提升自动驾驶异常分割速度，实现实时部署。
Towards Real-Time PixOOD: Efficient Anomaly Segmentation for Autonomous Vehicles
- 重构PixOOD的评分流程，结合TensorRT优化加速
- 在桌面端达182帧/秒，嵌入式平台75帧/秒
- 适合车载系统与铁路场景的实时异常检测
实时异常分割对自动驾驶系统的安全性至关重要。尽管近期方法精度较高，但计算开销限制了其在嵌入式硬件上的部署。本文提出一种高效加速流水线，适用于嵌入式与桌面平台，面向自动驾驶与铁路领域。通过重构当前最先进的分布外检测方法PixOOD的Neyman-Pearson评分阶段，并利用硬件优化的TensorRT编译部署，该方案在桌面端NVIDIA RTX 4060 GPU上达到最高182 FPS，嵌入式平台NVIDIA Jetson AGX Orin上达75 FPS，分别比原基线快20倍和18倍。结果表明，先进异常分割可高效部署于自动驾驶与铁路应用的车载处理中。
原文摘要 · Abstract (English)
Real-time anomaly segmentation is essential for the safety of autonomous systems. Although recent approaches offer high accuracy, their computational cost limits their deployment on embedded hardware. This work presents an efficient and accelerated pipeline designed for both embedded and desktop platforms, targeting the autonomous driving and railway domains. The proposed approach reformulates the Neyman-Pearson scoring stage of PixOOD, a state-of-the-art out-of-distribution detection method, and deploys the full pipeline through hardware-optimized TensorRT compilation, reaching up to 182 FPS on a desktop NVIDIA RTX 4060 GPU and 75 FPS on the NVIDIA Jetson AGX Orin embedded platform, respectively 20x and 18x faster than the original baseline. The achieved results demonstrate that advanced anomaly segmentation can be efficiently deployed for onboard processing in autonomous driving and railway applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。