English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The fusion of LiDARs and cameras has been increasingly adopted in autonomousdriving for perception tasks. The performance of such fusion-based algorithmslargely depends on the accuracy of sensor calibration, which is challenging dueto the difficulty of identifying common features across different datamodalities. Previously, many calibration methods involved specific targetsand/or manual intervention, which has proven to be cumbersome and costly.Learning-based online calibration methods have been proposed, but theirperformance is barely satisfactory in most cases. These methods usually sufferfrom issues such as sparse feature maps, unreliable cross-modality association,inaccurate calibration parameter regression, etc. In this paper, to addressthese issues, we propose CalibFormer, an end-to-end network for automaticLiDAR-camera calibration. We aggregate multiple layers of camera and LiDARimage features to achieve high-resolution representations. A multi-headcorrelation module is utilized to identify correlations between features moreaccurately. Lastly, we employ transformer architectures to estimate accuratecalibration parameters from the correlation information. Our method achieved amean translation error of $0.8751 \mathrm{cm}$ and a mean rotation error of$0.0562 ^{\circ}$ on the KITTI dataset, surpassing existing state-of-the-artmethods and demonstrating strong robustness, accuracy, and generalizationcapabilities.

CalibFormer: A Transformer-based Automatic LiDAR-Camera Calibration Network