Vision-Based Pedestrian Detection -- Improvement and Verification of Feature Extraction Methods and SVM-Based Classification

Schauland, Sam; Kummert, Anton; Park, Su-Birm; Iurgel, U.; Zhang, Yan

doi:10.1109/itsc.2006.1706725

Cited by 16 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Conversely, shape-based approaches exploit the pedestrians' appearance, so can detect both moving and stationary people [19], [23]. In model-based approach, the challenge is to model the several variations in the shapes, pose, size and appearance of humans and their backgrounds.…”

Section: Related Workmentioning

confidence: 99%

A Pedestrian Detector Using Histograms of Oriented Gradients and a Support Vector Machine Classifier

Bertozzi

Broggi

Rose

et al. 2007

2007 IEEE Intelligent Transportation Systems Conference

View full text Add to dashboard Cite

This paper details filtering subsystem for a tetravision based pedestrian detection system. The complete system is based on the use of both visible and far infrared cameras; in an initial phase it produces a list of areas of attention in the images which can contain pedestrians. This list is furtherly refined using symmetry-based assumptions. Then, this results is fed to a number of independent validators that evaluate the presence of human shapes inside the areas of attention.Histogram of oriented gradients and Support Vector Machines are used as a filter and demonstrated to be able to successfully classify up to 91% of pedestrians in the areas of attention.

show abstract

Section: Related Workmentioning

confidence: 99%

A Pedestrian Detector Using Histograms of Oriented Gradients and a Support Vector Machine Classifier

Bertozzi

Broggi

Rose

et al. 2007

2007 IEEE Intelligent Transportation Systems Conference

View full text Add to dashboard Cite

show abstract

“…Shape-based approaches are based on pedestrians' appearance, so can detect both moving and stationary people [14], [17]. In these cases, the challenge is to model the several variations in the shapes, pose, size and appearance of humans and their backgrounds.…”

Section: Related Workmentioning

confidence: 99%

“…Symmetry assumptions are used as well, in [16], [17] combination of symmetry and edge density features are extracted and fed into an SVM-classier using a statistical approach. Also the use of temporal tracking of symmetry features seems promising but, analogously to the previous mentioned motion-based recognition systems, it fails to detect still pedestrians [12].…”

Section: Related Workmentioning

confidence: 99%

A Symmetry-based Validator and Refinement System for Pedestrian Detection in Far Infrared Images

Bertozzi

Broggi

Rose

et al. 2007

2007 IEEE Intelligent Transportation Systems Conference

View full text Add to dashboard Cite

Abstract-This paper presents a refinement and validation stage for a tetra-vision based pedestrian detection system. The complete system is based on the use of both visible and far infrared cameras; in an initial phase it produces a list of areas of attention in the images which can contain pedestrians. Starting from the assumption that human shapes are mostly symmetrical and feature a number of vertical edges, the symmetry and edge density content of these areas is computed. The results is used to filter the list, discarding areas of attention that feature a scarce symmetry content. At the same time, the size of each area is refined to match the symmetry content and therefore to better adapt to human shapes. Moreover, this module can be successfully used to partition areas that contains two or more human shapes.

show abstract

“…Conversely, shape-based approaches exploit the pedestrians' appearance, so can detect both moving and stationary people [17,21]. In model-based approach, the challenge is to model the several variations in the shapes, pose, size and appearance of humans and their backgrounds.…”

Section: Related Workmentioning

confidence: 99%

Integrated Stereo Infrared and Color Human Detection on the ART platform

Bertozzi¹,

Broggi²,

Felisa³

et al. 2006

View full text Add to dashboard Cite

Public reporting burden for this collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing this collection of information. This report presents the research activities within the framework of N62558-05-P-0380 contract for the development of a Human Shape localization system by means of a 4 cameras vision system consisting of 2 daylight and 2 far infrared cameras.The main idea is to exploit the advantages of both far infrared and visible cameras to develop a system that combines the advantages of using far infrared or daylight technologies.In particular, this report details a system for detecting pedestrians using histogram of oriented gradients by means of support vector machines. SUBJECT TERMS AbstractThis report presents the research work developed under contract number N62558-07-P-0029 with the aim of localizing human shapes using two stereo systems consisting of two daylight and two far-infrared (FIR) cameras.

show abstract

Vision-Based Pedestrian Detection -- Improvement and Verification of Feature Extraction Methods and SVM-Based Classification

Cited by 16 publications

References 19 publications

A Pedestrian Detector Using Histograms of Oriented Gradients and a Support Vector Machine Classifier

A Pedestrian Detector Using Histograms of Oriented Gradients and a Support Vector Machine Classifier

A Symmetry-based Validator and Refinement System for Pedestrian Detection in Far Infrared Images

Integrated Stereo Infrared and Color Human Detection on the ART platform

Contact Info

Product

Resources

About