本文二维码信息
二维码（扫一下试试看！）
PHAM-YOLO Network-based Detection Method of Combustion Line of Cigarette Paper
Received:December 13, 2023  
DOI：10.11980/j.issn.0254-508X.2024.03.016
Key Words:cigarette paper  combustion line detection  YOLO  parallel hybrid attention mechanism
Fund Project:烟草行业标准项目“卷烟包灰性能测试方法”（2021B023）；国家烟草专卖局重大科技项目“烟草行业质量监控大数据构建及应用研究”（110202101080（SJ-04））。
Author NameAffiliationPostcode
DONG Hao University of Science and Technology of China， Hefei， Anhui Province， 230031
Hefei Institutes of Physical Science of CAS， Hefei， Anhui Province， 230031
China National Tobacco Quality Supervision and Test Center， Zhengzhou， He’nan Province， 450001 		450001
WANG Shu Hefei Institutes of Physical Science of CAS， Hefei， Anhui Province， 230031 230031
LU Xiaojia Hefei Institutes of Physical Science of CAS， Hefei， Anhui Province， 230031 230031
LIU Qiang Inner Mongolia Kunming Cigarette Limited Liability Co.， Hohhot， Inner Mongolia Autonomous Region， 010020 010020
GUO Xiaowei Inner Mongolia Kunming Cigarette Limited Liability Co.， Hohhot， Inner Mongolia Autonomous Region， 010020 010020
GAO Junjie Inner Mongolia Kunming Cigarette Limited Liability Co.， Hohhot， Inner Mongolia Autonomous Region， 010020 010020
ZHANG Long Hefei Institutes of Physical Science of CAS， Hefei， Anhui Province， 230031 230031
HU Xingfeng* China Tobacco Chongqing Industrial Co.， Ltd.， Chongqing， 400060 400060
ZHOU Mingzhu China National Tobacco Quality Supervision and Test Center， Zhengzhou， He’nan Province， 450001 450001
XING Jun China National Tobacco Quality Supervision and Test Center， Zhengzhou， He’nan Province， 450001 450001
Hits: 648
Download times: 389
Abstract:To determine the combustion line of cigarette paper， the dataset for cigarette combustion line detection was construct from common scenarios. To address the challenges of detecting complex backgrounds， multiple targets， varying scales， and shapes of combustion lines， a PHAM （parallel hybrid attention mechanism） was embedded into the YOLO v5 （you only look once， version 5） backbone network， and PHAM-YOLO was constructed for detecting multiple targets with varying scales and shapes in complex backgrounds. In addition， a spatial pyramid pooling fast （SPPF）， the boundary box regression （BBR） module were introduced to improve the accuracy of combustion line positioning. The results showed that the proposed PHAM-YOLO network achieved the average precision mean （mAP）， precision（P） and recall （R） of 99.0%， 99.8%， and 99.0%， respectively， where mAP was improved by 5.0% compared to the original model and higher than other types of target detection methods.
View Full Text  HTML  View/Add Comment  Download reader