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

To assist human drivers and autonomous vehicles in assessing crash risks,driving scene analysis using dash cameras on vehicles and deep learningalgorithms is of paramount importance. Although these technologies areincreasingly available, driving scene analysis for this purpose still remains achallenge. This is mainly due to the lack of annotated large image datasets foranalyzing crash risk indicators and crash likelihood, and the lack of aneffective method to extract lots of required information from complex drivingscenes. To fill the gap, this paper develops a scene analysis system. TheMulti-Net of the system includes two multi-task neural networks that performscene classification to provide four labels for each scene. The DeepLab v3 andYOLO v3 are combined by the system to detect and locate risky pedestrians andthe nearest vehicles. All identified information can provide the situationalawareness to autonomous vehicles or human drivers for identifying crash risksfrom the surrounding traffic. To address the scarcity of annotated imagedatasets for studying traffic crashes, two completely new datasets have beendeveloped by this paper and made available to the public, which were proved tobe effective in training the proposed deep neural networks. The paper furtherevaluates the performance of the Multi-Net and the efficiency of the developedsystem. Comprehensive scene analysis is further illustrated with representativeexamples. Results demonstrate the effectiveness of the developed system anddatasets for driving scene analysis, and their supportiveness for crash riskassessment and crash prevention.

A system of vision sensor based deep neural networks for complex driving scene analysis in support of crash risk assessment and prevention