基于改进YOLOv8s的夜间车辆检测
Improved YOLOv8s-Based Night Vehicle Detection
万欣蕾 1司占军1
作者信息
- 1. 天津科技大学 人工智能学院,天津 300457
- 折叠
摘要
随着自动驾驶技术的逐渐发展,人们的注意力不再局限于日常的自动驾驶目标检测.对于难以快速准确检测夜间自动驾驶复杂场景中视觉目标的问题,本研究提出了一种基于改进YOLOv8s的检测算法.首先,该模型通过在原始模型中的下采样层加入Triplet Attention注意力模块,该模型可以更好地保留和增强较低分辨率的特征图上与目标检测相关的特征信息,增强目标检测网络的鲁棒性,减少漏检问题;其次,在处理密集目标、重叠对象和复杂场景时,引入了Soft-NMS算法,其有助于减少误报和漏报,并在处理高度重叠的检测结果时提高了整体检测性能;最后,在引入MPDIoU损失函数数据集的实验结果表明,与原模型相比,改进后的方法在夜间车辆检测中的检测精度和速度均得到提升,其mAP和精度分别提高了2.9%和2.8%,可以有效改善夜间目标检测问题.
Abstract
With the gradual development of automatic driving technology,people's attention is no longer limited to daily automatic driving target detection.In response to the problem that it is difficult to achieve fast and accurate detection of visual targets in complex scenes of automatic driving at night,a detection algorithm based on improved YOLOv8s was proposed.Firsly,By adding Triplet Attention module into the lower sampling layer of the original model,the model can effectively retain and enhance feature information related to target detection on the lower-resolution feature map.This enhancement improved the robustness of the target detection network and reduced instances of missed detections.Secondly,the Soft-NMS algorithm was introduced to address the challenges of dealing with dense targets,overlapping objects,and complex scenes.This algorithm effectively reduced false and missed positives,thereby improved overall detection performance when faced with highly overlapping detection results.Finally,the experimental results on the MPDIoU loss function dataset showed that compared with the original model,the improved method,in which mAP and accuracy are increased by 2.9%and 2.8%respectively,can achieve better detection accuracy and speed in night vehicle detection.It can effectively improve the problem of target detection in night scenes.
关键词
车辆检测/YOLOv8/注意力机制Key words
Vehicle detection/Yolov8/Attention mechanism引用本文复制引用
出版年
2024
NETL
NSTL
万方数据