التفاصيل البيبلوغرافية
| العنوان: |
Improved Intelligent Learning Filter in Deep Learning Systems and Its Application in Traffic Object Detection. |
| المؤلفون: |
Zheng, Xiaoyi1 (AUTHOR), Fang, Xiaomin1 (AUTHOR), Lan, Kun2 (AUTHOR), Chai, Guofei3 (AUTHOR) chaig@qzc.edu.cn |
| المصدر: |
Traitement du Signal. Dec2024, Vol. 41 Issue 6, p3143-3151. 9p. |
| مصطلحات موضوعية: |
OBJECT recognition (Computer vision), TRAFFIC monitoring, DEEP learning, BLENDED learning, INTELLIGENT networks, INTELLIGENT transportation systems |
| مستخلص: |
With the continuous development of intelligent transportation systems, traffic object detection technology has been widely applied in fields such as autonomous driving, traffic monitoring, and public safety. However, existing traffic object detection methods still face numerous challenges in complex traffic environments, such as occlusion, dynamic changes, and uneven lighting, which lead to a decrease in detection accuracy. Traditional deep learning methods, although performing well in static scenarios, often fail to maintain stable performance in dynamic, complex traffic scenes. Therefore, improving the robustness and accuracy of object detection has become a pressing issue in the field of intelligent transportation. To address these challenges, this paper proposes an intelligent learning filtering-based improvement to the deep learning training mechanism and applies it to traffic object detection. First, the training data is optimized using intelligent learning filtering techniques to eliminate noise and irrelevant information, improving data quality and enhancing the learning effectiveness of deep learning models. Next, a hybrid Kalman Filter (KF)-Transformer network for traffic object detection is constructed, combining the advantages of Kalman filtering and Transformer models to strengthen the model's ability to capture dynamic information and long-term dependencies. Experimental results show that the proposed model achieves higher accuracy and stability in traffic object detection tasks, especially in handling high-speed motion, partial occlusion, and complex backgrounds, demonstrating significant advantages. This study provides a novel solution to improve the accuracy and robustness of traffic object detection systems, with important theoretical and practical value. [ABSTRACT FROM AUTHOR] |
|
Copyright of Traitement du Signal is the property of International Information & Engineering Technology Association (IIETA) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| قاعدة البيانات: |
Business Source Index |