An improved object detection algorithm based on depthwise separable convolutions

Xiuyuan Yu; Qiliang Bao; Haolong Jia; Yu Li; Rui Qin

doi:10.1117/12.2552710

31 January 2020 An improved object detection algorithm based on depthwise separable convolutions

Xiuyuan Yu, Qiliang Bao, Haolong Jia, Yu Li, Rui Qin

Proceedings Volume 11427, Second Target Recognition and Artificial Intelligence Summit Forum; 114272T (2020) https://doi.org/10.1117/12.2552710
Event: Second Target Recognition and Artificial Intelligence Summit Forum, 2019, Changchun, China

Abstract

Aiming at small objects detection such as unmanned aerial vehicle (UAV), this paper proposes a fast object detection algorithm based on depth wise separable convolutions. Firstly, the inverted residuals units based on depth wise convolutions and pointwise convolutions are used to construct a lightweight feature extraction network to improve the network’s speed. Secondly, the feature pyramid network is used to detect the five scale feature maps to improve the detection performance of small objects. Otherwise, we make an UAV dataset based on the urban background for training and testing of our experiments. The experimental results show that the improved method proposed in this paper can effectively improve the detection accuracy and real-time performance of UAVs in complex urban backgrounds, and the computation of network is greatly reduced, thereby making it possible to achieve object detection on embedded systems.

Citation Download Citation

Xiuyuan Yu, Qiliang Bao, Haolong Jia, Yu Li, and Rui Qin "An improved object detection algorithm based on depthwise separable convolutions", Proc. SPIE 11427, Second Target Recognition and Artificial Intelligence Summit Forum, 114272T (31 January 2020); https://doi.org/10.1117/12.2552710

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