A method of cross-layer fusion multi-object detection and recognition based on improved faster R-CNN model in complex traffic environment

•Cross-layer Fusion.•Multi-object Detection and Recognition.•Faster R-CNN Model.•Multi-class cross entropy loss function.•Soft-NMS. Improving the detection accuracy and speed is the prerequisite of multi-object recognition in the complex traffic environment. Despite object detection has made signifi...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Pattern recognition letters 2021-05, Vol.145, p.127-134
Hauptverfasser:	Li, Cui-jin, Qu, Zhong, Wang, Sheng-ye, Liu, Ling
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Artificial neural networks Convolution Datasets Embedding Entropy (Information theory) Faster R-CNN Multi-object detection Multi-object recognition Neural networks Object recognition Occlusion Pattern recognition Traffic models Traffic speed Weighted balanced multi-class cross entropy loss function
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!