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

Localization has been a challenging task for autonomous navigation. A loopdetection algorithm must overcome environmental changes for the placerecognition and re-localization of robots. Therefore, deep learning has beenextensively studied for the consistent transformation of measurements intolocalization descriptors. Street view images are easily accessible; however,images are vulnerable to appearance changes. LiDAR can robustly provide precisestructural information. However, constructing a point cloud database isexpensive, and point clouds exist only in limited places. Different fromprevious works that train networks to produce shared embedding directly betweenthe 2D image and 3D point cloud, we transform both data into 2.5D depth imagesfor matching. In this work, we propose a novel cross-matching method, called(LC)$^2$, for achieving LiDAR localization without a prior point cloud map. Tothis end, LiDAR measurements are expressed in the form of range images beforematching them to reduce the modality discrepancy. Subsequently, the network istrained to extract localization descriptors from disparity and range images.Next, the best matches are employed as a loop factor in a pose graph. Usingpublic datasets that include multiple sessions in significantly differentlighting conditions, we demonstrated that LiDAR-based navigation systems couldbe optimized from image databases and vice versa.

(LC)$^2$: LiDAR-Camera Loop Constraints For Cross-Modal Place Recognition