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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Place recognition is an important technique for autonomous cars to achievefull autonomy since it can provide an initial guess to online localizationalgorithms. Although current methods based on images or point clouds haveachieved satisfactory performance, localizing the images on a large-scale pointcloud map remains a fairly unexplored problem. This cross-modal matching taskis challenging due to the difficulty in extracting consistent descriptors fromimages and point clouds. In this paper, we propose the I2P-Rec method to solvethe problem by transforming the cross-modal data into the same modality.Specifically, we leverage on the recent success of depth estimation networks torecover point clouds from images. We then project the point clouds into Bird'sEye View (BEV) images. Using the BEV image as an intermediate representation,we extract global features with a Convolutional Neural Network followed by aNetVLAD layer to perform matching. The experimental results evaluated on theKITTI dataset show that, with only a small set of training data, I2P-Recachieves recall rates at Top-1\% over 80\% and 90\%, when localizing monocularand stereo images on point cloud maps, respectively. We further evaluateI2P-Rec on a 1 km trajectory dataset collected by an autonomous logistics carand show that I2P-Rec can generalize well to previously unseen environments.

I2P-Rec: Recognizing Images on Large-scale Point Cloud Maps through Bird's Eye View Projections