A lightweight defect detection algorithm for escalator steps

计算机科学 修剪 算法 棱锥(几何) 联营 人工智能 基线(sea) 目标检测 模式识别(心理学) 数据挖掘 数学 几何学 农学 生物 海洋学 地质学
作者
Hui Yu,Jiayan Chen,Ping Yu,Da Feng
出处
期刊:Scientific Reports [Nature Portfolio]
卷期号:14 (1)
标识
DOI:10.1038/s41598-024-74320-9
摘要

Abstract In this paper, we propose an efficient target detection algorithm, ASF-Sim-YOLO, to address issues encountered in escalator step defect detection, such as an excessive number of parameters in the detection network model, poor adaptability, and difficulties in real-time processing of video streams. Firstly, to address the characteristics of escalator step defects, we designed the ASF-Sim-P2 structure to improve the detection accuracy of small targets, such as step defects. Additionally, we incorporated the SimAM (Similarity-based Attention Mechanism) by combining SimAM with SPPF (Spatial Pyramid Pooling-Fast) to enhance the model’s ability to capture key information by assigning importance weights to each pixel. Furthermore, to address the challenge posed by the small size of step defects, we replaced the traditional CIoU (Complete-Intersection-over-Union) loss function with NWD (Normalized Wasserstein Distance), which alleviated the problem of defect missing. Finally, to meet the deployment requirements of mobile devices, we performed channel pruning on the model. The experimental results showed that the improved ASF-Sim-YOLO model achieved an average accuracy (mAP50) of 96.8% on the test data set, which was a 22.1% improvement in accuracy compared to the baseline model. Meanwhile, the computational complexity (in GFLOPS) of the model was reduced to a quarter of that of the baseline model, while the frame rate (FPS) was improved to 575.1. Compared with YOLOv3-tiny, YOLOv5s, YOLOv8s, Faster-RCNN, TOOD, RTMDET and other deep learning-based target recognition algorithms, ASF-Sim-YOLO has better detection accuracy and real-time processing capability. These results demonstrate that ASF-Sim-YOLO effectively balances lightweight design and performance improvement, making it highly suitable for real-time detection of step defects, which can meet the demands of escalator inspection operations.

科研通智能强力驱动
Strongly Powered by AbleSci AI
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
Jasper的应助被ss采纳,获得10
刚刚
米糊发布了新的文献求助10
1秒前
Annna完成签到,获得积分20
1秒前
曾经冰露完成签到,获得积分10
1秒前
元宝芒果黑虎完成签到,获得积分20
1秒前
1秒前
11完成签到,获得积分10
1秒前
2秒前
务实的忆雪的应助被美丽人生采纳,获得10
2秒前
2秒前
2秒前
yuta123发布了新的文献求助10
3秒前
kong发布了新的文献求助10
3秒前
棠棠完成签到 ,获得积分10
3秒前
3秒前
Annna发布了新的文献求助10
3秒前
3秒前
4秒前
Esang完成签到,获得积分10
4秒前
就爱炸元宵完成签到,获得积分10
4秒前
路宝发布了新的文献求助10
4秒前
lius发布了新的文献求助10
4秒前
5秒前
lxt发布了新的文献求助10
5秒前
深情安青的应助被开朗的慕儿采纳,获得10
5秒前
5秒前
5秒前
5秒前
6秒前
6秒前
duyi0521完成签到,获得积分10
6秒前
6秒前
霁月发布了新的文献求助10
6秒前
drizzle发布了新的文献求助10
6秒前
Sonder完成签到,获得积分10
6秒前
6秒前
6秒前
fangkong发布了新的文献求助10
6秒前
zaq66996发布了新的文献求助10
6秒前
7秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Boundaries and Bodhisattvas 500
高分子基功能界面水蒸发材料与应用研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8182602
求助须知:如何正确求助?哪些是违规求助? 9572033
关于积分的说明 21821767
捐赠科研通 7779061
什么是DOI,文献DOI怎么找? 3433684
关于科研通互助平台的介绍 2557863
邀请新用户注册赠送积分活动 2479732