IC-Mapper: Instance-Centric Spatio-Temporal Modeling for Online Vectorized Map Construction

2024-10-28

ACM Multimedia

AI Summary

Existing online HD map construction methods are limited to local perception and lack spatial scalability. This paper proposes the first instance-centric, vision-driven online vectorized HD mapping framework, breaking away from traditional paradigms reliant on offline data collection and manual annotation. Methodologically, we design a joint feature-geometric cross-frame instance association mechanism, incorporating instance-level temporal matching, multi-dimensional geometric consistency metrics, point-sampling-based spatial fusion, and an end-to-end differentiable vector decoding scheme to enable dynamic, collaborative updating between the historical global map and current observations. Evaluated on nuScenes, our approach achieves state-of-the-art performance across detection, tracking, and global map accuracy, while supporting millisecond-level real-time inference and scalable incremental map construction.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Online vector map construction based on visual data can bypass the processes of data collection, post-processing, and manual annotation required by traditional map construction, which significantly enhances map-building efficiency. However, existing work treats the online mapping task as a local range perception task, overlooking the spatial scalability required for map construction. We propose IC-Mapper, an instance-centric online mapping framework, which comprises two primary components: 1) Instance-centric temporal association module: For the detection queries of adjacent frames, we measure them in both feature and geometric dimensions to obtain the matching correspondence between instances across frames. 2) Instance-centric spatial fusion module: We perform point sampling on the historical global map from a spatial dimension and integrate it with the detection results of instances corresponding to the current frame to achieve real-time expansion and update of the map. Based on the nuScenes dataset, we evaluate our approach on detection, tracking, and global mapping metrics. Experimental results demonstrate the superiority of IC-Mapper against other state-of-the-art methods. Code will be released on https://github.com/Brickzhuantou/IC-Mapper.

Problem

• Enhances online vector map construction efficiency
• Addresses spatial scalability in map construction
• Improves real-time map expansion and updates

Innovation

• Instance-centric temporal association for frame matching
• Spatial fusion for real-time map updates
• Online vector map construction from visual data