|本期目录/Table of Contents|

[1]刘德儿,唐武,陈增辉,等.改进的SSD算法用于盲人户外出行多尺度障碍检测[J].江西理工大学学报,2021,42(01):87-97.[doi:10.13265/j.cnki.jxlgdxxb.2021.01.013]
 LIU Deer,TANG Wu,CHEN Zenghui,et al.Improved SSD in multi-scale obstacle detection for blind people traveling outdoors[J].Journal of Jiangxi University of Science and Technology,2021,42(01):87-97.[doi:10.13265/j.cnki.jxlgdxxb.2021.01.013]


点击复制
改进的SSD算法用于盲人户外出行多尺度障碍检测(/HTML)
分享到:

《江西理工大学学报》[ISSN:2095-3046/CN:36-1289/TF]

卷:
42卷
期数:
2021年01期
页码:
87-97
栏目:
出版日期:
2021-02-28

文章信息/Info

Title:
Improved SSD in multi-scale obstacle detection for blind people traveling outdoors
文章编号:
2095-3046(2021)01-0087-11
作者:
刘德儿1 唐武1 陈增辉1 赵尘2
(1. 江西理工大学土木与测绘工程学院,江西 赣州 341000; 2. 福建经纬测绘信息有限公司,福州 350000)
Author(s):
LIU De’er1 TANG Wu1 CHEN Zenghui1 ZHAO Chen2
(1. School of Civil and Surveying & Mapping Engineering, Jiangxi University of Science and Technology, Ganzhou 341000, Jiangxi, China; 2. Fujian JingWei Surveying and Mapping Information Co., Ltd., Fuzhou 350000, Fujian, China)
关键词:
SSD盲人计算机视觉障碍检测
分类号:
TP389.1;TP18
DOI:
10.13265/j.cnki.jxlgdxxb.2021.01.013
文献标志码:
A
摘要:
文章针对盲人户外出行的障碍物探测问题,利用深度学习的方法建立了障碍物数据集和检测模型。虽然传统的SSD方法在VOC数据集和COCO数据集上有着良好的泛化性能,但是对障碍物的检测效果并不好。因此对SSD的先验框比例参数和网络结构进行改进,将anchor比例设置成更加符合本数据集的尺度,并且通过增加Conv3_3特征层达到识别不同尺寸障碍物的要求。通过与现有检测算法和数据集进行实验对比,得出改进的SSD算法对建立的数据集中的特殊尺度的障碍物检测要优于其他算法。

参考文献/References:

