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

As a large proportion of road accidents occur at intersections, monitoringtraffic safety of intersections is important. Existing approaches are designedto investigate accidents in lane-based traffic. However, such approaches arenot suitable in a lane-less mixed-traffic environment where vehicles often plyvery close to each other. Hence, we propose an approach called SiameseInteraction Long Short-Term Memory network (SILSTM) to detect collision pronevehicle behavior. The SILSTM network learns the interaction trajectory of avehicle that describes the interactions of a vehicle with its neighbors at anintersection. Among the hundreds of interactions for every vehicle, there maybeonly some interactions which may be unsafe and hence, a temporal attentionlayer is used in the SILSTM network. Furthermore, the comparison of interactiontrajectories requires labeling the trajectories as either unsafe or safe, butsuch a distinction is highly subjective, especially in lane-less traffic.Hence, in this work, we compute the characteristics of interaction trajectoriesinvolved in accidents using the collision energy model. The interactiontrajectories that match accident characteristics are labeled as unsafe whilethe rest are considered safe. Finally, there is no existing dataset that allowsus to monitor a particular intersection for a long duration. Therefore, weintroduce the SkyEye dataset that contains 1 hour of continuous aerial footagefrom each of the 4 chosen intersections in the city of Ahmedabad in India. Adetailed evaluation of SILSTM on the SkyEye dataset shows that unsafe(collision-prone) interaction trajectories can be effectively detected atdifferent intersections.

Detection of Collision-Prone Vehicle Behavior at Intersections using Siamese Interaction LSTM