Edge Boxes论文浅读和EdgeBoxes Matlab代码功能函数浅析

【承接图像分类、检测、分割、生成相关项目，私信。】

论文《Edge Boxes: Locating Object Proposals from Edges》ECCV2014，微软研究院，Piotr。

文章没有涉及到“机器学习”，采用的是纯图像的方法。

研究目的：作者为了加速现有目标检测算法，提出了一种能够以较高精度确定proposal的新方法。

研究方法：利用边缘信息（Edge），确定box内的轮廓个数和与box边缘重叠的edge个数（知道一个box内完全包含的轮廓个数，那么目标有很大可能性，就在这个box中）,基于此对box进行评分，进一步根据得分的高低顺序确定proposal信息（由大小，长宽比，位置构成）。而后续工作就是在proposal内部运行相关检测算法。

Edge Boxes的Matlab代码功能函数说明

Edge Boxes的Matlab代码托管在Github上：https://github.com/pdollar/edges
本文旨在记录其各函数的功能说明,这部分说明在Contents.m中有记录！
原文如下：

Structured Edge detector code:
edgesChns - Compute features for structured edge detection.
edgesDemo - Demo for Structured Edge Detector (please see readme.txt first).
edgesDemoRgbd - Demo for RGBD Structured Edge Detector (please see readme.txt first).
edgesDetect - Detect edges in image.
edgesSweeps - Parameter sweeps for structured edge detector.
edgesTrain - Train structured edge detector.
Edge detection evaluation code:
edgesEval - Run and evaluate structured edge detector on BSDS500.
edgesEvalDir - Calculate edge precision/recall results for directory of edge images.
edgesEvalImg - Calculate edge precision/recall results for single edge image.
edgesEvalPlot - Plot edge precision/recall results for directory of edge images.
Edge Boxes object proposal generation code:
edgeBoxes - Generate Edge Boxes object proposals in given image(s).
edgeBoxesDemo - Demo for Edge Boxes (please see readme.txt first).
edgeBoxesSweeps - Parameter sweeps for Edges Boxes object proposals.
Object proposal evaluation code:
boxesData - Get ground truth data for object proposal bounding box evaluation.
boxesEval - Perform object proposal bounding box evaluation and plot results.
Sticky Edge Adhesive Superpixel code:
spDemo - Demo for Sticky Superpixels (please see readme.txt first).
spDetect - Detect Sticky Superpixels in image.
spAffinities - Compute superpixel affinities and optionally corresponding edge map.

简单翻译一下：

Edge 检测代码的组成:
edgesChns - 计算图像特征用以检测
edgesDemo - 运行会生成边缘检测的图，灰度图，效果挺好的。 (参考readme.txt).

edgesDemoRgbd - 训练用的.
edgesDetect - 检测图像中的edges.
edgesSweeps - Parameter sweeps for structured edge detector.
edgesTrain - 训练edge检测器
Edge detection evaluation code:
edgesEval - 运行 and 计算 edge on BSDS500.
edgesEvalDir - Calculate edge precision/recall results for directory of edge images.
edgesEvalImg - Calculate edge precision/recall results for single edge image.
edgesEvalPlot - Plot edge precision/recall results for directory of edge images.
Edge Boxes object proposal generation code:
edgeBoxes - 检测Edge的功能函数，用以检测给定图片中可能的Edge.
edgeBoxesDemo - Edge检测测试代码，有调用edgeBoxes.m这个函数 (please see readme.txt first).
edgeBoxesSweeps - Parameter sweeps for Edges Boxes object proposals.
Object proposal evaluation code:
boxesData - Get ground truth data for object proposal bounding box evaluation.
boxesEval - Perform object proposal bounding box evaluation and plot results.
Sticky Edge Adhesive Superpixel code:
spDemo - Demo for Sticky Superpixels (please see readme.txt first).
spDetect - Detect Sticky Superpixels in image.
spAffinities - Compute superpixel affinities and optionally corresponding edge map.