Fast object detection based on several samples by training voting space

In this paper, we propose a fast and novel detection method based on several samples to localize objects in target images or video. Firstly, we use several samples to train a voting space which is constructed by cells at corresponding positions. Each cell is described by a Gaussian distribution whos...

Full description

Saved in:
Bibliographic Details
Published in:Pattern recognition and image analysis 2015-10, Vol.25 (4), p.565-576
Main Authors: Xu, Pei, Ye, Mao, Pei, Lishen, Dou, Yumin, Chen, Hongyi
Format: Article
Language:English
Subjects:
Computer Science
Estimating techniques
Image Processing and Computer Vision
Image retrieval
Mathematical Method in Pattern Recognition
Normal distribution
Pattern Recognition
Pattern recognition systems
Studies
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we propose a fast and novel detection method based on several samples to localize objects in target images or video. Firstly, we use several samples to train a voting space which is constructed by cells at corresponding positions. Each cell is described by a Gaussian distribution whose parameters are estimated by maximum likelihood estimation method. Then, we randomly choose one sample as a query image. Patches of target image are recognized by densely voting in the trained voting space. Next, we use a mean-shift method to refine multiple instances of object class. The high performance of our approach is demonstrated on several challenging data sets in both efficiency and effectiveness.
ISSN:1054-6618
1555-6212
DOI:10.1134/S1054661815040227