TTSNet:通过变压器识别交通标志,通过学习谱图结构特征
Yi Deng1,2, Ziyi Wu1, Junhai Liu1
1School of Electronic and Electrical Engineering, Wuhan Textile University, Wuhan 430200, China.
Mathematical biosciences and engineering : MBE
|March 5, 2026
概括
我们开发了TTSNet,一种新的变压器模型,通过学习不变特征来改进交通标志识别. 这种方法提高了自动驾驶和计算机视觉具有挑战性的数据集的性能.
科学领域:
- 计算机视觉 计算机视觉
- 机器学习 机器学习
- 自主系统 自主系统
背景情况:
- 交通标志识别对于自动驾驶汽车和交通安全至关重要.
- 挑战包括高的类内变异性,类间相似性和复杂的背景.
研究的目的:
- 为有效的交通标志识别提出一种新型的不变提示感知特征度变压器 (TTSNet).
- 解决现有方法在处理视觉特征变化和背景复杂性的局限性.
主要方法:
- 引入了三个新型模块:基于注意力的内部尺度特征交互 (DLFL),跨尺度跨空间特征调制 (SSFM) 和消除空间和信息冗余 (ESIR).
- DLFL使用基于价值的特征选择来提取不变线索.
- SSFM汇总了多尺度的特征,而ESIR减少了空间和道冗余,以改善表示.
主要成果:
- 在基准数据集上,TTSNet实现了最先进的性能.
- 在T100K数据集上获得了89.1%的准确性.
- 在CTSDB数据集上实现了89.97%的准确性.
结论:
- 拟议的TTSNet有效地从交通标志中学习不变和核心信息.
- 新型模块显著提高了特征表示和识别精度.
- 在复杂的交通标志识别场景中,TTSNet表现出卓越的性能.
相关概念视频
Classification of Signals
1.5K
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
1.5K
Basic signals of Fourier Transform
1.1K
The Fourier Transform is a pivotal mathematical tool in signal processing, enabling the transformation of time-domain signals into their frequency-domain representations. Among the numerous elements within this domain, certain functions like the sinc function, delta function, and exponential signals hold significant importance due to their unique properties and implications.
The sinc function, defined as sinc(x) = sin(πx)/(πx), is particularly notable for its symmetry and behavior at...
The sinc function, defined as sinc(x) = sin(πx)/(πx), is particularly notable for its symmetry and behavior at...
1.1K
