面向实时PixOOD：自动驾驶的高效异常分割
Towards Real-Time PixOOD: Efficient Anomaly Segmentation for Autonomous Vehicles
浏览论文内容
中文总结 AI 辅助
该研究针对自动驾驶和铁路领域，提出优化PixOOD的高效异常分割流水线，经TensorRT编译后在桌面GPU和嵌入式平台实现高帧率，解决了实时部署的计算成本问题。
中文摘要 AI 辅助
实时异常分割对自主系统的安全至关重要。尽管近期方法准确率很高，但它们的计算成本限制了其在嵌入式硬件上的部署。本研究提出一种为嵌入式和桌面平台设计的高效加速流水线，面向自动驾驶和铁路领域。该方法重新设计了最先进的分布外检测方法PixOOD的奈曼-皮尔逊评分阶段，并通过硬件优化的TensorRT编译部署整个流水线，在桌面级NVIDIA RTX 4060 GPU上达到最高182 FPS，在NVIDIA Jetson AGX Orin嵌入式平台上达到75 FPS，分别比原始基线快20倍和18倍。所得结果表明，先进的异常分割可有效部署在自动驾驶和铁路应用的车载处理中。
英文摘要
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.
发表机构
- Scuola Superiore Sant’Anna（圣安娜高等学校）
机构由 AI 辅助整理，请以论文原文为准。
