面向自动驾驶巡航控制的基于 YOLO-PPA 的高效交通标志检测
YOLO-PPA based Efficient Traffic Sign Detection for Cruise Control in Autonomous Driving
AI总结：
针对远距离小交通标志检测及车载嵌入式设备算力受限问题，提出 YOLO PPA 检测算法，在 GTSDB 上显著提升推理效率与 mAP 50。
摘要：
在自动驾驶系统中，高效且准确地检测交通标志非常重要。然而，距离越远，交通标志就越小。现有目标检测算法几乎无法检测这些小尺度标志。此外，车载嵌入式设备的性能限制了检测模型的规模。为应对这些挑战，本文提出了一种基于 YOLO PPA 的交通标志检测算法。在 GTSDB 数据集上的实验结果表明，与原始 YOLO 相比，所提方法将推理效率提高了 11.2%。mAP 50 也提高了 93.2%，这证明了所提出的 YOLO PPA 的有效性。
英文摘要：
It is very important to detect traffic signs efficiently and accurately in autonomous driving systems. However, the farther the distance, the smaller the traffic signs. Existing object detection algorithms can hardly detect these small scaled signs.In addition, the performance of embedded devices on vehicles limits the scale of detection models.To address these challenges, a YOLO PPA based traffic sign detection algorithm is proposed in this paper.The experimental results on the GTSDB dataset show that compared to the original YOLO, the proposed method improves inference efficiency by 11.2%. The mAP 50 is also improved by 93.2%, which demonstrates the effectiveness of the proposed YOLO PPA.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
