Rotational multipyramid network with bounding‐box transformation for object detection

The study proposes a rotational multipyramid network (RoMP Net) with bounding‐box transformation for object detection. The RoMP Net is a single‐stage object detection neural network featuring three characteristics. First, the network uses a rotational bounding box to minimize the effect of backgroun...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	International journal of intelligent systems 2021-09, Vol.36 (9), p.5307-5338
Hauptverfasser:	Kim, Donggeun, Kim, San, Jeong, Siheon, Ham, Ji‐Wan, Son, Seho, Moon, Joonhyeok, Oh, Ki‐Yong
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Artificial neural networks Boxes Clustering Computer architecture Computer Science Computer Science, Artificial Intelligence Critical components deep learning Feature extraction High aspect ratio hyperplane Image transmission Intelligent systems multi‐scale and multi‐level feature extraction Neural networks object detection Object recognition Optimization Robustness Science & Technology space transformation Technology Transformations
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!