HDMapNet: An Online HD Map Construction and Evaluation Framework

By Qi Li, Yue Wang, Yilun Wang, Hang Zhao. IEEE International Conference on Robotics and Automation, 2021

462 citations recorded by the source corpus.

Constructing HD semantic maps is a central component of autonomous driving. However, traditional pipelines require a vast amount of human efforts and resources in annotating and maintaining the semantics in the map, which limits its scalability. In this paper, we introduce the problem of HD semantic map learning, which dynamically constructs the local semantics based on onboard sensor observations. Meanwhile, we introduce a semantic map learning method, dubbed HDMapNet. HDMapNet encodes image features from surrounding cameras and/or point clouds from LiDAR, and predicts vectorized map elements in the bird's-eye view. We benchmark HDMapNet on nuScenes dataset and show that in all settings, it performs better than baseline methods. Of note, our camera-LiDAR fusion-based HDMapNet outperforms existing methods by more than 50 % in all metrics. In addition, we develop semantic-level and instance-level metrics to evaluate the map learning performance. Finally, we showcase our method is capable of predicting a locally consistent map. By introducing the method and metrics, we invite the community to study this novel map learning problem.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/f13cdd9672914570c9b37f7fe31a54861f297d36

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation (2022, background): “Although they have demonstrated remarkable performance on large-scale detection benchmarks, these point-level fusion methods barely work on semantic-oriented tasks, such as BEV map segmentation [5], [6], [7], [8].”
Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting (2023, methodology): “HD map automation [46, 26] has received additional attention, along with 3D scene flow and pixel-level scene simulation [43, 8].”
VAD: Vectorized Scene Representation for Efficient Autonomous Driving (2023, unknown): “3.4).”
End-to-End Autonomous Driving: Challenges and Frontiers (2023, methodology): “Due to the high cost of availability of HD Maps, online mapping methods have been devised with different formulations, such as BEV segmentation [183], vectorized lanlines [184], centerlines and their topology [185], [186], and lane segments [187].”
VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning (2024, methodology): “In terms of vectorized mapping, HDMapNet [24] converts lane segmentation into vector maps through post-processing.”