keyword
HOG descriptors
Histogram of Oriented Gradients descriptors are visual feature descriptors used in computer vision and image processing to characterize the appearance and shape of objects within digital images. The method functions by capturing the distribution of local intensity gradients and edge directions across an image. To extract these features, an image is divided into small, connected spatial regions called cells, and a histogram of gradient orientations is compiled for the pixels within each cell. These local histograms are subsequently normalized for contrast across larger, overlapping groups of cells called blocks to ensure resilience against variations in illumination and shadowing. The concatenated normalized histograms form a comprehensive feature vector that effectively represents structural contours and shapes, making it widely utilized in object recognition applications such as pedestrian and human detection.
2 items
Human Detection Using Oriented Histograms of Flow and Appearance
Navneet Dalal, Bill Triggs, Cordelia Schmid
Why you should read this
Combines oriented histograms of differential optical flow with Histogram of Oriented Gradient appearance descriptors to achieve a tenfold reduction in false alarms for video-based human detection in complex dynamic scenes.
Detecting humans in films and videos is a challenging problem owing to the motion of the subjects, the camera and the background and to variations in pose, appearance, clothing, illumination and background clutter. We develop a detector for standing and moving people in videos with possibly moving cameras and backgrounds, testing several different motion coding schemes and showing empirically that orientated histograms of differential optical flow give the best overall performance. These motion-based descriptors are combined with our Histogram of Oriented Gradient appearance descriptors. The resulting detector is tested on several databases including a challenging test set taken from feature films and containing wide ranges of pose, motion and background variations, including moving cameras and backgrounds. We validate our results on two challenging test sets containing more than 4400 human examples. The combined detector reduces the false alarm rate by a factor of 10 relative to the best appearance-based detector, for example giving false alarm rates of 1 per 20,000 windows tested at 8% miss rate on our Test Set 1.
Added
2026-09-18
Histograms of Oriented Gradients for Human Detection
Navneet Dalal, Bill Triggs
Why you should read this
Demonstrates that a simple dense grid of locally normalized histogram-based orientation features dramatically outperforms existing methods for detecting people in images, establishing a practical and interpretable foundation for robust visual object recognition.
We study the question of feature sets for robust visual object recognition; adopting linear SVM based human detection as a test case. After reviewing existing edge and gradient based descriptors, we show experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection. We study the influence of each stage of the computation on performance, concluding that fine-scale gradients, fine orientation binning, relatively coarse spatial binning, and high-quality local contrast normalization in overlapping descriptor blocks are all important for good results. The new approach gives near-perfect separation on the original MIT pedestrian database, so we introduce a more challenging dataset containing over 1800 annotated human images with a large range of pose variations and backgrounds.
Added
2026-02-21