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

Detecting dangerous traffic agents in videos captured by vehicle-mounteddashboard cameras (dashcams) is essential to facilitate safe navigation in acomplex environment. Accident-related videos are just a minor portion of thedriving video big data, and the transient pre-accident processes are highlydynamic and complex. Besides, risky and non-risky traffic agents can be similarin their appearance. These make risky object localization in the driving videoparticularly challenging. To this end, this paper proposes an attention-guidedmultistream feature fusion network (AM-Net) to localize dangerous trafficagents from dashcam videos. Two Gated Recurrent Unit (GRU) networks use objectbounding box and optical flow features extracted from consecutive video framesto capture spatio-temporal cues for distinguishing dangerous traffic agents. Anattention module coupled with the GRUs learns to attend to the traffic agentsrelevant to an accident. Fusing the two streams of features, AM-Net predictsthe riskiness scores of traffic agents in the video. In supporting this study,the paper also introduces a benchmark dataset called Risky Object Localization(ROL). The dataset contains spatial, temporal, and categorical annotations withthe accident, object, and scene-level attributes. The proposed AM-Net achievesa promising performance of 85.73% AUC on the ROL dataset. Meanwhile, the AM-Netoutperforms current state-of-the-art for video anomaly detection by 6.3% AUC onthe DoTA dataset. A thorough ablation study further reveals AM-Net's merits byevaluating the contributions of its different components.

An Attention-guided Multistream Feature Fusion Network for Localization of Risky Objects in Driving Videos