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

Background modeling is widely used for intelligent surveillance systems todetect moving targets by subtracting the static background components. Mostroadside LiDAR object detection methods filter out foreground points bycomparing new data points to pre-trained background references based ondescriptive statistics over many frames (e.g., voxel density, number ofneighbors, maximum distance). However, these solutions are inefficient underheavy traffic, and parameter values are hard to transfer from one scenario toanother. In early studies, the probabilistic background modeling methods widelyused for the video-based system were considered unsuitable for roadside LiDARsurveillance systems due to the sparse and unstructured point cloud data. Inthis paper, the raw LiDAR data were transformed into a structuredrepresentation based on the elevation and azimuth value of each LiDAR point.With this high-order tensor representation, we break the barrier to allowefficient high-dimensional multivariate analysis for roadside LiDAR backgroundmodeling. The Bayesian Nonparametric (BNP) approach integrates the intensityvalue and 3D measurements to exploit the measurement data using 3D andintensity info entirely. The proposed method was compared against twostate-of-the-art roadside LiDAR background models, computer vision benchmark,and deep learning baselines, evaluated at point, object, and path levels underheavy traffic and challenging weather. This multimodal Weighted BayesianGaussian Mixture Model (GMM) can handle dynamic backgrounds with noisymeasurements and substantially enhances the infrastructure-based LiDAR objectdetection, whereby various 3D modeling for smart city applications could becreated.

Weighted Bayesian Gaussian Mixture Model for Roadside LiDAR Object Detection