动态调整感知区域大小与帧率，提升边缘设备实时检测精度
CSRAP: Enhanced Canvas Attention Scheduling for Real-Time Mission Critical Perception
- 根据兴趣区域动态调整处理画布大小和帧率
- 在Jetson Orin Nano上实现更高mAP与召回率
- 适合资源受限的实时自动驾驶感知场景
边缘平台上的实时感知面临核心挑战：在计算资源有限的情况下，仍需满足严格的延迟要求完成高分辨率目标检测。先前工作提出基于画布的注意力调度机制，将输入帧中的感兴趣区域整合到较小的画布帧中，以支持所需的帧率处理。本文扩展了该方法，引入可变尺寸画布帧，并允许画布帧率偏离原始数据帧率。我们在NVIDIA Jetson Orin Nano上运行YOLOv11作为感知模块，使用Waymo Open Dataset视频帧进行评估。结果表明，新增的自由度显著提升了质量与成本的权衡能力，使本方案在平均精度（mAP）和召回率方面持续优于当前最先进方法。
原文摘要 · Abstract (English)
Real-time perception on edge platforms faces a core challenge: executing high-resolution object detection under stringent latency constraints on limited computing resources. Canvas-based attention scheduling was proposed in earlier work as a mechanism to reduce the resource demands of perception subsystems. It consolidates areas of interest in an input data frame onto a smaller area, called a canvas frame, that can be processed at the requisite frame rate. This paper extends prior canvas-based attention scheduling literature by (i) allowing for variable-size canvas frames and (ii) employing selectable canvas frame rates that may depart from the original data frame rate. We evaluate our solution by running YOLOv11, as the perception module, on an NVIDIA Jetson Orin Nano to inspect video frames from the Waymo Open Dataset. Our results show that the additional degrees of freedom improve the attainable quality/cost trade-offs, thereby allowing for a consistently higher mean average precision (mAP) and recall with respect to the state of the art.
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。