Description: 二维图像视觉显著性检测，效果非常好。California Institute of Technology的
Jonathan Harel写的，很经典。-Two-dimensional image saliency detection, the effect was very good. California Institute of Technology' s Jonathan Harel written, very classic. Platform: |
Size: 1052672 |
Author:jiashijie |
Hits:
Description: 该文件夹包括代码及其对应的论文。其作用在于模拟人类视觉系统的生理特性--视觉注意机制，按照人眼观察外界的方式，检测视觉显著性物体和区域，并阐述了显著性区域的显著性密度和尺度之间的关系，可应用于生物视觉模拟、视觉目标检测、视觉目标跟踪、视觉智能监控，以及视觉生理学和视觉心理学等的研究中。-This document contains codes and the corresponding paper. The aim is to simulate a physiological characteristic of human visual system called visual attention mechanism. The code is used to detect salient objects or regions following the way human eye observes the world. The relation between density and scale of salient object/region is described. It has found widespread use in numerous applications such as biological vision simulation, visual object detection, visual object tracking, visual intelligent surveillance, visual physiological, and visual psychology. Platform: |
Size: 4237312 |
Author:朱亮亮 |
Hits:
Description: 基于上下文注意的显著区域检测，附件包括代码和英文文章。-Context-Aware Saliency Detection. The file includes the paper and the source code in matlab. Platform: |
Size: 4486144 |
Author:于子予 |
Hits:
Description: 本代码为清华大学程明明在2011年CVPR上发表的一篇视觉显著性的源代码。-It is the source code of visual saliency detection proposed by M.M Cheng in CVPR2011, which is coded by C++. Platform: |
Size: 27437056 |
Author:wang |
Hits:
Description: 这是论文“Context-Aware Saliency Detection”的matlab代码，已执行通过。-This is the code of the paper“Context-Aware Saliency Detection”，and it has been run successfully. Platform: |
Size: 417792 |
Author: |
Hits:
Description: 介绍了一种显著性检测，程序可以直接运行，可以得到显著图像，有图像源。-propose a bottom-up visual saliency detection algorithm. Different most previous methods that mainly concentrate on image object, we take both background and foreground into consideration. Platform: |
Size: 24430592 |
Author:吴韦佳 |
Hits:
Description: 《Saliency Detection: A Spectral Residual Approach》是上交高材生侯晓迪在07年的CVPR上发表的一篇论文，这篇文章提出了一个图像视觉显著性的简单计算模型，这个模型和Irri提出的模型是两个截然不同的模型，Irri模型对于图像视觉显著性主要关注整幅图片突出的部分，通过各种特征的融合提取显著性图，而Hou的这个模型一上来关注的点就不在一张图片里突出的地方，而是背景，观察是否大部分图片的背景在某个空间上都满足什么变化，最后剔除背景，自然就只剩下图片突出的部分了-" Saliency Detection: A Spectral Residual Approach" is turned on in the top students HOU Xiao Di 07 years CVPR paper published, this article presents a significant visual image of a simple calculation model, the model and the model proposed is two Irri distinct model, Irri model for the image saliency focused on the entire picture projecting portion extracted by the integration of the various features saliency map, and Hou this model up a point of interest in a picture is not prominent in place, but the background to observe whether the majority of the background image on a space to meet any changes, and finally removing the background, naturally, only the image projecting part Platform: |
Size: 1592320 |
Author:garth88 |
Hits:
Description: saliency detection,the ability of human visual system to detect visual saliency is extraordinarily fast and reliable. However, computational modeling of this basic intelligent behavior still remains a challenge.-saliency detection Platform: |
Size: 247808 |
Author:王五 |
Hits:
Description: 提出一种新的显着性检测方法，通过将区域级显着性估计和像素级显着性预测与CNN（表示为CRPSD）相结合。对于像素级显着性预测，通过修改VGGNet体系结构来执行完全卷积神经网络（称为像素级CNN）以执行多尺度特征学习，基于该学习进行图像到图像预测以完成像素级显着性检测。对于区域级显着性估计，首先设计基于自适应超像素的区域生成技术以将图像分割成区域，基于该区域通过使用CNN模型（称为区域级CNN）来估计区域级显着性。通过使用另一CNN（称为融合CNN）融合像素级和区域级显着性以形成nal显着图，并且联合学习像素级CNN和融合CNN。对四个公共基准数据集的大量定量和定性实验表明，所提出的方法大大优于最先进的显着性检测方法。-A new saliency detection method by significant regional level estimates and forecast significant pixel level and CNN (expressed as CRPSD) combined. For pixel-level significant prediction to perform a full convolution neural network by modifying VGGNet architecture (called pixel-level CNN) learning to perform multi-scale features, image to image prediction to complete the pixel level detection based on the significant learning . For regional levels significantly estimate, the first generation technology to design image is divided into regions based on adaptive super-pixel area, based on the model of the region through the use of CNN (CNN called regional level) to estimate regional levels significantly. By using another CNN (CNN called fusion) Fusion pixel level and regional level to form nal significant saliency map, and the Joint Learning pixel level fusion CNN and CNN. Four common reference data set of a large number of quantitative and qualitative experiments show that the proposed m Platform: |
Size: 4427776 |
Author:祖祖- |
Hits:
Search - Saliency detection