[PDF] Histograms of oriented gradients for human detection | Semantic Scholar (2024)

It is shown that the combination of the cascade of rejectors approach and the HoG features led to a fast and accurate human detection system and the integral image representation was used and the rejection cascade significantly speeded up the computation.

This work integrates the cascade-of-rejectors approach with the Histograms of Oriented Gradients (HoG) features to achieve a fast and accurate human detection system that can process up to 30 frames per second while maintaining an accuracy level similar to existing methods.

The Histogram of Oriented Gradients descriptors show experimentally significantly out-performs existing feature sets for human detection and are chosen to extract human feature from visible spectrum images based on OpenCv and MS VC++.

This research adopts annular spatial bins type cells and applies radial gradient transform (RGT) to attain gradient binning invariance for feature descriptors and significantly enhances HOG with respect to rotation-invariant ability and feature descripting accuracy.

A human detection framework based on an enhanced version of Histogram of Oriented Gradients features, which outperforms the integral of oriented histograms allowing the calculation of a single feature four times faster.

A new feature descriptor called scale space histogam of oriented gradients (SS-HOG) is designed, which encodes more information to discriminate human bodies from other object types than traditional uni-scale HOGs.

Comparative experiments show that though HOG is simple feature descriptor, the proposed HOG feature achieves good results with much lower computational time.

This work uses AdaBoost algorithm to learn local characteristics of human based on HOGs and adopts the head contour as the global feature for improving the detection accuracy.

The new representation, called sketchable-HoG, extends the classical histogram of oriented gradients (HoG) feature by adding two different aspects: the stability of the majority orientation and the continuity of gradient orientations.

A salience representation for pedestrian detection, Histograms-Of-Salience (HOS) is proposed and investigated, extracted saliency map learned from data by using Histogram Based Contrast, and aggregate salient value and oriented gradients to form local HOS.

...

...

A human detection framework based on an enhanced version of Histogram of Oriented Gradients features, which outperforms the integral of oriented histograms allowing the calculation of a single feature four times faster.

This paper examines (and improves upon) the local image descriptor used by SIFT, and demonstrates that the PCA-based local descriptors are more distinctive, more robust to image deformations, and more compact than the standard SIFT representation.

A trainable object detector achieves reliable and efficient detection of human faces and passenger cars with out-of-plane rotation.

This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.

This work builds on Forsyth & Fleck's general 'body plan' methodology and Felzenszwalb & Huttenlocher's dynamic programming approach for efficiently assembling candidate parts into 'pictorial structures' but replaces the rather simple part detectors used in these works with dedicated detectors learned for each body part using SupportVector Machines (SVMs) or Relevance Vector Machines (RVMs).

It is observed that the ranking of the descriptors is mostly independent of the interest region detector and that the SIFT-based descriptors perform best and Moments and steerable filters show the best performance among the low dimensional descriptors.

This pedestrian detection system is the first to combine both sources of information in a single detector, and operates on low resolution images under difficult conditions (such as rain and snow).

A method to recognize hand gestures, based on a pattern recognition technique developed by McConnell employing histograms of local orientation, which is simple and fast to compute, and which can distinguish a small vocabulary of about 10 hand gestures.

...

...