密筛与细筛？
与 sift 相比，密集 sift 实现有什么区别？一种与另一种的优点/缺点是什么？我特别谈论的是 VLFeat 的实现。
What is the difference between the dense sift implementation compare to sift? What are the advantages/disadvantages of one to another? I'm talking in particular about the VLFeat implementations.
如果你对这篇内容有疑问，欢迎到本站社区发帖提问 参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。
绑定邮箱获取回复消息
由于您还没有绑定你的真实邮箱，如果其他用户或者作者回复了您的评论，将不能在第一时间通知您！
发布评论
评论（5）
明显的区别是，使用密集 SIFT，您可以在以下位置获得 SIFT 描述符：
每个位置，而使用普通筛选时，您会在以下位置获得 SIFT 描述：
由 Lowe 算法确定的位置。
有许多应用程序需要非密集 SIFT，Lowe 的原创作品就是一个很好的例子。
有很多应用通过计算 a 获得了良好的结果
到处（密集）的描述符就是这样一个例子：this。类似于密集 SIFT 的描述符称为 HOG 或 DHOG，它们在技术上不是同一件事，但在概念上都基于梯度直方图并且非常相似。
The obvious difference is that with dense SIFT you get a SIFT descriptor at
every location, while with normal sift you get a SIFT descriptions at the
locations determined by Lowe's algorithm.
There are many applications where you require non-dense SIFT, one great example is Lowe's original work.
There are plenty of applications where good results have been obtained by computing a
descriptor everywhere (densely) one such example is this. A descriptor similar to dense SIFT is called HOG or DHOG, they are technically not the same thing but conceptually both based on histograms of gradients and are very similar.
通常，对于通用对象类别识别，使用密集特征提取而不是基于关键点的特征提取可以获得更好的结果。
Generally, for generic object category recognition, better results are obtained using dense feature extraction rather than keypoint-based feature extraction.
在 http://www.vlfeat.org/overview/dsift.html 您可以找到详细介绍了如何为 SIFT 和密集 SIFT 实现提取图像特征以及它们的执行时间的比较。 VLFeat 密集 SIFT 描述符的主要优点是速度。
在 MediaMixer 可交付版本 D1.1.2 提出了一种同时使用 SIFT 和密集 SIFT 描述符的概念检测技术，实验结果表明这种组合提供了更准确的分类。如需了解更多信息，您可以加入 MediaMixer 社区门户 http://community.mediamixer.eu/。
On http://www.vlfeat.org/overview/dsift.html you can find in detail how the image features are extracted for both SIFT and dense SIFT implementation as well as a comparison of their execution time. The main advantage of the VLFeat dense SIFT descriptor is the speed.
In MediaMixer Deliverable D1.1.2 a concept detection technique where both SIFT and dense SIFT descriptors are used is presented, and the experimental results have shown that this combination provides more accurate classification. For further information you can join the MediaMixer community portal on http://community.mediamixer.eu/.
Dense SIFT 在图像中的每个位置和尺度上收集更多特征，从而相应提高识别精度。然而，计算复杂性始终是它的一个问题（相对于正常的 SIFT）。
如果您使用 SIFT 进行分类，我建议使用具有多个核函数（用于聚类）的普通 SIFT，而不是使用具有单个线性核函数的密集 SIFT。不过，您将得到明显的速度/准确性权衡。
我建议查看这篇论文，它解释了 Big 中的实现差异-哦。
Dense SIFT collects more features at each location and scale in an image, increasing recognition accuracy accordingly. However, computational complexity will always be an issue for it (in relation to normal SIFT).
If you're using SIFT for classification, I recommend using normal SIFT with multiple kernel functions (for clustering) as oppose to using Dense SIFT with a single linear kernel function. You'll get the obvious speed/accuracy trade off, though.
I recommend checking out this paper which explains the implementation differences in Big-Oh.
您可以在 VLFeat 实现详细信息中阅读有关 DenseSIFT 的更多信息。
DenseSIFT 更快（x30-x60 加速）。
http://www.vlfeat.org/overview/dsift.html
http://www.robots.ox.ac。 uk/~vedaldi/assets/pubs/vedaldi10vlfeat-tutorial.pdf
You can read more about DenseSIFT in VLFeat implementation details.
DenseSIFT is more fast (x30-x60 speedup).
http://www.vlfeat.org/overview/dsift.html
http://www.robots.ox.ac.uk/~vedaldi/assets/pubs/vedaldi10vlfeat-tutorial.pdf