Faster R-CNN for Robust Pedestrian Detection Using Semantic Segmentation Network

Convolutional neural networks (CNN) have enabled significant improvements in pedestrian detection owing to the strong representation ability of the CNN features. However, it is generally difficult to reduce false positives on hard negative samples such as tree leaves, traffic lights, poles, etc. Som...

Full beskrivning

Sparad:
Bibliografiska uppgifter
Huvudupphovsmän: Tianrui Liu, Tania Stathaki
Materialtyp: Artigo
Språk:Inglês
Publicerad: Frontiers Media S.A. 2018-10-01
Serie:Frontiers in Neurorobotics
Ämnen:
pedestrian detection
deep learning
convolutional neural network
semantic segmentation
region proposal
Länkar:https://www.frontiersin.org/article/10.3389/fnbot.2018.00064/full
Taggar: Lägg till en tagg
Inga taggar, Lägg till första taggen!

Liknande verk