Urban Traffic Object Detection Based on Multi-Stage Proposal Sparse R-CNN

LIU Chang-yuan; ZHANG Yu-liang; BI Xiao-jun

doi:10.12263/DZXB.20211648

您当前的位置：

首页 >

文章列表页 >

Urban Traffic Object Detection Based on Multi-Stage Proposal Sparse R-CNN

PAPERS | 更新时间：2025-07-02

- Urban Traffic Object Detection Based on Multi-Stage Proposal Sparse R-CNN
- ACTA ELECTRONICA SINICA Vol. 51, Issue 1, Pages: 26-31(2023)
- 作者机构：
  
  1.哈尔滨理工大学测控技术与通信工程学院，黑龙江哈尔滨 150080
  2.中央民族大学信息工程学院，北京 100081
- 作者简介：
- 基金信息：
  
  Natural Science Foundation of Heilongjiang Province(F2016022)
- DOI：10.12263/DZXB.20211648
  CLC： TP391.4;TP181
- Received：12 December 2021，
  
  Revised：2022-07-01，
  
  Published：25 January 2023
- 稿件说明：
移动端阅览
柳长源,张玉亮,毕晓君.基于多阶段提议稀疏区域卷积网络的城市交通目标检测[J].电子学报,2023,51(01):26-31.

LIU Chang-yuan,ZHANG Yu-liang,BI Xiao-jun.Urban Traffic Object Detection Based on Multi-Stage Proposal Sparse R-CNN[J].ACTA ELECTRONICA SINICA,2023,51(01):26-31.
柳长源,张玉亮,毕晓君.基于多阶段提议稀疏区域卷积网络的城市交通目标检测[J].电子学报,2023,51(01):26-31. DOI： 10.12263/DZXB.20211648.

LIU Chang-yuan,ZHANG Yu-liang,BI Xiao-jun.Urban Traffic Object Detection Based on Multi-Stage Proposal Sparse R-CNN[J].ACTA ELECTRONICA SINICA,2023,51(01):26-31. DOI： 10.12263/DZXB.20211648.

摘要

针对城市交通场景多目标检测算法检测速度慢，检测精度低等问题，本文提出多阶段提议稀疏区域卷积网络算法（Multi-stage Proposal Sparse Region-based Convolutional Neural Network，MPS R-CNN）.算法主要有以下特点：提出了一种多阶段提议框过滤更新机制，提高算法检测精度；提出了一种双向并联特征金字塔网络（Bidirectional Parallel Feature Pyramid Network，BPFPN），增强了模型的特征融合能力；针对城市交通场景目标检测问题引入了Copy-Paste数据增强方法和CIoU损失函数.实验结果显示，MPS R-CNN算法在Urban Object Dataset数据集上mAP达到了77%，算法检测速度保持在37fps，优于目前其他城市交通场景目标检测算法.

Abstract

Aiming at the slow speed and low accuracy of multi-object detection algorithms in urban traffic scenes

this paper proposes a multi-stage proposal sparse region-based convolutional neural network algorithm (MPS R-CNN). The algorithm mainly has the following characteristics: a multi-stage proposal box filtering update mechanism is proposed to improve the detection accuracy of the algorithm; a bidirectional parallel feature pyramid network (BPFPN) is proposed to enhance the model feature fusion capability; for the problem of object detection in urban traffic scenes

the Copy-Paste data augmentation method and CIoU loss function are introduced. The experimental results show that the MPS R-CNN algorithm achieves 77% mAP on the urban object dataset

and the algorithm detection speed remains at 37 fps

which is better than other current urban traffic object detection algorithms.

关键词

Keywords

references

LOWE D G . Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision , 2004 , 60 ( 2 ): 91 - 110 .

GIRSHICK R , DONAHUE J , DARRELL T , et al . Rich feature hierarchies for accurate object detection and semantic segmentation [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2014 : 580 - 587 .

REDMON J , FARHADI A . YOLO9000: Better, faster, stronger [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2017 : 7263 - 7271 .

