在Jetson Nano上优化实时车道检测算法，速度提升22倍
Implementation of Real-Time Lane Detection on Autonomous Mobile Robot
- 将Ultra Fast Lane检测转为TensorRT部署，提升推理效率
- 室外数据集处理速度达101毫秒（CULane），室内略慢但整体提速22倍
- 适合自动驾驶机器人视觉系统开发者参考
本文实现了基于学习的车道检测算法在自主移动机器人上的应用。针对SEATER P2MC-BRIN原型机，采用摄像头采集数据，在Jetson Nano平台上部署并优化了Ultra Fast Lane检测算法。通过两个数据集评估性能：户外使用公开数据集CULane和TuSimple，室内使用印尼博罗研究所车间内部数据集。实验表明，转换为TensorRT后算法在Jetson Nano上运行更优，处理速度分别达到约101毫秒（CULane）和105毫秒（TuSimple），较之前模型快约22倍。尽管在室外数据集上表现良好，但在室内场景下精度下降明显。未来工作需聚焦迁移学习与微调以提升室内检测能力。
原文摘要 · Abstract (English)
This paper describes the implementation of a learning-based lane detection algorithm on an Autonomous Mobile Robot. It aims to implement the Ultra Fast Lane Detection algorithm for real-time application on the SEATER P2MC-BRIN prototype using a camera and optimize its performance on the Jetson Nano platform. Preliminary experiments were conducted to evaluate the algorithm's performance in terms of data processing speed and accuracy using two types of datasets: outdoor using a public dataset and indoor using an internal dataset from the indoor area of the BRIN Workshop Building in Bandung. The experiments revealed that the algorithm runs more optimally on the Jetson Nano platform after conversion to TensorRT compared to the ONNX model, achieving processing speeds of approximately 101 ms using CULane and 105 ms using TuSimple, which is about 22 times faster than the previous model. While the algorithm demonstrates good accuracy on the outdoor public dataset, its performance falls short on the indoor dataset. Future work should focus on transfer learning and fine-tuning to enhance indoor lane detection accuracy.
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。