hog size & aspect ratio

Target Parameter Set It is favorable to work with as few as possible parameters defining the target state. Small amount of parameters that can still describe well the dynamics of the target will tend to converge faster, and therefore fewer hypotheses would be needed in each step.   — HoG-Model based Human Tracking and Irregular Behavior Detection

The size of the object bounding box may vary greatly as well. Objects close to the camera would occupy more pixels than ones further away. However the aspect ratio of the bounding box is assumed to be constant, therefore it is possible to treat it with one parameter – width, rather than two (width and height). The walking appearance in the HoG feature manifold is treated with one parameter – sample index. In each iteration we look for a manifold sample of a chosen distance and direction from the current sample, therefore one dimensional sample index is a sufficient descriptor, if the neighborhood graph of the HoG features of the training data is known.

Blocks should better be vary in size, location, and aspect ratio.

Just use the trained classifier to convolve with the HoG feature pyramid at multiple scales for each image, to evaluate all the sub-windows of each image. The number of pyramid levels controls the size of possible detected windows in the image.

HOG advantages:

首先,由于HOG方法是在图像的局部细胞单元上操作,所以它对图像几何的(geometric)和光学的 (photometric)形变都能保持很好的不变性,这两种形变只会出现在更大的空间领域上。


HOG的思路正如paper所言来源于SIFT和Shape Context,将SIFT的sparse feature应用到dense feature,同时具有了目标的表象和形状(appearance and shape)。

R- HOG跟SIFT描述器看起来很相似,但他们的不同之处是:R-HOG是在单一尺度下、密集的网格内、没有对方向排序的情况下被计算出来(are computed in dense grids at some single scale without orientation alignment);而SIFT描述器是在多尺度下、稀疏的图像关键点上、对方向排序的情况下被计算出来(are computed at sparse scale-invariant key image points and are rotated to align orientation)。补充一点,R-HOG是各区间被组合起来用于对空域信息进行编码(are used in conjunction to encode spatial form information),而SIFT的各描述器是单独使用的(are used singly)。


Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s




Just another WordPress.com site

Jing's Blog

Just another WordPress.com site

Start from here......







Just another WordPress.com site

Where On Earth Is Waldo?

A Project By Melanie Coles

the Serious Computer Vision Blog

A blog about computer vision and serious stuff

Cauthy's Blog

paper review...

Cornell Computer Vision Seminar Blog

Blog for CS 7670 - Special Topics in Computer Vision


Life through nerd-colored glasses

Luciana Haill

Brainwaves Augmenting Consciousness



Dr Paul Tennent

and the university of nottingham

turn off the lights, please

A bunch of random, thinned and stateless thoughts around the Web

%d bloggers like this: