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

Cameras for traffic surveillance are usually pole-mounted and produce imagesthat reflect a birds-eye view. Vehicles in such images, in general, assume anellipse form. A bounding box for the vehicles usually includes a large emptyspace when the vehicle orientation is not parallel to the edges of the box. Tocircumvent this problem, the present study applied bounding ellipses to anon-anchor-based, single-shot detection model (CenterNet). Since this modeldoes not depend on anchor boxes, non-max suppression (NMS) that requirescomputing the intersection over union (IOU) between predicted bounding boxes isunnecessary for inference. The SpotNet that extends the CenterNet model byadding a segmentation head was also tested with bounding ellipses. Two otheranchor-based, single-shot detection models (YOLO4 and SSD) were chosen asreferences for comparison. The model performance was compared based on a localdataset that was doubly annotated with bounding boxes and ellipses. As aresult, the performance of the two models with bounding ellipses exceeded thatof the reference models with bounding boxes. When the backbone of the ellipsemodels was pretrained on an open dataset (UA-DETRAC), the performance wasfurther enhanced. The data augmentation schemes developed for YOLO4 alsoimproved the performance of the proposed models. As a result, the best mAPscore of a CenterNet with bounding ellipses exceeds 0.9.

Non-anchor-based vehicle detection for traffic surveillance using bounding ellipses