面向自动驾驶车辆实时车道拓扑预测的 LaneSegNet 优化
Optimizing LaneSegNet for Real-Time Lane Topology Prediction in Autonomous Vehicles
AI总结：
本研究优化LaneSegNet车道拓扑预测架构，通过调整Transformer编码器-解码器堆栈比例，在训练时间与精度间取得权衡：2:4配置减少22.3%训练时间而精度仅降7.1%，4:8配置以11.1%的时间代价提升23.7%平均精度，为不同算力用户提供调优依据。
摘要：
随着自动驾驶车辆的日益普及，计算机视觉算法必须能够实时准确地评估道路特征。本研究探讨了 LaneSegNet 架构，这是一种新的车道拓扑预测方法，它将拓扑信息与车道线数据相结合，以提供对道路环境更具上下文性的理解。LaneSegNet 架构包括特征提取器、车道编码器、车道解码器和预测头，利用了 ResNet-50、BEVFormer 以及多种注意力机制中的组件。我们通过修改特征提取器和 Transformer 编码器-解码器堆栈，对 LaneSegNet 架构进行了优化实验。我们发现，修改编码器和解码器堆栈在训练时间与预测精度之间提供了一种有趣的权衡，某些组合显示出有前景的结果。我们的实现在单个 NVIDIA Tesla A100 GPU 上训练，发现 2:4 的比例将训练时间减少了 22.3%，而平均精度均值仅下降 7.1%；而 4:8 的比例仅将训练时间增加了 11.1%，却将平均精度均值显著提高了 23.7%。这些结果表明，策略性的超参数调优可以根据用户的资源情况带来实质性改进。本研究为根据可用计算能力优化 LaneSegNet 提供了有价值的见解，使其对资源有限的用户更易用，同时增强了拥有更强大资源的用户的能力。
英文摘要：
With the increasing prevalence of autonomous vehicles, it is essential for computer vision algorithms to accurately assess road features in real-time. This study explores the LaneSegNet architecture, a new approach to lane topology prediction which integrates topological information with lane-line data to provide a more contextual understanding of road environments. The LaneSegNet architecture includes a feature extractor, lane encoder, lane decoder, and prediction head, leveraging components from ResNet-50, BEVFormer, and various attention mechanisms. We experimented with optimizations to the LaneSegNet architecture through feature extractor modification and transformer encoder-decoder stack modification. We found that modifying the encoder and decoder stacks offered an interesting tradeoff between training time and prediction accuracy, with certain combinations showing promising results. Our implementation, trained on a single NVIDIA Tesla A100 GPU, found that a 2:4 ratio reduced training time by 22.3% with only a 7.1% drop in mean average precision, while a 4:8 ratio increased training time by only 11.1% but improved mean average precision by a significant 23.7%. These results indicate that strategic hyperparameter tuning can yield substantial improvements depending on the resources of the user. This study provides valuable insights for optimizing LaneSegNet according to available computation power, making it more accessible for users with limited resources and increasing the capabilities for users with more powerful resources.
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。
