[1]姚芷馨,张太红,赵昀杰.基于卷积神经网络的多模型交通场景识别研究[J].计算机技术与发展,2022,32(07):93-98.[doi:10. 3969 / j. issn. 1673-629X. 2022. 07. 016]
　YAO Zhi-xin,ZHANG Tai-hong,ZHAO Yun-jie.Research on Multi-model Traffic Scene Recognition Based on Convolution Neural Network[J].,2022,32(07):93-98.[doi:10. 3969 / j. issn. 1673-629X. 2022. 07. 016]
点击复制

基于卷积神经网络的多模型交通场景识别研究()

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

卷:
32
期数:
2022年07期
页码:
93-98
栏目:
图形与图像
出版日期:
2022-07-10

文章信息/Info

Title:
Research on Multi-model Traffic Scene Recognition Based on Convolution Neural Network
文章编号:
1673-629X(2022)07-0093-06
作者:
姚芷馨; 张太红; 赵昀杰
新疆农业大学,新疆 乌鲁木齐 830052
Author(s):
YAO Zhi-xin; ZHANG Tai-hong; ZHAO Yun-jie
Xinjiang Agricultural University,Urumqi 830052,China
关键词:
目标检测; 语义分割; 特征提取; 上采样; 鲁棒性特征
Keywords:
object detection; semantic segmentation; feature extraction; up sampling; robust characteristics
分类号:
TP391. 41
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 07. 016
摘要:
利用人工智能中的视觉分析技术, 实现对高分辨率交通视频中出现的各个目标类别进行实时目标检测、语义分割和目标追踪。 数据集结合 BDD100K 和 Mapillary Vistas。 训练中不仅对模型中的参数进行调整,还对多个模型进行改进与创新。 目标检测模型使用 EfficientNet-B1 作为主干网络,使用 ASPP 与改进后的 FPN 作为脖颈网络,通过引入多种模型训练技巧,对模型进行优化,最终结果减少约 2. 3 倍的参数量,在不同数据集上的准确率都有所提升。 目标追踪使用DeepSort 追踪算法对多个目标类别进行追踪计数。 语义分割使用 Encoder-Decoder 结构,使用 EfficientNet-B4 作为主干网络,参照 U-Net++网络使用卷积层作为特征提取模块,反卷积层作为上采样模块,通过联结不同大小的特征图,得到最终输出结果。 将改进语义分割模型与 MobileNetV2 和 DeeplabV3 网络结合的模型进行对比,减少约 1. 35 倍的参数量。 实验证明,通过深度学习算法提取鲁棒性特征能够为自动驾驶和辅助驾驶场景中的检测识别提供便利。
Abstract:
The visual analysis technology in artificial intelligence is used to realize real-time object detection,semantic segmentation and object tracking for each object category in high-resolution traffic video. The dataset combines BDD100K and Mapillary Vistas. In the training,not only the parameters in the model are adjusted,but also several models are improved and innovated. The object detection model uses Efficient Net-B1 as the backbone network and uses ASPP and improved? ?FPN as the neck network. By introducing a variety of model training skills,the model is optimized. The final result reduces the number of parameters by about 2. 3 times and improves the accuracy on different datasets. Object tracking uses the Deep Sort tracking algorithm to track and count multiple object categories. The semantic segmentation uses the Encoder-Decoder structure and Efficient Net-B4 as the backbone network,and referring to the U-Net+ +network,it uses the convolution layer as the feature extraction module and the deconvolution layer as the up sampling module,and obtains? the final output result by connecting the feature maps of different sizes. The improved semantic segmentation model is compared with the model combined with MobileNetV2 and DeeplabV3 network,and the number of parameters is reduced by about 1. 35 times. Experiments show that extracting robust features through deep learning algorithm can facilitate the detection and recognition in automatic driving and assisted driving scenes.

相似文献/References:

[1]刘晓明 李毓蕙 高燕 郑华强.基于目标区域清晰显示的H.264编码策略[J].计算机技术与发展,2010,(06):29.
　LIU Xiao-ming,LI Yu-hui,GAO Yan,et al.A Coding Strategy of H.264 Based on High-definition Display of Target Region[J].,2010,(07):29.
[2]刘翔 吴谨 祝愿博 康晓晶.基于视频序列的目标检测与跟踪技术研究[J].计算机技术与发展,2009,(11):179.
　LIU Xiang,WU Jin,ZHU Yuan-bo,et al.A Study of Object Detecting and Tracking Based on Video Sequences[J].,2009,(07):179.
[3]曙光 张超 蔡则苏.基于改进的混合高斯模型的目标检测方法[J].计算机技术与发展,2012,(07):60.
　SHU Guang,ZHANG Chao,CAI Ze-su.Target Detection Method Based on Improved Gaussian Mixture Model[J].,2012,(07):60.
[4]刘洁,李目,周少武.一种混沌混合粒子群优化RBF神经网络算法[J].计算机技术与发展,2013,(08):181.
　LIU Jie[],LI Mu[],ZHOU Shao-wu[].An Algorithm of Chaotic Hybrid Particle Swarm Optimization Based on RBF Neural Network[J].,2013,(07):181.
[5]蒋翠清,孙富亮,吴艿芯. 基于相对欧氏距离的背景差值法视频目标检测[J].计算机技术与发展,2015,25(01):37.
　JIANG Cui-qing,SUN Fu-liang,WU Nai-xin. Video Object Detection of Background Subtraction Method Based on Relative Euclidean Distance[J].,2015,25(07):37.
[6]卢官明,衣美佳. 步态识别关键技术研究[J].计算机技术与发展,2015,25(07):100.
　LU Guan-ming,YI Mei-jia. Research on Critical Techniques in Gait Recognition[J].,2015,25(07):100.
[7]高翔,朱婷婷,刘洋. 多摄像头系统的目标检测与跟踪方法研究[J].计算机技术与发展,2015,25(07):221.
　GAO Xiang,ZHU Ting-ting,LIU Yang. Research of Target Detection and Tracking Method for Multi-camera System[J].,2015,25(07):221.
[8]章文洁[][],黄旻[],张桂峰[]. 滤光片多光谱成像中运动目标场景误配准修正[J].计算机技术与发展,2016,26(01):18.
　ZHANG Wen-jie[][],HUANG Min[],ZHANG Gui-feng[]. Misregistration Correction for Moving Object Scene in Filter-type Multispectral Imaging[J].,2016,26(07):18.
[9]施泽浩,赵启军.基于全卷积网络的目标检测算法[J].计算机技术与发展,2018,28(05):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
　SHI Ze-hao,ZHAO Qi-jun.Object Detection Algorithm Based on Fully Convolutional Neural Network[J].,2018,28(07):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
[10]张夏清,茅耀斌. 一种改进的ViBe背景提取算法[J].计算机技术与发展,2016,26(07):36.
　ZHANG Xia-qing,MAO Yao-bin. An Improved ViBe Background Generation Method[J].,2016,26(07):36.
[11]曾碧卿,杨 睿,李一娴,等.基于卷积神经网络的零件圆检测方法[J].计算机技术与发展,2023,33(11):64.[doi:10. 3969 / j. issn. 1673-629X. 2023. 11. 010]
　ZENG Bi-qing,YANG Rui,LI Yi-xian,et al.Part Circle Detection Method Based on Convolutional Neural Network[J].,2023,33(07):64.[doi:10. 3969 / j. issn. 1673-629X. 2023. 11. 010]

更新日期/Last Update: 2022-07-10