Neural Attention-Driven Non-Maximum Suppression for Person Detection

Non-maximum suppression (NMS) is a post-processing step in almost every visual object detector. NMS aims to prune the number of overlapping detected candidate regions-of-interest (RoIs) on an image, in order to assign a single and spatially accurate detection to each object. The default NMS algorith...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 32(2023) vom: 24., Seite 2454-2467
1. Verfasser: Symeonidis, Charalampos (VerfasserIn)
Weitere Verfasser: Mademlis, Ioannis, Pitas, Ioannis, Nikolaidis, Nikos
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2023
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article
Beschreibung
Zusammenfassung:Non-maximum suppression (NMS) is a post-processing step in almost every visual object detector. NMS aims to prune the number of overlapping detected candidate regions-of-interest (RoIs) on an image, in order to assign a single and spatially accurate detection to each object. The default NMS algorithm (GreedyNMS) is fairly simple and suffers from severe drawbacks, due to its need for manual tuning. A typical case of failure with high application relevance is pedestrian/person detection in the presence of occlusions, where GreedyNMS doesn't provide accurate results. This paper proposes an efficient deep neural architecture for NMS in the person detection scenario, by capturing relations of neighboring RoIs and aiming to ideally assign precisely one detection per person. The presented Seq2Seq-NMS architecture assumes a sequence-to-sequence formulation of the NMS problem, exploits the Multihead Scale-Dot Product Attention mechanism and jointly processes both geometric and visual properties of the input candidate RoIs. Thorough experimental evaluation on three public person detection datasets shows favourable results against competing methods, with acceptable inference runtime requirements
Beschreibung:Date Completed 02.05.2023
Date Revised 02.05.2023
published: Print-Electronic
Citation Status PubMed-not-MEDLINE
ISSN:1941-0042
DOI:10.1109/TIP.2023.3268561