基于机器视觉的驾驶员视野盲区安全预警方法研究

doi:10.11896/jsjkx.220700141

计算机科学 ›› 2023, Vol. 50 ›› Issue (6A): 220700141-7.doi: 10.11896/jsjkx.220700141

• 图像处理&多媒体技术 • 上一篇下一篇

基于机器视觉的驾驶员视野盲区安全预警方法研究

王巍¹, 白龙², 马欢畅¹, 刘衍珩³

1 长春财经学院信息工程学院长春 130122;
2 北京三快在线科技有限公司北京 100000;
3 吉林大学计算机科学与技术学院长春 130012

出版日期:2023-06-10 发布日期:2023-06-12
通讯作者: 刘衍珩(yhliu@jlu.edu.cn)
作者简介:(wangw262@ccufe.edu.cn)
基金资助:
国家自然科学基金面上项目(61872158);吉林省科技发展计划(重点研发)项目(20210201072GX)

Study on Safety Warning Method of Driver’s Blind Area Based on Machine Vision

WANG Wei¹, BAI Long², MA Huanchang¹, LIU Yanheng³

1 School of Information Engineering,Changchun University of Finance and Economics,Changchun 130122,China;
2 Beijing Sankuai Online Technology Co.,Ltd.,Beijing 100000,China;
3 College of Computer Science and Technology,Jilin University,Changchun 130012,China

Online:2023-06-10 Published:2023-06-12
About author:WANG Wei,born in 1981,master.Her main research interests include network communication and mobile network application. LIU Yanheng,born in 1958,Ph.D,profes-sor,postgraduate supervisor,is a member of China Computer Federation.His main research interests include network communication and security,mobile computing network theory and application,mobile IP technology and QoS mechanism.
Supported by:
National Natural Science Foundation of China(61872158) and Jilin Provincial Science and Technology Development Plan Project(20210201072GX).

摘要/Abstract

摘要： 为降低驾驶员在行驶过程中对汽车左前方、右前方盲区及周边观察判断的精力消耗和安全预警成本,研究驾驶员盲区行人安全自动检测及测距相关算法和技术,提出一种基于机器视觉的驾驶员盲区安全预警方法。首先,基于驾驶员实际驾驶视角考虑,通过对图像行人识别特征的研究,设计多特征融合盲区行人安全检测方法,获取融合方案特征直方图进行行人检测的正负分类,引入GPU加速提高数据共享交易的处理效率;其次,基于插值测量法及单目测距原理进行实验室测距,对部分像素点进行标定并结合实际场景对不同位置点进行标定,提升固定角度场景下的测量准确性及计算速度,优化车载视频场景下的单目摄像头测距方法;最后,对汽车左右两侧行人进行自动识别测距,根据驾驶员的反应时间和汽车刹车距离计算最优提醒距离并适当对驾驶员进行提醒,减少事故发生的概率。实验结果表明,该方案能够有效识别行人并测距,保证对驾驶员的实时提醒,具有较低的经济成本和良好的实用性。

关键词: 盲区预警, 机器视觉, 行人检测, 特征融合, 测距

Abstract: In order to reduce the energy consumption and safety warning cost of the driver’s observation and judgment of the left front,right front blind area and the surrounding during driving,this paper studies algorithms and technologies related to pedes-trian safety automatic detection and ranging in the driver’s blind area,and proposes a driver’s blind area safety warning scheme based on machine vision.Firstly,based on the driver’s actual driving perspective,through the study on the image pedestrian recognition features,the multifeature fusion blind area pedestrian satety detection method is designed,the feature histogram of the fusion scheme is obtained for the positive and negative classification of automatic pedestrian detection,and GPU is introduced to accelerate the processing efficiency of data sharing transactions.Secondly,based on the interpolation measurement method and monocular ranging principle,the laboratory ranging is carried out,some pixels are calibrated and different location points are calibrated in combination with the actual scene,so as to improve the measurement accuracy and calculation speed under the fixed angle scene,and optimize the monocular camera ranging method under the vehicle video scene.the pedestrians on the left and right sides of the car are automatically identified and ranging,and the optimal reminder distance is calculated according to the driver’s reaction time and the braking distance of the car,and the driver is reminded appropriately to reduce the probability of accidents.Experimental results show that the scheme can effectively identify pedestrians and measure the distance,ensure the real-time reminder to drivers,and has low economic cost and good practicability.

