Accelerating Histograms of Oriented Gradients descriptor extraction for pedestrian recognition

Lee, Seung Eun; Min, Kyung-Won; Suh, Taeweon

doi:10.1016/j.compeleceng.2013.04.001

Cited by 28 publications

(13 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has become very successful in diverse domains such as face, pedestrian, and onroad vehicle detection (Déniz et al, 2011;Lee et al, 2013;Arróspide et al, 2013). The HOG descriptor is originally defined as the distribution of the local intensity gradients from an image, which are computed from small connected regions (cells).…”

Section: Histograms Of Oriented Gradients (Hog)mentioning

confidence: 99%

See 1 more Smart Citation

Recognition of handwritten characters using local gradient feature descriptors

Surinta

Karaaba

Schomaker

et al. 2015

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

Section: Histograms Of Oriented Gradients (Hog)mentioning

confidence: 99%

“…Finally, the feature descriptors are normalized by applying the L2 block normalization (Lee et al, 2013) as follows:…”

Section: Histograms Of Oriented Gradients (Hog)mentioning

confidence: 99%

Recognition of handwritten characters using local gradient feature descriptors

Surinta

Karaaba

Schomaker

et al. 2015

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

“…In such implementation the memory footprint grows accordingly to the size of the 2D LUT, and consequently to the gradient resolution. More recently, in [6] the polar conversion is computed implementing both the arc-tangent and the square-root functions with iterative hardware operations, thus reducing significantly the data throughput.…”

Section: Introductionmentioning

confidence: 99%

HOG-Dot: A Parallel Kernel-Based Gradient Extraction for Embedded Image Processing

Maggiani

Bourrasset

Petracca

et al. 2015

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

International audienceIn this paper we propose HOG-Dot, a method for the direct computation of the polar image gradients coordinates from the pixels values. The proposed algorithm, to be used as the first step of the Histogram of Oriented Gradient (HOG) pipeline, approximates the exact gradient with its projection onto a versor chosen among the projection plane set. Instead of non linear computations, the HOG-Dot method exploits linear operations while introducing a bounded approximation error with respect to other HOG approaches, thus resulting a more suitable solution for embedded devices. Concerning the state of the art, it also achieves improved accuracy with the mathematical spatial gradient formulation

show abstract

“…It is in fact a greyscale image feature formed by a set of normalized gradient histograms [29]. The HoG descriptor has performed well in many object recognition problems including pedestrian recognition, human detection applications, body part detection and smile recognition [29,[34][35][36][37].…”

Section: Histogram Of Oriented Gradientsmentioning

confidence: 99%

“…For instance, in the recognition framework, dynamic dense grid-based HoG features are used to extract the appearance features by accumulating the gradient magnitudes for a set of orientations in 1D histograms defined over a size-adaptive dense grid [24]. HoG descriptor extraction is also used as a fast and accurate method for pedestrian recognition [29]. In [30], once the HoG features are extracted, PCA is applied to the feature vectors.…”

Section: Introductionmentioning

confidence: 99%

Robust Real-Time Gradient-based Eye Detection and Tracking Using Transform Domain and PSO-Based Feature Selection

Salehi

Keyvanara

Monadjemi

2017

ELCVIA

View full text Add to dashboard Cite

Despite numerous research on eye detection, this field of study remains challenging due to the individuality of eyes, occlusion, and variability in scale, location, and light conditions. This paper combines a technique of feature extraction and a feature selection method to achieve a significant increase in eye recognition. Subspace methods may improve detection efficiency and accuracy of eye centers detection using dimensionality reduction. In this study, HoG (histogram of Oriented Gradient) descriptor is used to lay the ground for Binary Particle Swarm Optimization (BPSO) based feature selection. HoG features are used for efficient extraction of pose, translation and illumination invariant features. HoG descriptors uses the fact that local object appearance and shape within an image can be described by the distribution of intensity gradients or edge directions. The method upholds invariance to geometric and photometric transformations. The performance of presented method is evaluated using several benchmark datasets, namely, BioID and RS-DMV. Experimental results obtained by applying the proposed algorithm on BioID dataset show that the proposed system outperforms other eye recognition systems. A significant increase in the recognition rate is achieved when using the combination of HoG descriptor, BPSO, and SVM for feature extraction, feature selection and training phase respectively. The Recognition rate for BioID dataset was 99.6% and the detection time was 15.24 msec for every single frame.

show abstract

Accelerating Histograms of Oriented Gradients descriptor extraction for pedestrian recognition

Cited by 28 publications

References 5 publications

Recognition of handwritten characters using local gradient feature descriptors

Recognition of handwritten characters using local gradient feature descriptors

HOG-Dot: A Parallel Kernel-Based Gradient Extraction for Embedded Image Processing

Robust Real-Time Gradient-based Eye Detection and Tracking Using Transform Domain and PSO-Based Feature Selection

Contact Info

Product

Resources

About