Histograms of Oriented Gradients for Human Detection | VitaVision
PaperCVPR · 2005

Histograms of Oriented Gradients for Human Detection

Navneet DalalBill Triggs
DOIView in graph
1page built on it
3more pages cite it
2narratives
4registry papers cite it

In the Atlas

AlgorithmPrimary source of
HOG: Histograms of Oriented Gradients

Compute a fixed-length descriptor for an image window by binning pixel gradients into 8×8 cells of 9 unsigned-orientation histograms, normalising overlapping 2×2-cell blocks with L2-Hys, and concatenating the 3780 block values into a single vector fed to a linear SVM — the canonical pre-CNN pedestrian detector.

Cited as a reference by 3 pages, grouped by domain

Detection 2
Deformable Part ModelsYOLOv1
Features 1
Feature Descriptors

Appears in 2 narratives

NarrativeDetection, Removing the MachineryNarrativeWhere Did the Inductive Bias Go?

Lineage

Papers in the Atlas registry only · one dot per paper
Built upon by · 4
’04’05’06’07’08’09’10’11’12’13’14’15’16’17Object Detection with Discriminatively Trained Part-Based Models (2010)You Only Look Once: Unified, Real-Time Object Detection (2016)Feature Pyramid Networks for Object Detection (2017)Focal Loss for Dense Object Detection (2017)Distinctive Image Features from Scale-Invariant Keypoints (2004)