[1]张 鑫,陈 黎.基于多尺度特征融合的消防车通道占用检测[J].计算机技术与发展,2022,32(10):51-57.[doi:10. 3969 / j. issn. 1673-629X. 2022. 10. 009]
　ZHANG Xin,CHEN Li.Fire Truck Passages Occupancy Detection Based on Multi-scale Feature Fusion[J].,2022,32(10):51-57.[doi:10. 3969 / j. issn. 1673-629X. 2022. 10. 009]
点击复制

基于多尺度特征融合的消防车通道占用检测()

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年10期
页码:
51-57
栏目:
媒体计算
出版日期:
2022-10-10

文章信息/Info

Title:
Fire Truck Passages Occupancy Detection Based on Multi-scale Feature Fusion
文章编号:
1673-629X(2022)10-0051-07
作者:
张 鑫1; 2 ; 陈 黎1; 2
1. 武汉科技大学 计算机科学与技术学院,湖北 武汉 430065
2. 武汉科技大学 智能信息处理与实时工业系统湖北省重点实验室,湖北 武汉 430065
Author(s):
ZHANG Xin1; 2 ; CHEN Li1; 2
1. School of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan 430065,China;
2. Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System,Wuhan University of Science and Technology,W
关键词:
语义分割; 特征融合; 注意力机制; 消防车通道; 占用检测
Keywords:
semantic segmentation; feature fusion; attention mechanism; fire truck passages; occupancy detection
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 10. 009
摘要:
针对屡禁不止的消防车通道占用、堵塞的问题,为保“ 生命通道冶 时时畅通,消防部门定时开展消防车通道安全隐患检查工作变得尤为重要,然而人工巡检消防车通道除了投入成本大、效率低等问题外更存在执法力量不足、取证不便、执法告知不易等难点,致使该问题具备隐患动态的特点。 对此,该文提出一种基于多尺度特征融合网络的消防车通道占用检测算法和光照补偿模块。 首先对图像特别在夜晚场景下进行亮度优化,在图像过亮或过暗的区域实现像素点亮度局部自适应调整,再使用多个分支提取不同尺度图像的特征,并通过注意机制进行优化,最后进行特征融合。 通过语义分割得到目标区域的消防车通道和车辆信息后,利用占用判定算法实现消防车通道的占用检测。 经验证,该方法在相关数据集上白天和夜晚场景检测准确率分别达到了 97% 和 85. 2% ,兼具实时性、高效性等优点,能有效降低消防车通道占用检查难度与成本。
Abstract:
In view of the repeated occupation and blockage of fire truck passages,in order to ensure that the " life passage" is always unblocked,it is particularly important for the fire department to regularly carry out the inspection of potential safety hazards of fire truck passages. However,in addition to the problems of high investment cost and low efficiency,manual inspection of fire truck passage also has difficulties such as insufficient law enforcement force,inconvenient evidence collection and difficult law enforcement notification. As are sult,the problem has the characteristics of hidden danger dynamics. In this case,a fire truck passages occupancy detection algorithm based on multi- scale feature fusion network and illumination compensation module is proposed. Firstly,the brightness of the image,especially in the night scene,is optimized,and the local adaptive adjustment of pixel illumination is realized in the area where the image istoo bright or too dark. Then,multiple branches are used to extract the features of images with different scales and optimized through theattention mechanism. Finally,feature fusion is carried out. After obtaining the fire truck passages and vehicle information in the targetarea through semantic segmentation,the occupation detection of fire truck passages is realized by using the occupation determination algorithm. It has been verified that the accuracy of scene detection in daytime and night on the relevant data sets has reached 97% and 85.2% respectively. It has the advantages of real-time and high efficiency,which can effectively reduce the difficulty and cost of firetruck access inspection.

