2006 IEEE Intelligent Vehicles Symposium
DOI: 10.1109/ivs.2006.1689629
|View full text |Cite
|
Sign up to set email alerts
|

Pedestrian Detection using Infrared images and Histograms of Oriented Gradients

Abstract: Abstract-This paper presents a complete method for pedestrian detection applied to infrared images. First, we study an image descriptor based on histograms of oriented gradients (HOG), associated with a Support Vector Machine (SVM) classifier and evaluate its efficiency. After having tuned the HOG descriptor and the classifier, we include this method in a complete system, which deals with stereo infrared images. This approach gives good results for window classification, and a preliminary test applied on a vid… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
137
0
2

Publication Types

Select...
6
3
1

Relationship

0
10

Authors

Journals

citations
Cited by 197 publications
(140 citation statements)
references
References 12 publications
1
137
0
2
Order By: Relevance
“…A set of features such as Haar wavelet coefficients [33,35], histogram of oriented gradient [16,40] or covariance matrices of a set of features [4,42], can be extracted from a large number of training samples to train a classifier with a support vector machine [13,33], or boosting approaches [42,43]. Given a fixed camera, a moving object can also be detected by modeling the background and tracking becomes simply an object correspondence across frames.…”
Section: Introductionmentioning
confidence: 99%
“…A set of features such as Haar wavelet coefficients [33,35], histogram of oriented gradient [16,40] or covariance matrices of a set of features [4,42], can be extracted from a large number of training samples to train a classifier with a support vector machine [13,33], or boosting approaches [42,43]. Given a fixed camera, a moving object can also be detected by modeling the background and tracking becomes simply an object correspondence across frames.…”
Section: Introductionmentioning
confidence: 99%
“…However, similar to motion filters, edge based histogram features are not scale invariant, hence one must first scale the test images to form a pyramid to make the local edge orientation histograms features reliable. Later, in [19] a similar scheme called histogram of oriented gradients (HoG) was proposed, which became a very popular feature for human/pedestrian detection [81,82,83,84, 85] (we will discuss about the use of HoG features in face detection in the next subsection). In [86], the authors proposed spectral histogram features, which adopts a broader set of filters before collecting the histogram features, including gradient, Laplacian of Gaussian and Gabor filters.…”
Section: Feature Extractionmentioning
confidence: 99%
“…Edge density can also be analysed as pedestrians in far-IR images are usually much brighter than the background, and there can be a sharp change in image intensity at their edges (Bertozzi et al, 2004). The gradient operator can also be used to aid detection (Meis et al, 2003;Suard et al, 2006).…”
Section: 1 Infrared For Pedestrian Detectionmentioning
confidence: 99%