Optimizing LaneSegNet for Real-Time Lane Topology Prediction in Autonomous Vehicles
William Stevens, Vishal Urs, Karthik Selvaraj, Gabriel Torres, Gaurish Lakhanpal
TL;DR
The paper addresses real-time lane topology prediction for autonomous vehicles by evaluating LaneSegNet, a architecture that fuses topological information with lane-line features. It analyzes hyperparameter tuning of the feature extractor and transformer encoder-decoder stacks, testing ResNet variants and 2:4 vs 4:8 configurations on the OpenLane-V2 dataset using a single NVIDIA A100 GPU. Key findings show that swapping ResNet-50 for ResNet-18 increases training time and reduces accuracy, while deeper encoder-decoder stacks (4:8) can substantially boost accuracy with modest time costs, achieving a mAP of 27.7 after 20 epochs compared to 23.5 after 30 epochs baseline. The results offer practical guidance for deploying LaneSegNet across different compute budgets, enabling faster training for resource-constrained users and achieving higher accuracy on powerful GPUs.
Abstract
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.