A Lightweight Model for Real-Time Detection of Vehicle Black Smoke

计算机科学 特征提取 特征(语言学) 目标检测 人工智能 骨干网 网络模型 实时计算 模拟 模式识别(心理学) 电信 语言学 哲学
作者
Ke Chen,Han Wang,Yingchao Zhai
出处
期刊:Sensors [MDPI AG]
卷期号:23 (23): 9492-9492
标识
DOI:10.3390/s23239492
摘要

This paper discusses the application of deep learning technology in recognizing vehicle black smoke in road traffic monitoring videos. The use of massive surveillance video data imposes higher demands on the real-time performance of vehicle black smoke detection models. The YOLOv5s model, known for its excellent single-stage object detection performance, has a complex network structure. Therefore, this study proposes a lightweight real-time detection model for vehicle black smoke, named MGSNet, based on the YOLOv5s framework. The research involved collecting road traffic monitoring video data and creating a custom dataset for vehicle black smoke detection by applying data augmentation techniques such as changing image brightness and contrast. The experiment explored three different lightweight networks, namely ShuffleNetv2, MobileNetv3 and GhostNetv1, to reconstruct the CSPDarknet53 backbone feature extraction network of YOLOv5s. Comparative experimental results indicate that reconstructing the backbone network with MobileNetv3 achieved a better balance between detection accuracy and speed. The introduction of the squeeze excitation attention mechanism and inverted residual structure from MobileNetv3 effectively reduced the complexity of black smoke feature fusion. Simultaneously, a novel convolution module, GSConv, was introduced to enhance the expression capability of black smoke features in the neck network. The combination of depthwise separable convolution and standard convolution in the module further reduced the model’s parameter count. After the improvement, the parameter count of the model is compressed to 1/6 of the YOLOv5s model. The lightweight vehicle black smoke real-time detection network, MGSNet, achieved a detection speed of 44.6 frames per second on the test set, an increase of 18.9 frames per second compared with the YOLOv5s model. The mAP@0.5 still exceeded 95%, meeting the application requirements for real-time and accurate detection of vehicle black smoke.
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
大幅提高文件上传限制,最高150M (2024-4-1)

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
叶世玉发布了新的文献求助10
刚刚
楼迎荷发布了新的文献求助10
1秒前
科目三应助科研通管家采纳,获得10
1秒前
SciGPT应助科研通管家采纳,获得10
1秒前
英俊的铭应助科研通管家采纳,获得10
1秒前
慕青应助科研通管家采纳,获得10
2秒前
2秒前
2秒前
2秒前
科研通AI2S应助科研通管家采纳,获得10
2秒前
2秒前
2秒前
linzhuo发布了新的文献求助10
3秒前
科研菜鸡623完成签到 ,获得积分10
3秒前
4秒前
YHK发布了新的文献求助30
4秒前
华仔应助wx采纳,获得10
4秒前
杨志坚发布了新的文献求助10
5秒前
汉堡包应助lanshuitai采纳,获得10
5秒前
干不动了完成签到,获得积分10
5秒前
文艺的又亦完成签到,获得积分10
6秒前
Liuyicong发布了新的文献求助10
6秒前
合适尔槐完成签到 ,获得积分10
7秒前
小张发布了新的文献求助10
7秒前
Owen应助sunzhuxi采纳,获得10
8秒前
PengHu发布了新的文献求助10
9秒前
害羞凡阳完成签到,获得积分10
9秒前
张皓123完成签到,获得积分10
9秒前
10秒前
11111发布了新的文献求助10
10秒前
所所应助Tici采纳,获得30
10秒前
LYQ完成签到,获得积分10
10秒前
暴躁的建辉完成签到,获得积分20
11秒前
世间再无延毕完成签到,获得积分10
11秒前
11秒前
12秒前
楼迎荷完成签到,获得积分10
13秒前
牛牛完成签到,获得积分10
13秒前
13秒前
14秒前
高分求助中
Lire en communiste 1000
Ore genesis in the Zambian Copperbelt with particular reference to the northern sector of the Chambishi basin 800
Becoming: An Introduction to Jung's Concept of Individuation 600
中国氢能技术发展路线图研究 500
Communist propaganda: a fact book, 1957-1958 500
Briefe aus Shanghai 1946‒1952 (Dokumente eines Kulturschocks) 500
A new species of Coccus (Homoptera: Coccoidea) from Malawi 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 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 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3168208
求助须知:如何正确求助?哪些是违规求助? 2819559
关于积分的说明 7927087
捐赠科研通 2479402
什么是DOI,文献DOI怎么找? 1320787
科研通“疑难数据库(出版商)”最低求助积分说明 632907
版权声明 602458