|本期目录/Table of Contents|

[1]娄翔飞,吕文涛,叶冬,等.基于计算机视觉的行人检测方法研究进展[J].浙江理工大学学报,2023,49-50(自科三):318-330.
 LOU Xiangfei,L  Wentao,YE Dong,et al.Research progress of pedestrian detection methods  based on computer vision[J].Journal of Zhejiang Sci-Tech University,2023,49-50(自科三):318-330.
点击复制

基于计算机视觉的行人检测方法研究进展()
分享到:

浙江理工大学学报[ISSN:1673-3851/CN:33-1338/TS]

卷:
第49-50卷
期数:
2023年自科第三期
页码:
318-330
栏目:
出版日期:
2023-05-31

文章信息/Info

Title:
Research progress of pedestrian detection methods  based on computer vision
文章编号:
1673-3851 (2023) 05-0318-13
作者:
娄翔飞吕文涛叶冬郭庆鲁竞陈影柔
1.浙江理工大学,a.信息科学与工程学院;b.浙江省智能织物与柔性互联重点实验室,杭州 310018;2.浙江移动信息系统集成有限公司,杭州 311217;3.浙江省技术创新服务中心,杭州 310007
Author(s):
LOU Xiangfei L  Wentao YE Dong GUO Qing LU Jing CHEN Yingrou
1a.School of Information Science and Engineering; 1b.Key Laboratory of Intelligent Textile and  Flexible Interconnection of Zhejiang Province, Zhejiang Sci-Tech University, Hangzhou 310018,  China; 2.Zhejiang Mobile Information System Integration Co., Ltd., Hangzhou 311217, China;  3.Zhejiang Technology Innovation Service Center, Hangzhou 310007, China
关键词:
计算机视觉行人检测图像分割特征提取机器学习分类与定位
分类号:
TP391-4;TP183
文献标志码:
A
摘要:
基于计算机视觉的行人检测方法可有效提高行人检测效率,已广泛应用于智慧城市、辅助驾驶等场景。文章对行人检测涉及的图像分割、特征提取、机器学习和分类与定位等方法进行了归纳,综述了各种方法的主要思想、适用性和局限性;同时介绍了行人检测算法的评价指标,对算法性能进行了分析;最后总结了行人检测方法的研究进展,并对未来的发展方向进行了展望。计算机视觉作为目标检测中的一项重要技术,在行人检测领域仍有待发展,算法结构改进、分类器优化、复杂场景下的行人检测等是未来的研究重点。

参考文献/References:

1 Zheng G, Chen Y B. A review on vision - based pedestrian detection C ]∥ 2012 IEEE Global High Tech Congress on Electronics. Shenzhen, China. IEEE, 2012: 49 - 54.

2Ahmed Z, Iniyavan R, Madhan M P. Enhanced vulnerable pedestrian detection using deep learningC]∥2019 International Conference on Communication and Signal Processing (ICCSP). Chennai, India. IEEE, 2019: 971-974.

3Song Y, Li M, Qiu X H, et al. Full-time infrared feature pedestrian detection based on CSP networkC]∥2020 International Conference on Intelligent Transportation, Big Data & Smart City (ICITBS). Vientiane, Laos. IEEE, 2020: 516-518.JP

4]雷诗谣. 改进的候选区域生成网络应用于半监督行人检测[D. 广州: 华南理工大学, 2019: 1-17.

5Renu Chebrolu K N, Kumar P N. Deep learning based pedestrian detection at all light conditionsC]∥2019 International Conference on Communication and Signal Processing (ICCSP). Chennai, India. IEEE, 2019: 838-842.

6Cao J L, Pang Y W, Xie J, et al. From handcrafted to deep features for pedestrian detection: a surveyJ. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(9): 4913-4934.

7Feng T T, Ge H Y. Pedestrian detection based on attention mechanism and feature enhancement with SSDC]∥2020 5th International Conference on Communication, Image and Signal Processing (CCISP). Chengdu, China. IEEE, 2020: 145-148.

8Li F, Li X Y, Liu Q, et al. Occlusion handling and multi-scale pedestrian detection based on deep learning: a reviewJ. IEEE Access, 2022, 10: 19937-19957.

9Cheng Y, Li B J. Image segmentation technology and its application in digital image processingC]∥2021 IEEE Asia-Pacific Conference on Image Processing, Electronics and Computers (IPEC). Dalian, China. IEEE, 2021: 1174-1177.

10Guo X Q, Yang C, Liu Y J, et al. Learn to threshold: ThresholdNet with confidence-guided manifold mixup for polyp segmentationJ. IEEE Transactions on Medical Imaging, 2021, 40(4): 1134-1146.

undefined

备注/Memo

备注/Memo:
收稿日期: 2022-11-18
网络出版日期:2023-03-01
基金项目: 国家自然科学基金项目(61601410);浙江省科技厅重点研发计划项目(2021C01047, 2022C01079);东北大学流程工业综合自动化国家重点实验室联合基金项目(2021-KF-21-03,2021-KF-21-06)
作者简介: 娄翔飞(1998-),男,浙江金华人,硕士研究生,主要从事机器学习、图像处理方面的研究
通信作者: 吕文涛,E-mail:alvinlwt@zstu.edu.cn
更新日期/Last Update: 2023-09-08