AspectNet: Aspect-Aware Anchor-Free Detector for Autonomous Driving

The anchor-free-based object detection method is a crucial part in an autonomous driving system because of its low computing cost. However, the under-fitting of positive samples and over-fitting of negative samples affect the detection performance. An aspect-aware anchor-free detector is proposed in...

Full description

Saved in:
Bibliographic Details
Published inApplied sciences Vol. 12; no. 12; p. 5972
Main Authors Liang, Tianjiao, Bao, Hong, Pan, Weiguo, Fan, Xinyue, Li, Han
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.06.2022
Subjects
anchor free
autonomous driving
Boxes
Deep learning
Methods
object detection
Sensors
Online AccessGet full text

Cover

More Information
Summary:The anchor-free-based object detection method is a crucial part in an autonomous driving system because of its low computing cost. However, the under-fitting of positive samples and over-fitting of negative samples affect the detection performance. An aspect-aware anchor-free detector is proposed in this paper to address this problem. Specifically, it adds an aspect prediction head at the end of the detector, which can learn different distributions of aspect ratios between other objects. The sample definition method is improved to alleviate the problem of positive and negative sample imbalance. A loss function is designed to strengthen the learning weight of the center point of the network. The validation results show that the AP50 and AP75 of the proposed method are 97.3% and 93.4% on BCTSDB, and the average accuracies of the car, pedestrian, and cyclist are 92.7%, 77.4%, and 78.2% on KITTI, respectively. The comparison results demonstrate that the proposed algorithm is better than existing anchor-free methods.
ISSN:2076-3417
2076-3417
DOI:10.3390/app12125972