相似文献/References:

[1]周伟 武港山.基于显著图的花卉图像分类算法研究[J].计算机技术与发展,2011,(11):15.
　ZHOU Wei,WU Gang-shan.Research on Saliency Map Based Flower Image Classification Algorithm[J].,2011,(10):15.
[2]黎粤华,单磊,田仲富,等. 基于多特征融合的视频烟雾检测[J].计算机技术与发展,2016,26(01):129.
　LI Yue-hua,SHAN Lei,TIAN Zhong-fu,et al. Video Smoke Detection Based on Multi Feature Fusion Technology[J].,2016,26(10):129.
[3]刘加运,李玉惠,李勃,等. 一种多维特征融合的车辆对象同一性匹配方法[J].计算机技术与发展,2016,26(04):167.
　LIU Jia-yun,LI Yu-hui,LI Bo,et al. A Vehicle Object Identity Matching Method of Multidimensional Feature Combination[J].,2016,26(10):167.
[4]陈浩翔,蔡建明,刘铿然,等. 手写数字深度特征学习与识别[J].计算机技术与发展,2016,26(07):19.
　CHEN Hao-xiang,CAI Jian-ming,LIU Keng-ran,et al. Deep Learning and Recognition of Handwritten Numeral Features[J].,2016,26(10):19.
[5]张雅倩,曾卫明,石玉虎.基于特征融合与稀疏表示的人耳识别[J].计算机技术与发展,2017,27(12):7.
　ZHANG Ya-qian,ZENG Wei-min,SHI Yu-hu.Ear Recognition Based on Feature Fusion and Sparse Representation[J].,2017,27(10):7.
[6]谭程午,夏利民,王 嘉.基于融合特征的群体行为识别[J].计算机技术与发展,2018,28(01):17.[doi:10.3969/ j. issn.1673-629X.2018.01.004]
　TAN Cheng-wu,XIA Li-min,WANG Jia.Recognition of Human Group Action Based on Fusion Features[J].,2018,28(10):17.[doi:10.3969/ j. issn.1673-629X.2018.01.004]
[7]王 敏,陈立潮,曹建芳,等.Hadoop 下自适应随机权值多特征融合图像分类[J].计算机技术与发展,2018,28(11):30.[doi:10.3969/ j. issn.1673-629X.2018.11.007]
　WANG Min,CHEN Li-chao,CAO Jian-fang,et al.Multi-feature Fusion Image Classification of Adaptive Random Weight Based on Hadoop[J].,2018,28(10):30.[doi:10.3969/ j. issn.1673-629X.2018.11.007]
[8]韩欣欣,叶奇玲.基于 SIFT 和 HOG 特征融合的人体行为识别方法[J].计算机技术与发展,2019,29(06):71.[doi:10. 3969 / j. issn. 1673-629X. 2019. 06. 015]
　HAN Xin-xin,YE Qi-ling.Human Action Recognition Based on Feature Fusion of SIFT and HOG[J].,2019,29(10):71.[doi:10. 3969 / j. issn. 1673-629X. 2019. 06. 015]
[9]宋相法,吕 明.融合三维骨架和深度图像特征的人体行为识别[J].计算机技术与发展,2019,29(07):55.[doi:10. 3969 / j. issn. 1673-629X. 2019. 07. 011]
　SONG Xiang-fa,LYU Ming.Human Activity Recognition Based on Fusing 3D Skeleton and Depth Image Feature[J].,2019,29(10):55.[doi:10. 3969 / j. issn. 1673-629X. 2019. 07. 011]
[10]王泽泓,刘厚泉.基于迁移学习与自适应特征融合的建筑物识别[J].计算机技术与发展,2019,29(12):40.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 007]
　WANG Ze-hong,LIU Hou-quan.Building Recognition Based on Transfer Learning and Adaptive Feature Fusion[J].,2019,29(10):40.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 007]
[11]刘贤梅,刘鹏飞,贾 迪,等.基于多特征融合的城市场景三维点云语义分割[J].计算机技术与发展,2023,33(11):78.[doi:10. 3969 / j. issn. 1673-629X. 2023. 11. 012]
　LIU Xian-mei,LIU Peng-fei,JIA Di,et al.3D Point Cloud Semantic Segmentation of Urban Scene Based on Multi-feature Fusion[J].,2023,33(10):78.[doi:10. 3969 / j. issn. 1673-629X. 2023. 11. 012]
[12]刁君华,冯向萍,马新春.基于多源数据融合的山体滑坡研究[J].计算机技术与发展,2025,(04):214.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0385]
　DIAO Jun-hua,FENG Xiang-ping,MA Xin-chun.Research on Landslides Based on Multi-source Data Fusion[J].,2025,(10):214.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0385]

更新日期/Last Update: 2022-10-10