Key words: Blind area warning, Machine vision, Pedestrian detection, Feature fusion, Ranging

中图分类号:

TP309

王巍, 白龙, 马欢畅, 刘衍珩. 基于机器视觉的驾驶员视野盲区安全预警方法研究[J]. 计算机科学, 2023, 50(6A): 220700141-7. https://doi.org/10.11896/jsjkx.220700141

WANG Wei, BAI Long, MA Huanchang, LIU Yanheng. Study on Safety Warning Method of Driver’s Blind Area Based on Machine Vision[J]. Computer Science, 2023, 50(6A): 220700141-7. https://doi.org/10.11896/jsjkx.220700141

参考文献

[1]CHEN J W,SHI Z C,LIU J,et al.Research on early warning algorithm of driving safety about road traffic[J].Electronic Mea-surement Technology,2019,42(5):6-10.
[2]WAN M,WU Q,YAN L X,et al.A Review of Current Situation and Hot Spots of Road Safety Research[J].Journal of Transport Information and Safety,2022,40(2):11-21.
[3]MA Y,FU R.Research and Development of Drivers Visual Behavior and Driving Safety[J].China Journal of Highway and Transport,2015,28(6):82-94.
[4]SHAN X K,ZHANG B L.A fast pedestrian detection methodusing two-level random forest classifier[J].Optical Technique,2020,46(6):741-749.
[5]ZOU Z Y,GAI S Y,DA F P,et al.Occluded Pedestrian Detection Algorithm Based on Attention Mechanism[J].Acta Optica Sinica,2021,41(15):157-165.
[6]LAN L R,LUO W T,QIN Y,et al.Roadside pedestrian detection and location based on binocular machine vision and RetinaNet[J].Journal of Image and Graphics,2021,26(12):2941-2952.
[7]LI M Y,HE J L,CHEN Y,et al.Research on the detection algorithm of obscured pedestrain targets in infrared traffic scenes[J].Laser & Infrared,2022,52(9):1417-1424
[8]BAI Z H,LI Z Q,JIANG B H,et al.Real-time Pedestrian Detection in Advanced Driver Assistance Systems Based on Improved YOLOv2 Model[J].Automotive Engineering,2019,41(12):1416-1423.
[9]HUANG T Y,YANG X J,XIANG G H,et al.Study on Small Target Pedestrian Detection and Ranging Based on Monocular Vision[J].Computer Science,2020,47(11):205-211.
[10]CHEN Y,LIU X,LIU H L.Occluded Pedestrian DetectionBased on Joint Attention Mechanism of Channel-wise and Spatial Information[J].Journal of Electronics & Information Technology,2020,42(6):1486-1493.
[11]WANG L,WANG S,ZHANG G F,et al.Pedestrian Detection Based on Semantic Segmentation Attention and Visible Region Prediction[J].Journal of Northeastern University(Natural Science),2021,42(9):1261-1267.
[12]ZHAO W Z,LIU Q G,LV Y S,et al.Texture Variation Adap-tive Image Denoising With Nonlocal PCA.[J].IEEE Transactions on Image Processing:a Publication of the IEEE Signal Processing Society,2019,28(11):5537-5551.
[13]HAN H.A tensor voting based fractional-order image denoising model and its numerical algorithm[J].Applied Numerical Mathe-matics,2019,145(Nov.):133-144.
[14]HE G X,YIN R J,GAO J Q.An efficient sparse approximate inverse preconditioning algorithm on GPU[J].Concurrency and Computation:Practice and Experience,2020,32(7):e5598.1-e5598.13.
[15]NANDAL P,SHARMA R P.Numerical simulation on GPUs with CUDA to study nonlinear dynamics of whistler wave and its turbulent spectrum in radiation belts[J].Computer Physics Communications,2020,254:107214.
[16]DING Z,LU W Z.Moving Target Detection Algorithm Based on Vibe Background Modeling[J].Computer Systems & Applications,2019,28(4):183-187.
[17]LIANG FD,TANG S,ZHANG Y D,et al.Pedestrian detection based on sparse coding and transfer learning[J].Machine Vision and Applications,2014,25(7):1697-1709.
[18]LUO Q,GAI J H,ZHENG H Y.Small-scale Pedestrian Detection Based on Multi-scale Feature Fusion[J].Computer Engineering & Software,2019,40(12):100 -105.
[19]HU S X,CHANG Y C,YANG J,et al.Multi-Target Tracking Algorithm for Highway Vehicles Based on Multi-Feature Fusion[J].Automobile Technology,2020(9):8-13.
[20]MURTHY C B,HASHMI M F,KESKARA G.Optimized MobileNet + SSD:a real-time pedestrian detection on a low-end edge device[J].International Journal of Multimedia Information Retrieval,2021(8):1-14.
[21]ElSALAMOY H Y.Detection of anaemia disease in human red blood cells using cell signature,neural networks and SVM[J].Multimedia Tools and Applications,2018,77(12):15047-15074.
[22]KONG X B,MENG Z L,NOJIRI N,et al.A HOG-SVM Based Fall Detection IoT System for Elderly Persons Using Deep Sensor[J].Procedia Computer Science,2019,147:276-282.
[23]UMAIR D,CHRIS L,DHWANI S.Predicting driver reactiontime and deceleration:Comparison of perception-reaction thresholds and evidence accumulation framework[J].Accident Analysis & Prevention,2021,149:105889.
[24]YUAN S L,GUO Z.A warning model for vehicle collision on account of the reaction time of the driver[J].Journal of Safety and Environment,2021,21(1):270-276.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于机器视觉的驾驶员视野盲区安全预警方法研究

Study on Safety Warning Method of Driver’s Blind Area Based on Machine Vision

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

Metrics

本文评价

推荐阅读 0