Back to timeline

Research · June 2005

Gradient histograms find pedestrians

In June 2005 Navneet Dalal and Bill Triggs showed that a dense grid of histograms of oriented gradients, normalised over overlapping blocks and fed to a linear support vector machine, detects people in images at least ten times more accurately than existing feature sets. Alongside the method they released the INRIA Person set of 1805 human images at 64 by 128 pixels.

Why it matters

Detecting objects of variable shape acquired a feature good for something harder than a face. The Viola-Jones method worked on faces because faces are alike; a person in an arbitrary pose does not yield to that, and HOG held this position until convolutional detectors arrived.

The settings the paper calls its default: 9 orientation bins over 0 to 180 degrees, 16 by 16 pixel blocks of four 8 by 8 cells, a 64 by 128 detection window, a block stride of 8 pixels, L2-Hys normalisation. The best result in the sweep over geometries comes from different sizes: 3 by 3 cell blocks of 6 by 6 pixel cells give a 10.4 percent miss rate at 10 to the minus 4 false positives per window. The record does not attribute 10.4 percent to the default setting: these are two separate lines in the paper, and the figure belongs to 3 by 3 blocks of 6 by 6 cells, not to 16 by 16 blocks of 8 by 8 cells. The INRIA Person set holds 1805 images, not 1807. It was made because on the older MIT set of 509 training and 200 test images the detector gave essentially perfect separation — that is, the set had stopped measuring anything. The paper puts the comparison with other features this way: HOG-based detectors give at least an order of magnitude reduction in false positives per window on the INRIA set against the authors' own implementations of Haar wavelets, PCA-SIFT and shape contexts.

Event record

Event date
June 2005
Timeline date
Event date
Verification
Sources gathered automatically · September 21, 2026
Lines
ID
evt-0499

CVPR 2005, San Diego, pages 886-893. The month and the span of the conference, 20 to 25 June 2005, come from a UC San Diego news release of 22 June 2005; the day of the talk is not fixed.

Sources

Related events

Records that link to this one