DetectFormer: Category-Assisted Transformer for Traffic Scene Object Detection

Object detection plays a vital role in autonomous driving systems, and the accurate detection of surrounding objects can ensure the safe driving of vehicles. This paper proposes a category-assisted transformer object detector called DetectFormer for autonomous driving. The proposed object detector c...

Full description

Saved in:
Bibliographic Details
Published in:Sensors (Basel, Switzerland) Switzerland), 2022-06, Vol.22 (13), p.4833
Main Authors: Liang, Tianjiao, Bao, Hong, Pan, Weiguo, Fan, Xinyue, Li, Han
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
autonomous driving
Classification
deep learning
Driving
Machine translation
Methods
Natural language processing
object detection
Sensors
transformer
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Object detection plays a vital role in autonomous driving systems, and the accurate detection of surrounding objects can ensure the safe driving of vehicles. This paper proposes a category-assisted transformer object detector called DetectFormer for autonomous driving. The proposed object detector can achieve better accuracy compared with the baseline. Specifically, ClassDecoder is assisted by proposal categories and global information from the Global Extract Encoder (GEE) to improve the category sensitivity and detection performance. This fits the distribution of object categories in specific scene backgrounds and the connection between objects and the image context. Data augmentation is used to improve robustness and attention mechanism added in backbone network to extract channel-wise spatial features and direction information. The results obtained by benchmark experiment reveal that the proposed method can achieve higher real-time detection performance in traffic scenes compared with RetinaNet and FCOS. The proposed method achieved a detection performance of 97.6% and 91.4% in AP50 and AP75 on the BCTSDB dataset, respectively.
ISSN:1424-8220
1424-8220
DOI:10.3390/s22134833