SIFT,SURF,ORB,FAST,BRISK 特征提取算法比较

 

原文：http://blog.csdn.net/vonzhoufz/article/details/46594369

图像处理的基础就是要进行特征点的提取，feature(interest points) detect 的方法也在不断的进步，边检测，角点检测，直线检测，圆检测，SIFT特征点检测，同时描述符也在发展，为了匹配的高效，逐渐从高维特征向量到二进制向量…下面做一个简单的罗列，并调用opencv API看看效果！
承接上一篇文章。

Feature Detection Methods List:

• Canny Edge Detect, A Computational Approach to Edge Detection, 1986. The Canny edge detector is an edge detection operator that uses a multi-stage algorithm to detect a wide range of edges in images.
• Harris, A combined corner and edge detector, 1988. considering the differential of the corner score with respect to direction directly.
• GFTT，Good Features to Track,1994, Determines strong corners on an image.
• Matas-2000, Robust Detection of Lines Using the Progressive Probabilistic Hough Transform. 霍夫变换检测直线.
• SIFT,Distinctive Image Features from Scale-Invariant Keypoints,2004, invariant to image translation, scaling, and rotation, partially invariant to illumination changes and robust to local geometric distortion. 128-dim(512B).
• SURF, Speeded Up Robust Features,2006,受SIFT启发，比SIFT快，健壮. 64-dim(256B).
• FAST ,Machine Learning for High-speed Corner Detection, 2006,wiki. Very fast, not robust to high level noise.
• ORB, ORB: an efficient alternative to SIFT or SURF,2011，基于FAST和BRIEF，比SIFT快两个数量级，可作为SIFT的替代(a fusion of FAST keypoint detector and BRIEF descriptor). 32B binary descriptor.
• BRISK，BRISK: Binary Robust Invariant Scalable Keypoints, 2011 . 64B binary descriptor.
• STAR，Censure: Center surround extremas for realtime feature detection and matching,2008,引用次数不高.scale-invariant center-surround detector (CENSURE) that claims to outperform other detectors and is capable of real-time implementation.
• MSER，Robust Wide Baseline Stereo from Maximally Stable Extremal Regions, 2002, 斑点检测(blob detection).

特征点提取算法比较(image dataset(27 pictures)):

ImageNO	SIFT	SURF	ORB	FAST	STAR	BRISK
0	2414	4126	500	11978	715	1538
1	4295	8129	500	16763	1166	1861
2	3404	4784	500	16191	816	1445
3	1639	2802	500	7166	203	699
4	1510	1484	497	29562	2383	3421
5	10572	8309	500	720	0	65
6	191	187	295	16125	825	1782
7	3352	4706	500	567	15	43
8	165	403	374	26701	1558	2762
9	4899	7523	500	12780	473	1299
10	1979	4212	500	10676	864	1498
11	3599	3294	500	663	0	70
12	163	168	287	7923	661	953
13	1884	2413	500	11681	548	2683
14	2509	5055	500	18097	1671	2898
15	9177	4773	500	7224	842	888
16	3332	3217	500	20502	1381	2612
17	5446	6611	500	16553	683	1959
18	4592	6033	500	706	54	216
19	266	509	459	9613	356	583
20	2087	2786	500	7459	223	607
21	2582	3651	500	12147	720	1530
22	2509	4237	500	14890	507	1113
23	1236	4545	500	6473	410	718
24	1311	2606	500	4293	199	491
25	237	387	500	657	122	132
26	968	1418	488	6609	45	343
Time Cost	21.52	17.4	0.97	0.25	2.34	2.14

上面是通过一些图片集测的单单是feature detect 的时间，接下来通过一对图片看看feature detect和compute feature descriptor总共花费的时间开销（秒）：

Image pair	SIFT	SURF	ORB	FAST(SURF)
eiffel-1,13.jpg	2.77	3.22	0.11	0.22

可以看到计算descriptor的开销还是很大的，这里仅仅两张图片，所以主要开始是计算描述符，提取是很快的。

下面通过通过两张图片来看这几个算法匹配的效果，1639-1311-697表示图片1，2分别提取了1639，1311个keypoints，其中匹配的有697个。

Image pair	SIFT	SURF	ORB	FAST(SURF)	BRISK
eiffel-1,13.jpg	1639/1311/697	2802/2606/1243	500/500/251	1196/1105/586	607/491/287

---

Canny Edge Detection效果：

Find line segments by probabilistic Hough transform：

Harris Corner Detection：

SIFT match效果图：

SURF match效果图：

ORB match效果图：

BRISK match效果图：

---

代码在这里

---

参考：
Canny Edge Detector Example
Feature Detection-Canny, HoughLinesP
Harris corner detector Example
BRIEF (Binary Robust Independent Elementary Features)
ORB (Oriented FAST and Rotated BRIEF)

<style></style>