Object Detection Network Based on Feature Fusion and Attention Mechanism

In recent years, almost all of the current top-performing object detection networks use CNN (convolutional neural networks) features. State-of-the-art object detection networks depend on CNN features. In this work, we add feature fusion in the object detection network to obtain a better CNN feature,...

Full description

Saved in:
Bibliographic Details
Published inFuture internet Vol. 11; no. 1; p. 9
Main Authors Zhang, Ying, Chen, Yimin, Huang, Chen, Gao, Mingke
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.01.2019
Subjects
Accuracy
Artificial neural networks
attention mechanism
Cameras
CNN
Convolution
Deep learning
Feature extraction
feature fusion
International conferences
Internet
Machine translation
Neural networks
Neurosciences
object detection network
Object recognition
Pattern recognition
Proposals
R&D
Research & development
Semantics
Telematics
Trucks
Vision systems
Canada
United States > US
China
Online AccessGet full text

Cover

More Information
Summary:In recent years, almost all of the current top-performing object detection networks use CNN (convolutional neural networks) features. State-of-the-art object detection networks depend on CNN features. In this work, we add feature fusion in the object detection network to obtain a better CNN feature, which incorporates well deep, but semantic, and shallow, but high-resolution, CNN features, thus improving the performance of a small object. Also, the attention mechanism was applied to our object detection network, AF R-CNN (attention mechanism and convolution feature fusion based object detection), to enhance the impact of significant features and weaken background interference. Our AF R-CNN is a single end to end network. We choose the pre-trained network, VGG-16, to extract CNN features. Our detection network is trained on the dataset, PASCAL VOC 2007 and 2012. Empirical evaluation of the PASCAL VOC 2007 dataset demonstrates the effectiveness and improvement of our approach. Our AF R-CNN achieves an object detection accuracy of 75.9% on PASCAL VOC 2007, six points higher than Faster R-CNN.
ISSN:1999-5903
1999-5903
DOI:10.3390/fi11010009