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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

To mitigate the challenges arising from partial occlusion in human posekeypoint based pedestrian detection methods , we present a novel pedestrianpose keypoint completion method called the separation and dimensionalityreduction-based generative adversarial imputation networks (SDR-GAIN) .Firstly, we utilize OpenPose to estimate pedestrian poses in images. Then, weisolate the head and torso keypoints of pedestrians with incomplete keypointsdue to occlusion or other factors and perform dimensionality reduction toenhance features and further unify feature distribution. Finally, we introducetwo generative models based on the generative adversarial networks (GAN)framework, which incorporate Huber loss, residual structure, and L1regularization to generate missing parts of the incomplete head and torso posekeypoints of partially occluded pedestrians, resulting in pose completion. Ourexperiments on MS COCO and JAAD datasets demonstrate that SDR-GAIN outperformsbasic GAIN framework, interpolation methods PCHIP and MAkima, machine learningmethods k-NN and MissForest in terms of pose completion task. Furthermore, theSDR-GAIN algorithm exhibits a remarkably short running time of approximately0.4ms and boasts exceptional real-time performance. As such, it holdssignificant practical value in the domain of autonomous driving, wherein highsystem response speeds are of paramount importance. Specifically, it excels atrapidly and precisely capturing human pose key points, thus enabling anexpanded range of applications for pedestrian detection tasks based on pose keypoints, including but not limited to pedestrian behavior recognition andprediction.

SDR-GAIN: A High Real-Time Occluded Pedestrian Pose Completion Method for Autonomous Driving