Improving HOG with Image Segmentation: Application to Human Detection

Socarr, Yainuvis; Salas, Sergio; David, Éric; Bermudez, zquez; Peña, Antonio M. López; Gómez, David; Gevers, Theo

doi:10.1007/978-3-642-33140-4_16

Cited by 14 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although, the HOG method is particularly suited for human detection in images [11,12,23,[27][28][29], in this paper we show that it can be used to represent different objects accurately, and even perform well in multi-class applications.…”

Section: Introductionmentioning

confidence: 92%

Multi-Object Recognition Using a Feature Descriptor and Neural Classifier

Enrique¹,

García²,

Guerrero-Ramírez³

et al. 2023

Vision Sensors - Recent Advances

View full text Add to dashboard Cite

In the field of object recognition, feature descriptors have proven to be able to provide accurate representations of objects facilitating the recognition task. In this sense, Histograms of Oriented Gradients (HOG), a descriptor that uses this approach, together with Support Vector Machines (SVM) have proven to be successful human detection methods. In this paper, we propose a scheme consisting of improved HOG and a classifier with a neural approach to producing a robust system for object recognition. The main contributions of this work are: First, we propose an improved gradient calculation that allows for better discrimination for the classifier system, which consists of performing a threshold over both the magnitude and direction of the gradients. This improvement reduces the rate of false positives. Second, although HOG is particularly suited for human detection, we demonstrate that it can be used to represent different objects accurately, and even perform well in multi-class applications. Third, we show that a classifier that uses a neuronal approach is an excellent complement to a HOG-based feature extractor. Finally, experimental results on the well-known Caltech 101 dataset illustrate the benefits of the proposed scheme.

show abstract

Section: Introductionmentioning

confidence: 92%

Multi-Object Recognition Using a Feature Descriptor and Neural Classifier

Enrique¹,

García²,

Guerrero-Ramírez³

et al. 2023

Vision Sensors - Recent Advances

View full text Add to dashboard Cite

show abstract

“…Dollár et al [13] proposed a feature extraction method of Haar-like functionality on the basis of paper [3]. [16] used the higher-level information coming from image segmentation, for re-weighting the HOG descriptor for each one of the cells while it is computed, which will enhance human silhouette orientations, without explicitly computing such silhouettes, but using information not as local as the own gradient magnitude. J. Marin et al [17] proposed a novel ensemble of local experts by means of a Random Forest ensemble.…”

Section: Related Workmentioning

confidence: 99%

An Enhanced Histogram of Oriented Gradients for Pedestrian Detection

Zhao¹,

Zhang

Cheng³

et al. 2015

IEEE Intell. Transport. Syst. Mag.

View full text Add to dashboard Cite

The outstanding Histogram-of-OrientedGradients (HOG) feature proposed by Dalal and Triggs is a state-of-art technique for pedestrian detection, and it is usually applied with a linear support vector machine (SVM) in a slidingwindow framework. Most other algorithms for pedestrian detection use HOG as the basic feature, and combine other features with HOG to form the feature set. Hence, the HOG feature is actually the most efficient and fundamental feature for pedestrian detection. However, the HOG feature cannot adequately handle scale variation of pedestrians. In addition, simply downsampling an image into a different scale, or decomposing via wavelet into multi-resolution subimages, calculating their HOG feature and combining them cannot enhance performance. Therefore, in this paper, based on the idea of multi-resolution feature descriptors, we propose a new robust edge feature referred to as Enhanced HOG (eHOG). It is a complementary descriptor for An Enhanced Histogram of Oriented Gradients for Pedestrian Detection IEEE IntEllIgEnt transportatIon systEms magazInE • 30 • fall 2015the histograms-of-oriented-gradients feature. Though the extraction process of the eHOG descriptor is derived only from HOG itself, similar to the process of extracting edge information from the downscaling image, it retains much more information for the edge gradient than that of the original HOG, without significantly increasing the complexity of computation. In the INRIA pedestrian dataset, many experiments have been conducted with eHOG and HOG, and the results show that the proposed new feature consistently improves the detection rate more than the original HOG feature detector. Particularly, eHOG with a Histogram Intersection Kernel SVM (HIKSVM) classifier has greatly improved performance. These results suggest that eHOG may be a better substitute for HOG for pedestrian detection in many applications.

show abstract

“…Colour has shown to be an effective feature for pedestrian detection and hence multiple colour spaces have been explored (both hand-crafted and learned) [8,17,18,22]. Local structure) Instead of simple pixel values, some approaches try to encode a larger local structure based on colour similarities (soft-cue) [38,15], segmentation methods (hard-decision) [26,31,35], or by estimating local boundaries [20]. Covariance) Another popular way to encode richer information is to compute the covariance amongst features (commonly colour, gradient, and oriented gradient) [36,28].…”

Section: Related Workmentioning

confidence: 99%

Filtered channel features for pedestrian detection

Zhang

Benenson

Schiele

2015

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

343

304

View full text Add to dashboard Cite

This paper starts from the observation that multiple top performing pedestrian detectors can be modelled by using an intermediate layer filtering low-level features in combination with a boosted decision forest. Based on this observation we propose a unifying framework and experimentally explore different filter families. We report extensive results enabling a systematic analysis.Using filtered channel features we obtain top performance on the challenging Caltech and KITTI datasets, while using only HOG+LUV as low-level features. When adding optical flow features we further improve detection quality and report the best known results on the Caltech dataset, reaching 93% recall at 1 FPPI.

show abstract

Improving HOG with Image Segmentation: Application to Human Detection

Cited by 14 publications

References 23 publications

Multi-Object Recognition Using a Feature Descriptor and Neural Classifier

Multi-Object Recognition Using a Feature Descriptor and Neural Classifier

An Enhanced Histogram of Oriented Gradients for Pedestrian Detection

Filtered channel features for pedestrian detection

Contact Info

Product

Resources

About