Paper
27 September 2024 An improved transformer-based high-performance object detection method
Ziwen Sun, Zonghao Tian, Shengbin Shi, Chong Ling
Author Affiliations +
Proceedings Volume 13275, Sixth International Conference on Information Science, Electrical, and Automation Engineering (ISEAE 2024); 132752X (2024) https://doi.org/10.1117/12.3037710
Event: 6th International Conference on Information Science, Electrical, and Automation Engineering (ISEAE 2024), 2024, Wuhan, China
Abstract
The Transformer architecture is widely used in the field of computer vision due to its ability to relate context and global modeling, and Transformer-based object detection methods have achieved very bright results. However, the existing methods have the problems of underutilizing background images and the model structure is too complex and redundant. In order to solve such problems, an improved high-performance object detection method based on Transformer is proposed. The method first extracts the depth features of the object by means of feature pyramid extraction, then extracts the large, medium and small object regions present in the object image by means of RPN and ROI Pooling, and finally seeks the extrinsic connection between different regions by means of the attention mechanism in the Transformer method, and predicts the object location and category using the proposed loss function. Compared with state-of-the-art object detection methods on MS-COCO datasets, The effectiveness and superiority of the proposed method were demonstrated.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Ziwen Sun, Zonghao Tian, Shengbin Shi, and Chong Ling "An improved transformer-based high-performance object detection method", Proc. SPIE 13275, Sixth International Conference on Information Science, Electrical, and Automation Engineering (ISEAE 2024), 132752X (27 September 2024); https://doi.org/10.1117/12.3037710
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Object detection

Transformers

Feature extraction

Bismuth

Detection and tracking algorithms

Education and training

Ablation

Back to Top