Machine learning for high-speed corner detection
Machine learning for high-speed corner detection
复制标题
DOI：
10.1007/11744023_34
复制
发表时间：
2006-01-01
期刊：
影响因子：
--
通讯作者：
Drummond, Tom
中科院分区：
文献类型：
--
作者：
Rosten, Edward;Drummond, Tom
在实时帧率应用中使用特征点时，需要高速特征检测器。SIFT （DoG）、Harris和SUSAN等特征检测器是产生高质量特征的好方法，但是对于任何复杂性的实时应用来说，它们的计算量都太大。在这里，我们展示了机器学习可以用来推导一个特征检测器，它可以用不到7%的可用处理时间来完全处理实时PAL视频。通过比较，Harris检测器（120%）和SIFT检测级（300%）都不能在全帧速率下工作。显然，如果产生的特征不适合下游加工，高速检测器的用途是有限的。特别是，从两个不同的位置观看相同的场景应该产生与现实世界相同的3D位置对应的特征[1]。因此，本文的第二个贡献是基于该准则的比较角检测器应用于3D场景。这一比较支持了其他地方关于现有角落探测器的一些主张。此外，与我们最初的预期相反，我们表明，尽管主要是为了速度而构建的，但根据这一标准，我们的检测器明显优于现有的特征检测器。
Where feature points are used in real-time frame-rate applications, a high-speed feature detector is necessary. Feature detectors such as SIFT (DoG), Harris and SUSAN are good methods which yield high quality features, however they are too computationally intensive for use in real-time applications of any complexity. Here we show that machine learning can be used to derive a feature detector which can fully process live PAL video using less than 7% of the available processing time. By comparison neither the Harris detector (120%) nor the detection stage of SIFT (300%) can operate at full frame rate.Clearly a high-speed detector is of limited use if the features produced are unsuitable for downstream processing. In particular, the same scene viewed from two different positions should yield features which correspond to the same real-world 3D locations[1]. Hence the second contribution of this paper is a comparison corner detectors based on this criterion applied to 3D scenes. This comparison supports a number of claims made elsewhere concerning existing corner detectors. Further, contrary to our initial expectations, we show that despite being principally constructed for speed, our detector significantly outperforms existing feature detectors according to this criterion.