Authors:
Eric Gabriel
;
Hauke Schramm
and
Carsten Meyer
Affiliation:
Kiel University of Applied Sciences and Kiel University (CAU), Germany
Keyword(s):
Object Detection, Pedestrian Detection, Hough Transform, Proposal Generation, Patch Classification, Convolutional Neural Network.
Related
Ontology
Subjects/Areas/Topics:
Computer Vision, Visualization and Computer Graphics
;
Features Extraction
;
Image and Video Analysis
;
Shape Representation and Matching
Abstract:
Pedestrian detection is one of the most essential and still challenging tasks in computer vision. Among traditional
feature- or model-based techniques (e.g., histograms of oriented gradients, deformable part models etc.),
deep convolutional networks have recently been applied and significantly advanced the state-of-the-art. While
earlier versions (e.g., Fast-RCNN) rely on an explicit proposal generation step, this has been integrated into
the deep network pipeline in recent approaches. It is, however, not fully clear if this yields the most efficient
way to handle large ranges of object variability (e.g., object size), especially if the amount of training data
covering the variability range is limited. We propose an efficient pedestrian detection framework consisting
of a proposal generation step based on the Discriminative Generalized Hough Transform and a rejection step
based on a deep convolutional network. With a few hundred proposals per (2D) image, our framework achieve
s
state-of-the-art performance compared to traditional approaches on several investigated databases. In this
work, we analyze in detail the impact of different components of our framework.
(More)