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/

Zendy Plus

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

Zendy Tools

Zendy Open

As a result of significant advances in deep learning, computer visiontechnology has been widely adopted in the field of traffic surveillance.Nonetheless, it is difficult to find a universal model that can measure trafficparameters irrespective of ambient conditions such as times of the day,weather, or shadows. These conditions vary recurrently, but the exact points ofchange are inconsistent and unpredictable. Thus, the application of amulti-regime method would be problematic, even when separate sets of modelparameters are prepared in advance. In the present study we devised a robustapproach that facilitates multi-regime analysis. This approach employs anonline parametric algorithm to determine the change-points for ambientconditions. An autoencoder was used to reduce the dimensions of input images,and reduced feature vectors were used to implement the online change-pointalgorithm. Seven separate periods were tagged with typical times in a givenday. Multi-regime analysis was then performed so that the traffic density couldbe separately measured for each period. To train and test models for vehiclecounting, 1,100 video images were randomly chosen for each period and labeledwith traffic counts. The measurement accuracy of multi-regime analysis was muchhigher than that of an integrated model trained on all data.

Multi-regime analysis for computer vision-based traffic surveillance using a change-point detection algorithm