An improved algorithm for object detection based on deep learning

Ke Li

doi:10.1117/12.2674730

23 May 2023 An improved algorithm for object detection based on deep learning

Ke Li

Proceedings Volume 12604, International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2022); 126044V (2023) https://doi.org/10.1117/12.2674730
Event: 2nd International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2022), 2022, Guangzhou, China

Abstract

The goal of object detection is to recognize the position and category of all objects in an image, allowing for machine vision understanding. Many approaches have been developed to solve this problem, primarily based on convolutional image feature extraction and deep learning algorithms. However, the current algorithms lack robustness and often have high error rates and a reliance on numerous parameters, making them difficult to apply in practical settings. To address these limitations, this paper presents an improved object detection method based on the R-CNN model. This method leverages the target feature matching module in the R-CNN model to accurately extract features through similarity calculation. Analysis showed that this improved method outperforms traditional models in terms of detection efficiency, especially in complex environments. The proposed method serves as a valuable reference for further research in related fields.

Citation Download Citation

Ke Li "An improved algorithm for object detection based on deep learning", Proc. SPIE 12604, International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2022), 126044V (23 May 2023); https://doi.org/10.1117/12.2674730

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