交通流基础设施安全的SIFT-SNN:一个实时的上下文意识异常检测框架
Munish Rathee1, Boris Bačić1, Maryam Doborjeh1,2
1School of Engineering, Computer and Mathematical Sciences, Auckland University of Technology, Auckland 1010, New Zealand.
Journal of imaging
|February 26, 2026
概括
本研究引入了一种增强的神经形态视觉系统,用于在运输基础设施中自动检测异常,提高安全性并降低检查成本. 该系统实现了高精度和高效率,为传统方法提供了可部署的替代方案.
科学领域:
- 计算机视觉 计算机视觉
- 神经形态工程的神经形态工程
- 人工智能的人工智能
背景情况:
- 手动检查运输基础设施是昂贵的,容易出现错误.
- 现有的自动化系统与运动和照明变化作斗争.
- 神经形态系统为高效,低功耗的异常检测提供了潜力.
研究的目的:
- 开发一种改进的神经形态视觉系统,用于在交通基础设施中检测异常.
- 通过使用时间特征聚合来增强上下文意识和序列稳定检测.
- 为传统的基于CNN的检查工具提供可部署,可解释和节能的替代方案.
主要方法:
- 实现了一个改进的尺度不变特征转换尖端神经网络 (SIFT-SNN) 与时间特征聚合.
- 将编码的 SIFT 关键点转化为基于延迟的尖端列车,用于使用漏洞的整合和发射 (LIF) 尖端神经网络进行分类.
- 在GPU,CPU和模拟嵌入式硬件配置中评估系统性能.
主要成果:
- 实现了92.3%的准确性和91.0%的宏观F1得分,并进行了五次交叉验证.
- 在硬件平台上,推断延迟从每9.5ms到~48.3ms不等.
- 展示了一个紧的模型尺寸 (2.9 MB) 和低功耗 (5-65 W).
结论:
- 拟议的暂时光滑的神经形态系统提供了一个强大的解决方案,用于检测基础设施中的关键故障模式,如屏障钉.
- 时间平滑增强检测回忆,特别是在模两可的情况下.
- 该系统的效率和低资源需求使其适合于现实世界的部署.
相关概念视频
01:18Uniform Depth Channel Flow: Problem Solving
To calculate the flow rate for a trapezoidal channel, first, identify the bottom width, side slope, and flow depth of the channel. The cross-sectional area (A) corresponding to the depth of flow (y), channel bottom width (B), and side slope (θ) is determined by:Next, calculate the wetted perimeter, which includes the bottom width and the sloped side lengths in contact with the water. Using the values of the cross-sectional area and the wetted perimeter, determine the hydraulic radius by...
01:24Rapidly Varying Flow
Rapidly varying flow (RVF) in open channels is characterized by abrupt changes in flow depth over a short distance, with the rate of depth change relative to distance often approaching unity. These flows are inherently complex due to their transient and multi-dimensional nature, making exact analysis difficult. However, approximate solutions using simplified models provide valuable insights into their behavior.Key Features of Rapidly Varying FlowRVF is commonly observed in scenarios involving...