2012 IEEE Intelligent Vehicles Symposium 2012
DOI: 10.1109/ivs.2012.6232264
|View full text |Cite
|
Sign up to set email alerts
|

Real-time pedestrian detection with deformable part models

Abstract: Abstract-We describe a real-time pedestrian detection system intended for use in automotive applications. Our system demonstrates superior detection performance when compared to many state-of-the-art detectors and is able to run at a speed of 14 fps on an Intel Core i7 computer when applied to 640×480 images. Our approach uses an analysis of geometric constraints to efficiently search feature pyramids and increases detection accuracy by using a multiresolution representation of a pedestrian model to detect sma… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
26
0
2

Year Published

2014
2014
2018
2018

Publication Types

Select...
4
3
3

Relationship

0
10

Authors

Journals

citations
Cited by 61 publications
(28 citation statements)
references
References 22 publications
(54 reference statements)
0
26
0
2
Order By: Relevance
“…In his paper, Yan et al [32] presented an extension of the prevalent deformable part model [33] (DPM) called Multi task DPM (MT-DPM) which aims to explore the relation among multiple resolutions by combining an optimal DPM detector and resolution aware transformations. It takes the pedestrians from multiple resolutions and determines their commonness and differences jointly.…”
Section: ) Deformable Part Based Detectionmentioning
confidence: 99%
“…In his paper, Yan et al [32] presented an extension of the prevalent deformable part model [33] (DPM) called Multi task DPM (MT-DPM) which aims to explore the relation among multiple resolutions by combining an optimal DPM detector and resolution aware transformations. It takes the pedestrians from multiple resolutions and determines their commonness and differences jointly.…”
Section: ) Deformable Part Based Detectionmentioning
confidence: 99%
“…Several works exist which apply the aforementioned algorithms on traffic safety applications, and are thus related to our work. However, to the best of our knowledge, often only forward-looking cameras are used and only single object classes (pedestrians or bicyclists) are detected [3,4,16]. In [15] we presented a similar safety system, however only targeting pedestrians which evidently is a much easier scenario.…”
Section: Related Workmentioning
confidence: 99%
“…The idea of the Histogram of Oriented Gradients (HOG) descriptor by using then slidingwindow detection formulation was proposed by Dalal and Triggs [1]. It has become the most popular descriptor and many algorithms were proposed based on it [2,3,4].…”
Section: Related Workmentioning
confidence: 99%