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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tianrui Liu, Tania Stathaki
Format: Artigo
Sprache:Inglês
Veröffentlicht: Frontiers Media S.A. 2018-10-01
Schriftenreihe:Frontiers in Neurorobotics
Schlagworte:
pedestrian detection
deep learning
convolutional neural network
semantic segmentation
region proposal
Online Zugang:https://www.frontiersin.org/article/10.3389/fnbot.2018.00064/full
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge