摘要
随着科技的飞速发展,辅助驾驶技术已经成为汽车行业未来发展的重要方向。在基于图像的道路障碍物检测中,现有方法对尺度变化大的目标、小目标和存在遮挡目标的检测能力有限,常出现误判和漏判等问题。针对此问题,提出了一种基于自注意力与双向特征融合的道路障碍物检测方法(CoXt-FCOS)。该方法在主干特征提取网络中引入分组的自注意力机制模块CoXT,以增强网络的全局信息捕获能力;为解决遮挡问题,引入跨阶段金字塔池化模块SPPCSPC;在特征融合模块中,引入路径增强网络,形成双向特征融合模块ESPAFPN,提升网络对小目标的感知能力。实验结果表明,CoXT-FCOS模型的精度较高,在CODA数据集上的mAP达到了88%,能够更准确地检测出道路上的障碍物。
With the rapid development of technology,assisted driving technology has become an important direction for the future development of the automotive industry.In image-based road obstacle detection,existing methods have limited detection capabilities for targets with large scale changes,small targets,and targets with occlusion,often resulting in misjudgments and omissions.To address this problem,a road obstacle detection method based on self-attention and bidirectional feature fusion(CoXt-FCOS)is proposed.This method introduces a grouped self-attention mechanism module CoXT in the backbone to enhance the global information capture capabilities of the network.To solve the occlusion problem,a cross-stage pyramid pooling module SPPCSPC is introduced.In the feature fusion module,a path enhancement network is introduced,forming a bidirectional feature fusion module ESPAFPN,to enhance the network’s perception of small targets.Experiments show that the CoXT-FCOS model has high accuracy,with an mAP of 88% on the CODA dataset,and can more accurately detect obstacles on the road.
作者
李婷
赵尔敦
杨军
LI Ting;ZHAO Erdun;YANG Jun(School of Computer Science,Central China Normal University,Wuhan 430079,China)
出处
《计算机科学》
CSCD
北大核心
2024年第S02期277-281,共5页
Computer Science
关键词
障碍物检测
自动驾驶
FCOS
自注意力机制
特征融合
Obstacle detection
Autopilot
Fully convolutional one-stage object detection
Self-attentio
Feature fusion
作者简介
LI Ting,born in 1997,postgraduate.Her main research interests include computer vision,object detection and autopilot,liting@mails.ccnu.edu.cn;通信作者:ZHAO Erdun,born in 1972,Ph.D,associate professor.His main research interests include computer vision,object detection and autopilot.erdunz@ccnu.edu.cn。
