Scribd
Upload
96 views11 pages

Histograms of Oriented Gradients For Human Detection N. Dalal and B. Triggs CVPR 2005

The document describes the steps of the Histogram of Oriented Gradients (HOG) algorithm for human detection. [1] HOG extracts features by dividing an image into small spatial regions called cells and computing histograms of gradient directions for pixels within each cell. [2] It then normalizes and concatenates the histograms into a feature vector for use in classification. [3] Key steps include computing gradients, quantizing orientations into bins, accumulating votes in each spatial block, and concatenating block histograms into the final feature vector.

Uploaded by

SudhagarSubbiyan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
96 views11 pages

Histograms of Oriented Gradients For Human Detection N. Dalal and B. Triggs CVPR 2005

The document describes the steps of the Histogram of Oriented Gradients (HOG) algorithm for human detection. [1] HOG extracts features by dividing an image into small spatial regions called cells and computing histograms of gradient directions for pixels within each cell. [2] It then normalizes and concatenates the histograms into a feature vector for use in classification. [3] Key steps include computing gradients, quantizing orientations into bins, accumulating votes in each spatial block, and concatenating block histograms into the final feature vector.

Uploaded by

SudhagarSubbiyan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 11

Histograms of Oriented Gradients for Human Detection

(HOG)
N. Dalal and B. Triggs
CVPR 2005
Cited by 6021

2
Dr. Edgar Seemann 3
HOG Steps
HOG feature extraction
Compute centered horizontal and vertical gradients with no smoothing
Compute gradient orientation and magnitudes
For color image, pick the color channel with the highest gradient magnitude for each
pixel.

For a 64x128 image,


Divide the image into 16x16 blocks of 50% overlap.
7x15=105 blocks in total
Each block should consist of 2x2 cells with size 8x8.
Quantize the gradient orientation into 9 bins
The vote is the gradient magnitude
Interpolate votes between neighboring bin center.
The vote can also be weighted with Gaussian to downweight the pixels near the edges
of the block.
Concatenate histograms (Feature dimension: 105x4x9 = 3,780)
Computing Gradients
f ( x h) f ( x h )
Centered: f ' ( x) lim h0
2h

Filter masks in x and y directions


-1
Centered: -1 0 1 0
1

Gradient

Magnitude: s s x2 s y2

Orientation: s
arctan( y )
sx

5
Blocks, Cells
Block 2
Block 1
16x16 blocks of 50% overlap.
7x15=105 blocks in total

Each block should consist of 2x2


cells with size 8x8.

Cells
Votes
Each block consists of 2x2 cells with
size 8x8
Quantize the gradient orientation into 9 9 Bins

bins (0-180)

The vote is the gradient magnitude


Bin centers

Interpolate votes linearly between neighboring bin


centers.
Example: if =85 degrees.
Distance to the bin center Bin 70 and Bin 90
are 15 and 5 degrees, respectively.
Hence, ratios are 5/20=1/4, 15/20=3/4.

The vote can also be weighted with Gaussian to


down weight the pixels near the edges of the block.
Final Feature Vector
Concatenate histograms
Make it a 1D vector of length 3780.

Visualization

8
How to Select Different Parameters?

9
Results

Navneet Dalal and Bill Triggs Histograms of Oriented Gradients for


Human Detection CVPR05
SIFT Vs HOG

SIFT HOG
128 dimensional vector 3,780 dimensional vector
16 by 16 window 64 by 128 window
4x4 sub-window (16 total) 16 by 16 blocks with
8 bin histogram overlap
Each block consists of 2 by
2 cells each of 8 by 8
Overlapping
9 bin histogram

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy