YOLOv8-CB: Dense Pedestrian Detection Algorithm Based on In-Vehicle Camera

行人检测 计算机科学 保险丝(电气) 算法 人工智能 行人 特征(语言学) 级联 目标检测 计算机视觉 模式识别(心理学) 工程类 语言学 哲学 电气工程 化学工程 运输工程
作者
Qiuli Liu,Haixiong Ye,Shiming Wang,Zhe Xu
出处
期刊:Electronics [Multidisciplinary Digital Publishing Institute]
卷期号:13 (1): 236-236
标识
DOI:10.3390/electronics13010236
摘要

Recently, the field of vehicle-mounted visual intelligence technology has witnessed a surge of interest in pedestrian detection. Existing algorithms for dense pedestrian detection at intersections face challenges such as high computational weight, complex models that are difficult to deploy, and suboptimal detection accuracy for small targets and highly occluded pedestrians. To address these issues, this paper proposes an improved lightweight multi-scale pedestrian detection algorithm, YOLOv8-CB. The algorithm introduces a lightweight cascade fusion network, CFNet (cascade fusion network), and a CBAM attention module to improve the characterization of multi-scale feature semantics and location information, and it superimposes a bidirectional weighted feature fusion path BIFPN structure to fuse more effective features and improve pedestrian detection performance. It is experimentally verified that compared with the YOLOv8n algorithm, the accuracy of the improved model is increased by 2.4%, the number of model parameters is reduced by 6.45%, and the computational load is reduced by 6.74%. The inference time for a single image is 10.8 ms. The cascade fusion algorithm YOLOv8-CB has higher detection accuracy and is a lighter model for multi-scale pedestrian detection in complex scenes such as streets or intersections. This proposed algorithm presents a valuable approach for device-side pedestrian detection with limited computational resources.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
Xiaoxiao应助shinn采纳,获得10
1秒前
cat关闭了cat文献求助
3秒前
英姑应助xuexi采纳,获得10
4秒前
wihjnfnk发布了新的文献求助10
4秒前
yls完成签到,获得积分10
4秒前
郑未晚完成签到,获得积分10
5秒前
5秒前
情怀应助大饼卷肉采纳,获得10
7秒前
科研通AI2S应助旋律采纳,获得10
8秒前
CipherSage应助飘逸的寄柔采纳,获得10
8秒前
SciGPT应助小妮采纳,获得10
10秒前
adding发布了新的文献求助10
10秒前
11秒前
13秒前
13秒前
14秒前
honey完成签到,获得积分10
14秒前
小李先绅发布了新的文献求助10
14秒前
17秒前
大神装完成签到,获得积分10
18秒前
青衣北风发布了新的文献求助10
19秒前
19秒前
旋律完成签到,获得积分10
19秒前
失眠朋友发布了新的文献求助10
19秒前
19秒前
jiujiuhuang完成签到,获得积分10
19秒前
专注寻菱完成签到,获得积分10
19秒前
MAKEYF发布了新的文献求助10
20秒前
22秒前
23秒前
zyw发布了新的文献求助10
23秒前
科研通AI5应助王sir采纳,获得10
23秒前
追寻的雁完成签到,获得积分10
23秒前
23秒前
24秒前
25秒前
25秒前
小二郎应助小李先绅采纳,获得10
25秒前
25秒前
无私的孤风完成签到,获得积分20
26秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
Immigrant Incorporation in East Asian Democracies 600
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3967544
求助须知:如何正确求助?哪些是违规求助? 3512763
关于积分的说明 11165008
捐赠科研通 3247759
什么是DOI,文献DOI怎么找? 1794027
邀请新用户注册赠送积分活动 874808
科研通“疑难数据库(出版商)”最低求助积分说明 804528