李宝奇 , 贺昱曜 , 强伟 , 何灵蛟 . 基于并行附加特征提取网络的SSD地面小目标检测模型 [J]. 电子学报 , 2020 , 48 ( 1 ): 84 - 91 .

LI Baoqi , HE Yuyao , QIANG Wei , HE Lingjiao . SSD small target detection model based on parallel additional feature extraction network [J]. Acta Electronica Sinica , 2020 , 48 ( 1 ): 84 - 91 . (in Chinese)

HE K , GKIOXARI G , DOLLÁR P , et al . Mask r-cnn [C]// Proceedings of the IEEE International Conference on Computer Vision . Piscataway : IEEE , 2017 : 2961 - 2969 .

LIN T Y , GOYAL P , GIRSHICK R , et al . Focal loss for dense object detection [C]// Proceedings of the IEEE International Conference on Computer Vision . Piscataway : IEEE , 2017 : 2980 - 2988 .

SUN P , ZHANG R , JIANG Y , et al . Sparse r-cnn: End-to-end object detection with learnable proposals [C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2021 : 14454 - 14463 .

HE K , ZHANG X , REN S , et al . Deep residual learning for image recognition [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2016 : 770 - 778 .

LIN T Y , DOLLÁR P , GIRSHICK R , et al . Feature pyramid networks for object detection [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2017 : 2117 - 2125 .

侯庆山 , 邢进生 . 基于Grad-CAM与KL损失的SSD目标检测算法 [J]. 电子学报 , 2020 , 48 ( 12 ): 2409 - 2416 .

HOU Qingshan , XING Jinsheng . SSD target detection algorithm based on Grad-CAM and KL loss [J]. Acta Electronica Sinica , 2020 , 48 ( 12 ): 2409 - 2416 . (in Chinese)

GHIASI G , CUI Y , SRINIVAS A , et al . Simple copy-paste is a strong data augmentation method for instance segmentation [C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2021 : 2918 - 2928 .

ZHENG Z , WANG P , REN D , et al . Enhancing geometric factors in model learning and inference for object detection and instance segmentation [J]. IEEE Transactions on Cybernetics , 2021 , 62 ( 01 ): 1 - 13 .

LIU S , QI L , QIN H , et al . Path aggregation network for instance segmentation [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 8759 - 8768 .

DOMINGUEZ-SANCHEZ A , CAZORLA M , ORTS-ESCOLANO S . A new dataset and performance evaluation of a region-based cnn for urban object detection [J]. Electronics , 2018 , 7 ( 11 ): 301 .

GLENN J . ultralytics/yolov5 [EB/OL]. ( 2021-07-08 )[ 2021-07-08 ]. https://github.com/ultralytics/yolov5 https://github.com/ultralytics/yolov5 .

TAN M , PANG R , LE Q V . Efficientdet: Scalable and efficient object detection [C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2020 : 10781 - 10790 .

PSALTIS A , DIMOU A , ALVAREZ F , et al . Flow R-CNN: Flow-enhanced object detection [C]// ICPR International Workshops and Challenges . Berlin : Springer , 2021 : 685 - 700 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

AI-DETR: Interpretable Object Detection Method Based on Adaptive Weighting

Open World Object Detection Based on Causal Prompt Distillation

Low Illumination Image Object Detection Method Based on ICFIE-YOLO

A Guided Diffusion-based Approach to Natural Adversarial Patch Generation

A Low-Light Object Detection Method Based on SAM-MSFF Network

Related Author

LU Yin-yuan

XU Sheng-quan

XIE Juan-ying

ZHAO Jia-qi

WANG Ping-an

ZHOU Yong

DU Wen-liang

YAO Rui

Related Institution

School of Computer Science, Shaanxi Normal University

Collegel of Life Sciences, Shaanxi Normal University

School of Computer Science and Technology, China University of Mining and Technology

Mine Digitization Engineering Research Center of the Ministry of Education

Guangxi Key Laboratory of Image and Graphic Intelligent Processing, Guilin University of Electronic Technology

⁰