Diff-Net: Image Feature Difference based High-Definition Map Change Detection for Autonomous Driving

TL;DR

Diff-Net is a novel end-to-end deep neural network designed for high-definition map change detection in autonomous driving, utilizing feature difference comparison and spatio-temporal fusion to improve accuracy and efficiency.

Contribution

This work introduces the first end-to-end network for HD map change detection, incorporating feature difference calculation and temporal fusion for enhanced performance.

Findings

Diff-Net outperforms baseline methods in change detection accuracy.

The spatio-temporal fusion module improves detection performance with historical data.

Validated on newly collected datasets, demonstrating practical applicability.

Abstract

Up-to-date High-Definition (HD) maps are essential for self-driving cars. To achieve constantly updated HD maps, we present a deep neural network (DNN), Diff-Net, to detect changes in them. Compared to traditional methods based on object detectors, the essential design in our work is a parallel feature difference calculation structure that infers map changes by comparing features extracted from the camera and rasterized images. To generate these rasterized images, we project map elements onto images in the camera view, yielding meaningful map representations that can be consumed by a DNN accordingly. As we formulate the change detection task as an object detection problem, we leverage the anchor-based structure that predicts bounding boxes with different change status categories. To the best of our knowledge, the proposed method is the first end-to-end network that tackles the high-definition map change detection task, yielding a single stage solution. Furthermore, rather than relying on single frame input, we introduce a spatio-temporal fusion module that fuses features from history frames into the current, thus improving the overall performance. Finally, we comprehensively validate our method's effectiveness using freshly collected datasets. Results demonstrate that our Diff-Net achieves better performance than the baseline methods and is ready to be integrated into a map production pipeline maintaining an up-to-date HD map.