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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

In this paper, we propose a new deep architecture for fusing camera and LiDARsensors for 3D object detection. Because the camera and LiDAR sensor signalshave different characteristics and distributions, fusing these two modalitiesis expected to improve both the accuracy and robustness of 3D object detection.One of the challenges presented by the fusion of cameras and LiDAR is that thespatial feature maps obtained from each modality are represented bysignificantly different views in the camera and world coordinates; hence, it isnot an easy task to combine two heterogeneous feature maps without loss ofinformation. To address this problem, we propose a method called 3D-CVF thatcombines the camera and LiDAR features using the cross-view spatial featurefusion strategy. First, the method employs auto-calibrated projection, totransform the 2D camera features to a smooth spatial feature map with thehighest correspondence to the LiDAR features in the bird's eye view (BEV)domain. Then, a gated feature fusion network is applied to use the spatialattention maps to mix the camera and LiDAR features appropriately according tothe region. Next, camera-LiDAR feature fusion is also achieved in thesubsequent proposal refinement stage. The camera feature is used from the 2Dcamera-view domain via 3D RoI grid pooling and fused with the BEV feature forproposal refinement. Our evaluations, conducted on the KITTI and nuScenes 3Dobject detection datasets demonstrate that the camera-LiDAR fusion offerssignificant performance gain over single modality and that the proposed 3D-CVFachieves state-of-the-art performance in the KITTI benchmark.

3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection