Scribd
Upload
9 views9 pages

Hog - 2

The document outlines the process of using Histograms of Oriented Gradients (HOG) for human detection, detailing steps such as computing gradients, binning them by orientation, and normalizing blocks. It compares R-HOG blocks to SIFT descriptors, highlighting differences in computation and orientation alignment. Additionally, it provides specifics on cell and block sizes, normalization techniques, and the resulting descriptor sizes for various template dimensions.

Uploaded by

Shravan A P
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
9 views9 pages

Hog - 2

The document outlines the process of using Histograms of Oriented Gradients (HOG) for human detection, detailing steps such as computing gradients, binning them by orientation, and normalizing blocks. It compares R-HOG blocks to SIFT descriptors, highlighting differences in computation and orientation alignment. Additionally, it provides specifics on cell and block sizes, normalization techniques, and the resulting descriptor sizes for various template dimensions.

Uploaded by

Shravan A P
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/ 9

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.
Standard HOG visualization shows orientations
Some guy named Juergen’s visualizations
shows gradient vectors
Pictorial Example of HOG for Human Detection
*

(a) average gradient image over training examples


(b) each “pixel” shows max positive SVM weight in the block centered on that pixel
(c) same as (b) for negative SVM weights
(d) test image
(e) its R-HOG descriptor
(f) R-HOG descriptor weighted by positive SVM weights
(g) R-HOG descriptor weighted by negative SVM weights
Details from More Recent Work
• A cell is of 8x8 pixels. A block is of 2x2 cells.
• For each cell, construct a 9-bin orientation histogram.
• Contrast normalize each histogram using 4
adjacent/overlapping blocks, giving 36 numeric values for cell.
• Total descriptor size depends on what template size you want.
• If your template (say for a car) is 8 x 10 cells, the descriptor
size would be 8x10x36 = 2880 values per window.
• For whole images, they are typically resized to 100 x 100
pixels, discretized to 10 x 10 cells, so 10x10x36 = 3600 values.
• Visualizations tend to plot only the first 9 dimensions of the
36 dimensions per cell.

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