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

Machine learning (ML)-enabled approaches are considered a substantial supporttechnique of detection and classification of obstacles of traffic participantsin self-driving vehicles. Major breakthroughs have been demonstrated the pastfew years, even covering complete end-to-end data processing chain from sensoryinputs through perception and planning to vehicle control of acceleration,breaking and steering. YOLO (you-only-look-once) is a state-of-the-artperception neural network (NN) architecture providing object detection andclassification through bounding box estimations on camera images. As the NN istrained on well annotated images, in this paper we study the variations ofconfidence levels from the NN when tested on hand-crafted occlusion added to atest set. We compare regular pedestrian detection to upper and lower bodydetection. Our findings show that the two NN using only partial informationperform similarly well like the NN for the full body when the full body NN'sperformance is 0.75 or better. Furthermore and as expected, the network, whichis only trained on the lower half body is least prone to disturbances fromocclusions of the upper half and vice versa.

Understanding the Impact of Edge Cases from Occluded Pedestrians for ML Systems