An improved YOLOv2 model with depth-wise separable convolutional layers for object detection

Zhuo Han; Dongfei Wang; Aidong Men; Yun Zhou

doi:10.1117/12.2524181

6 May 2019 An improved YOLOv2 model with depth-wise separable convolutional layers for object detection

Zhuo Han, Dongfei Wang, Aidong Men, Yun Zhou

Proceedings Volume 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018); 110693V (2019) https://doi.org/10.1117/12.2524181
Event: Tenth International Conference on Graphic and Image Processing (ICGIP 2018), 2018, Chengdu, China

Abstract

Object detection is the basic research direction in the field of computer vision. It provides basic image information data for other advanced computer vision processing and analysis tasks. With the continuous breakthrough of deep machine learning technology, especially convolutional neural network model in the field of digital image processing shows a strong ability to extract image features. By choosing the depth separable convolution layer to replace the standard convolution layer used in the traditional model, the number of parameters of CNN network model is compressed. Depth Separable Convolution Layer (DSCL) decomposes the standard convolution layer factor into depth convolution layer and point convolution layer, and extracts and merges image features in two steps to reduce the number of parameters. By introducing a depth-separable convolution layer instead of a standard convolution layer, the number of parameters of the model convolution layer is reduced by 78.1%. We choose image feature pyramid network to fuse the image features extracted from each layer of CNN network, so that the target detection model can use matching image fusion features for different size and shape of the target to be detected. The average detection precision on the PASCAL VOC dataset increased to 77.5%.

Citation Download Citation

Zhuo Han, Dongfei Wang, Aidong Men, and Yun Zhou "An improved YOLOv2 model with depth-wise separable convolutional layers for object detection", Proc. SPIE 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018), 110693V (6 May 2019); https://doi.org/10.1117/12.2524181

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Convolution

Image fusion

Feature extraction

Target detection

Data modeling

Performance modeling

Image compression

Show All Keywords

Keywords/Phrases

Search In:

Publication Years