A joint mechanism algorithm for object detection

Zhuo Han; Dongfei Wang; Aidong Men; Yun Zhou

doi:10.1117/12.2524207

6 May 2019 A joint mechanism algorithm for object detection

Zhuo Han, Dongfei Wang, Aidong Men, Yun Zhou

Proceedings Volume 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018); 110693X (2019) https://doi.org/10.1117/12.2524207
Event: Tenth International Conference on Graphic and Image Processing (ICGIP 2018), 2018, Chengdu, China

Abstract

The main goal of object detection is to recognize and locate the object of interest from the static image or video sequence. It is one of the key tasks in the field of computer vision. However, there are many factors in brightness, shape, color and occlusion of targets, and they are disturbed by complex environmental factors, which make the research opportunities and challenges of object detection algorithms coexist. In this paper, two main frameworks of object detection algorithm based on convolutional neural network are researched, which are based on region proposals and regression idea respectively. Then we present a joint mechanism algorithm for object detection. This algorithm makes a balance between detection efficiency and accuracy to make it more meet the actual needs. The internal of the algorithm is adjusted and optimized, so that the two detectors can make their own judgments according to the characteristics of the image, and decide whether to detect the object to classify and locate it, so that the efficiency is higher and the accuracy is also improved.

Citation Download Citation

Zhuo Han, Dongfei Wang, Aidong Men, and Yun Zhou "A joint mechanism algorithm for object detection", Proc. SPIE 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018), 110693X (6 May 2019); https://doi.org/10.1117/12.2524207

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