Resources of Salient Patch Features

Image Patch Detectors

·         T Lindeberg , Edge detection and ridge detection with automatic scale selection , CVPR, 1996 [IEEE link ] [IJCV98 version ]

Patch Descriptors for Image

·         Q Zhu, S Avidan , MC Yeh , KT Cheng, Fast Human Detection Using a Cascade of Histograms of Oriented Gradients , CVPR, 2006

·         S. Bileschi and L. Wolf, Image representations beyond histograms of gradients: The role of Gestalt descriptors . CVPR, 2007.

·         Bosch, A. , Zisserman , A. and Munoz, X. , Representing shape with a spatial pyramid kernel , CIVR, 2007

·         ============================= Shape Context ==============================

·         S Belongie , J Malik , J Puzicha , Shape context: A new descriptor for shape matching and object recognition , NIPS 2000. [ICCV01 Version ] [PAMI02 Version ] [webpage with code ]

·         G Mori, S Belongie , J Malik , Shape contexts enable efficient retrieval of similar shapes, CVPR, 2001

·         G Mori, J Malik , Estimating human body configurations using shape context matching, ECCV 2002

·         H Zhang, J Malik , Learning a discriminative classifier using shape context distances, CVPR 2003

·         A Thayananthan , B Stenger , PHS Torr , R Cipolla , Shape context and chamfer matching in cluttered scenes, CVPR 2003

·         =============================Angular Radial Histogram==============================

·         T. Serre , L. Wolf, S. Bileschi , M. Riesenhuber , and T. Poggio Robust Object Recognition with Cortex-like Mechanisms , PAMI, 2007.

·         Ethan. Meyers and Lior Wolf , Using Biologically Inspired Features for Face Processing , IJCV, 2008.

·         Ankur Agarwal , Bill Triggs , Multilevel Image Coding with Hyperfeatures , IJCV 2007. [ECCV 06 version ]

·         D. Song and D. Tao, Biologically Inspired Feature Manifold for Scene Classification, IEEE Transactions on Image Processing, accepted.

·         Y. Huang et al, Enhanced Biologically Inspired Model, CVPR 2008.

·         D. Song and D. Tao, C1 Units for Scene Classification, ICPR 2008.

·         ==============================Gabor, LBP ======================================

·         J-K Kämäräinen et al, Object Localisation Using Generative Probability Model for Spatial Constellation and Local Image Features, ICCV-NRTL 2007 . [Webpage with code ]

·         Chengjun  Liu , Gabor-based Kernel PCA with Fractional Power Polynomial Models for Face Recognition , PAMI, 2004.

·         Marko Heikkilä , Matti Pietikäinen , Cordelia Schmid : Description of Interest Regions with Center-Symmetric Local Binary Patterns. ICVGIP 2006. [LBP web ] [LBP code ]

·         ============================== Dense Sampled Shape Descriptor =================================

·         H. Zhang, A. Berg, , M. Maire , and J. Malik . SVM-KNN: Discriminative nearest neighbor classication for visual category recognition. In CVPR, pages 2126–2136, 2006.

Evaluations

·         C Schmid , R Mohr, C Bauckhage , Evaluation of Interest Point Detectors . IJCV 2000

Matching and Indexing Algorithms

Dimension Reduction, Vocabulary

Applications

Software and Other Resources

Peter Kovesi' s Spatitial feature detection: canny , harris , fast radial , Garbor

Edward Rosten FAST corner detector

Vincent Garcia's keypoint extraction at Matlab Central

SURF: ETH binary and an openCV implementation

SIFT on GPU . (with source code ): http://cs.unc.edu/~ccwu/siftgpu/

Optical Flow on GPU : http://openvidia.sourceforge.net/

HOG:  Dalal’s toolkit .                   windows version using OpenCV & boost .               

Sebastian Nowozin @TU-Berlin's SIFT implementation in C#

Andrea Vedaldi @UCLA's SIFT, MSER, and VL Feature Library

[irresponsible note ]: SIFT for two 800x600 im :  Gaussian (4sec) + detector (<3sec) + descriptor (40sec) + siftmatch (24sec) + plotss (17sec). MSER: several second: but not clear  feature descriptor

Gyuri  Dorkó @INRIA's scale and affine Linux binary

Vgg's affine region detectors and descriptors   (binary) and Krystian Mikolajczyk's   matching , indexing

Course and Tutorial

Cordelia Schmid and David Lowe's CVPR 03 tutorial

 

From: http://www.ifp.illinois.edu/~cao4/reading/patchbib.htm

  • 0
    点赞
  • 3
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
Salient object detection是指在图像或视频中检测出视觉上显著的对象区域。通过这种技术,我们可以确定图像中最吸引人的部分,这对于许多应用程序,如图像编辑和视频压缩,非常有用。目前有多种方法用于实现Salient object detection。 一种可能的方法是利用对象检测或对象建议方法,例如FastRCNN,来提取候选对象边界框并进一步分割出其中的显著对象。另一种方法是利用边缘信息区分不同的显著对象。这些方法可以帮助我们在图像中找到显著的对象,并提取出它们的特征。 人类在视觉上能够自然地检测到显著的场景区域,并在注意到这些区域后进一步处理以提取更丰富的高级信息。计算机视觉领域的研究者对这种能力进行了深入研究,并将其应用于解决复杂的视觉问题,如场景理解。与视觉显著性相关的其他研究方向包括显著对象检测、注视预测、对象重要性、可记忆性、场景杂乱、视频趣味性、惊奇、图像质量评估等。 不幸的是,目前对于多个输入图像上的显著对象检测的研究还比较有限。这可能是因为可用于这些问题的基准数据集有限。然而,多模态数据的可获得性正在变得越来越容易,而利用诸如时空一致性和深度等附加线索将有助于更有效地进行显著目标检测。 总的来说,Salient object detection是一种用于检测图像或视频中显著对象区域的技术,可以帮助我们理解图像中最吸引人的部分,并在许多应用中发挥重要作用。<span class="em">1</span><span class="em">2</span><span class="em">3</span> #### 引用[.reference_title] - *1* *2* *3* [【综述论文Salient Object Detection: A Survey翻译整理](https://blog.csdn.net/weixin_45875199/article/details/106626397)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v93^chatsearchT3_1"}}] [.reference_item style="max-width: 100%"] [ .reference_list ]
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值