计算机科学
棱锥(几何)
目标检测
残余物
人工智能
特征(语言学)
对象(语法)
卷积(计算机科学)
模式识别(心理学)
网络结构
算法
计算机视觉
数学
机器学习
人工神经网络
语言学
哲学
几何学
作者
Jing Zhou,Xiaohan Huang,Qin Zebang,Yin Guo
出处
期刊:Lecture notes in electrical engineering
日期:2024-01-01
卷期号:: 268-277
标识
DOI:10.1007/978-981-99-9239-3_27
摘要
Aiming at the difficulty of small object detection, a small object detection model combining coordinated attention mechanism and P2-BiFPN (P2 Bidirectional Feature Pyramid Network) structure is constructed based on YOLOv5. Firstly, we introduce the coordinated attention mechanism into the residual units of the backbone network to achieve more accurate localization of small objects. Secondly, to reduce the number of model parameters, we decompose the square convolution in the residual unit into parallel asymmetric convolutions. Then, the P2-BiFPN feature fusion network was constructed to enrich the information of small objects, so as to improve the small objects detection accuracy. Finally, we train and test the model on the WiderPerson dataset. The experimental results shows that compared with YOLOv5, our small object detection model has a 1.7% improvement in mAP and a 5.66 m reduction in the amount of parameters, with better detection performance for small-object pedestrians.
科研通智能强力驱动
Strongly Powered by AbleSci AI