CTAFFNet: CNN–Transformer Adaptive Feature Fusion Object Detection Algorithm for Complex Traffic Scenarios
Transportation Research Record: Journal of the Transportation Research Board · 2025-01 · 2679 (1) · 1947-1965
DOI: 10.1177/03611981241258753 ↗Kurz gefasst
Fachartikel in der Zeitschrift Transportation Research Record: Journal of the Transportation Research Board, online erschienen am 15.09.2024. Verfasst von Xinlong Dong und 3 weiteren Autor:innen. Die Arbeit wurde bisher 75-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: Natural Science Foundation of Anhui Province, Anhui Provincial Key Research and Development Plan, Yangtze River Delta Science and Technology Innovation Community Joint Research Project.
Abstract (Originalsprache)
As the core technology of an environmental perception system, object detection has received more and more attention and has become a hot research direction for intelligent driving vehicles. The CNN–Transformer hybrid model has poor generalization ability, making it difficult to meet the detection requirements for small objects in complex scenes. We propose a novel convolutional neural network (CNN)–Transformer Adaptive Feature Fusion Network (CTAFFNet) for object detection. First, we design a Local–Global Feature Fusion unit known as the Convolutional Transformation Adaptive Fusion Kernel (CTAFFK), which is integrated into CTAFFNet. The CTAFFK kernel utilizes two branches, namely CNN and Transformer, to extract local and global features from the image, and adaptively fuses the features from both branches. Subsequently, we develop an adaptive feature fusion strategy that combines local high-frequency and global low-frequency features to obtain comprehensive feature information. Finally, CTAFFNet employs an encoder–decoder structure to facilitate the flow of fused local–global information between different stages, ensuring the model’s generalization capabilities. Results from the experiment conducted on the large and challenging KITTI dataset demonstrate the effectiveness and efficiency of the proposed network. Compared with other mainstream networks, it achieves an average precision of 91.17%, particularly excelling in the detection of small objects at longer distances with a remarkable 70.18% accuracy, while also providing real-time detection capabilities.
Förderung
- Natural Science Foundation of Anhui Province
- Anhui Provincial Key Research and Development Plan
- Yangtze River Delta Science and Technology Innovation Community Joint Research Project
- Wuhu ChiZhu Light Major Science and Technology Project
Zitieren
APA
Dong, X., Shi, P., Liang, T., & Yang, A. (2025). CTAFFNet: CNN–Transformer Adaptive Feature Fusion Object Detection Algorithm for Complex Traffic Scenarios. Transportation Research Record: Journal of the Transportation Research Board, 2679(1), 1947-1965. https://doi.org/10.1177/03611981241258753
Vancouver
Dong X, Shi P, Liang T, Yang A. CTAFFNet: CNN–Transformer Adaptive Feature Fusion Object Detection Algorithm for Complex Traffic Scenarios. Transportation Research Record: Journal of the Transportation Research Board. 2025;2679(1):1947-1965. doi:10.1177/03611981241258753
BibTeX
@article{Dong2025,
author = {Dong, Xinlong and Shi, Peicheng and Liang, Taonian and Yang, Aixi},
title = {CTAFFNet: CNN–Transformer Adaptive Feature Fusion Object Detection Algorithm for Complex Traffic Scenarios},
journal = {Transportation Research Record: Journal of the Transportation Research Board},
year = {2025},
volume = {2679},
number = {1},
pages = {1947--1965},
doi = {10.1177/03611981241258753}
}
EUVIMED