Scribd
Upload
13 views6 pages

Another Descriptor: Histograms of Oriented Gradients For Human Detection

The document describes the Histogram of Oriented Gradients (HOG) method for human detection. It computes gradients in image regions and assigns them to orientation bins, grouping cells into blocks. The blocks are normalized and used to train classifiers to detect human parts. Key aspects covered include gradient and cell histogram computation, block formation, block normalization techniques, comparisons to SIFT descriptors, and a pictorial example of the process.

Uploaded by

DoMinhSang
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
13 views6 pages

Another Descriptor: Histograms of Oriented Gradients For Human Detection

The document describes the Histogram of Oriented Gradients (HOG) method for human detection. It computes gradients in image regions and assigns them to orientation bins, grouping cells into blocks. The blocks are normalized and used to train classifiers to detect human parts. Key aspects covered include gradient and cell histogram computation, block formation, block normalization techniques, comparisons to SIFT descriptors, and a pictorial example of the process.

Uploaded by

DoMinhSang
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 6

Another Descriptor

Histograms of Oriented
Gradients for Human Detection
Navneet Dalal and Bill Triggs
CVPR 2005

Overview
1. Compute gradients in the region to be described
2. Put them in bins according to orientation
3. Group the cells into large blocks

4. Normalize each block


5. Train classifiers to decide if these are parts of a human

Details
Gradients
[-1 0 1] and [-1 0 1]T were good enough.
Cell Histograms
Each pixel within the cell casts a weighted vote for an
orientation-based histogram channel based on the values
found in the gradient computation. (9 channels worked)

Blocks
Group the cells together into larger blocks, either R-HOG
blocks (rectangular) or C-HOG blocks (circular).

More Details
Block Normalization
They tried 4 different kinds of normalization.
Let be the block to be normalized and e be a small constant.

R-HOG compared to SIFT Descriptor


R-HOG blocks appear quite similar to the SIFT descriptors.
But, R-HOG blocks are computed in dense grids at some
single scale without orientation alignment.

SIFT descriptors are computed at sparse, scale-invariant


key image points and are rotated to align orientation.

Pictorial Example
*

(a)
(b)
(c)
(d)
(e)
(f)
(g)

average gradient image over training examples


each pixel shows max positive SVM weight in the block centered on that pixel
same as (b) for negative SVM weights
test image
its R-HOG descriptor
R-HOG descriptor weighted by positive SVM weights
R-HOG descriptor weighted by negative SVM weights

You might also like