基于SFF的场景重建。本文试图提出24种不同的焦点测量方法,用于量化图像焦点,并使用标准函数插值深度。由于序列中的图像受到放大倍数变化的影响,因此找到对应关系本身就是一个值得解决的问题。采用强大的角点检测器和鲁棒匹配算法处理像素运动。正确对焦度量的知识是非常重要的,因为它毕竟是从对焦度量中插值出景深的。本文提出的聚焦测量是各种应用的集合,如显微镜成像、自动聚焦、全息重建等,但适用于包含聚焦和放大倍数变化的图像序列。