ALODAD: An Anchor-Free Lightweight Object Detector for Autonomous Driving

Vision-based object detection is an essential component of autonomous driving. Because vehicles typically have limited on-board computing resources, a small-sized detection model is required. Simultaneously, high object detection accuracy and real-time inference detection speeds are required to ensu...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2022, Vol.10, p.40701-40714
Main Authors: Liang, Tianjiao, Bao, Hong, Pan, Weiguo, Pan, Feng
Format: Article
Language:English
Subjects:
Accuracy
Autonomous driving
Autonomous vehicles
Computational modeling
Convolution
deep learning
Driver behavior
Driving
Feature extraction
Lightweight
Location awareness
Neural networks
Object detection
Object recognition
Pyramids
Real time
Sensors
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:Vision-based object detection is an essential component of autonomous driving. Because vehicles typically have limited on-board computing resources, a small-sized detection model is required. Simultaneously, high object detection accuracy and real-time inference detection speeds are required to ensure safety while driving. In this paper, an anchor-free lightweight object detector for autonomous driving called ALODAD is proposed. ALODAD incorporates an attention scheme into the lightweight neural network GhostNet and builds an anchor-free detection framework to achieve lower computational costs and provide parameters with high detection accuracy. Specifically, the lightweight backbone neural network integrates a convolutional block attention model that analyzes the valuable features from traffic scene images to generate an accurate bounding box, and then constructs feature pyramids for multi-scale object detection. The proposed method adds an intersection over union (IoU) branch to the decoupled detector to rank the vast number of candidate detections accurately. To increase the data diversity, data augmentation was used during training. Extensive experiments based on benchmarks demonstrate that the proposed method offers improved performance compared to the baseline. The proposed method can achieve an increased detection accuracy while meeting the real-time requirements of autonomous driving. The proposed method was compared with the YOLOv5 and RetinaNet models and 98.7% and 94.5% were obtained for the average precision metrics AP50 and AP75, respectively, on the BCTSDB dataset.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2022.3166923