[1] 罗会兰,易慧. 基于三流卷积神经网络模型的图像分类方法[J]. 江西理工大学学报,2019,40(5): 86-92.[2] MAKSAI A,FUA P. Eliminating exposure bias and metric mismatch in multiple object tracking[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),Long Beach,CA,USA.IEEE,2019:4634-4643.[3] DA K, LI T C, ZHU Y F, et al. A computationally efficient approach for distributed sensor localization and multitarget tracking[J]. IEEE Communications Letters, 2020, 24(2):335-338.[4] THERMOS S, PAPADOPOULOS G T, DARAS P, et al. Deep sensorimotor learning for RGB-D object recognition[J]. Computer Vision and Image Understanding, 2020, 190: 102844.[5] 张索非,冯烨,吴晓富. 基于深度卷积神经网络的目标检测算法进展[J]. 南京邮电大学学报(自然科学版),2019,39(5): 72-80.[6] ZHAO Z Q , ZHENG P , XU S T , et al. Object detection with deep learning: A review[J]. IEEE Transactions on Neural Networks and Learning Systems, 2019, 30(11):3212-3232. [7] ZOU Z, SHI Z, GUO Y, et al. Object detection in 20 years: A survey[J]. arXiv preprint arXiv:1905.05055, 2019.[8] PLIKYNAS D, ?觩VIRONAS A, BUDRIONIS A, et al. Indoor navigation systems for visually impaired persons:Mapping the features of existing technologies to user needs[J]. Sensors, 2020, 20(3):636.[9] 陈旻,刘德儿,林珲. 从地理信息系统角度探究盲人户外导航的几个关键问题[J]. 地球信息科学学报,2014,16(4): 553-559.[10] 廖文,徐进,高莹,等. 超声波测距导盲车关键技术的研究[J]. 计算机测量与控制,2017,25(6): 294-297.[11] SIDDHARTHA B, CHAVAN A P, UMA B V. An electronic smart jacket for the navigation of visually impaired society[J]. Materials Today: Proceedings, 2018, 5(4): 10665-10669.[12] YING J C, LI C Y, WU G W, et al. A deep learning approach to sensory navigation device for blind guidance[C]// 2018 IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS). IEEE, 2018:1195-1200.[13] SERR?魨O M, SHAHRABADI S, MORENO M, et al. Computer vision and GIS for the navigation of blind persons in buildings[J]. Universal Access in the Information Society, 2015, 14(1): 67-80.[14] AFIF M, AYACHI R, SAID Y, et al. An evaluation of RetinaNet on indoor object detection for blind and visually impaired persons assistance navigation[J]. Neural Processing Letters, 2020, 51(3):2265-2279.[15] OU S, PARK H, LEE J. Implementation of an obstacle recognition system for the blind[J]. Applied Sciences, 2019, 10(1):282.[16] AKTA A, DOAN B, DEMIR N. Tactile paving surface detection with deep learning methods[J]. Journal of the Faculty of Engineering and Architecture of Gazi University, 2020, 35(3):1685-1700.[17] GUERREIRO J,SATO D,AHMETOVIC D,et al. Virtual navigation for blind people:Transferring route knowledge to the real-World[J]. International Journal of Human-Computer Studies, 2020, 135:102369.[18] 朱文霖,刘华平,王博文,等. 基于视-触跨模态感知的智能导盲系统[J]. 智能系统学报,2020,15(1): 33-40.[19] 黄鸿志,黄诗铭,刘静,等. 智能盲人出行导航头盔[J]. 中国新通信,2020,22(1): 51.[20] 丁雯雯,康佳. 基于社会创新理论的盲人导航眼镜设计研究[J]. 南方农机,2019,50(23): 286.[21] 李诗芸. 基于可穿戴的智能盲人导航设计[J]. 工业设计,2018(3): 102-103.[22] 刘天金,杨雪. 基于单片机的智能盲人避障靴子[J]. 电子世界,2018(9): 16-18.[23] 刘德儿,李瑞雪,覃燕敏. 改进坡度的数学形态学非地面点云去除算法研究[J]. 江西理工大学学报,2019,40(5):43-48.[24] 邓壮来,汪盼,宋雪桦,等. 基于SSD的粮仓害虫检测研究[J]. 计算机工程与应用,2020,56(11):214-218.[25] 潘卫国,刘博,陈英昊,等. 基于YOLO v3的交通标志牌检测识别[J]. 传感器与微系统,2019,38(11):147-150.[26] 周慧娟,张强,刘羽,等. 基于YOLO2的地铁进站客流人脸检测方法[J]. 计算机与现代化,2019(10):76-82.[27] 钮赛赛,周华伟,朱婧文,等. 基于YOLO智能网络的红外弱小多目标检测技术[J]. 上海航天,2019,36(5):28-34.[28] GIRSHICK R. Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision (ICCV). December 7-13, 2015, Santiago, Chile. IEEE, 2015:1440-1448.[29] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6):1137-1149. [30] REDMON J, FARHADI A. YOLOv3:an incremental improvement[EB/OL]. 2018:arXiv:1804.02767[cs. CV]. https://arxiv. org/abs/1804.02767[31] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once:unified, real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). June 27-30, 2016, Las Vegas, NV, USA. IEEE, 2016:779-788.[32] 凌梓钦,徐昶悦,仇威,等. 基于YOLO算法的内河船舶检测与监控实现[J].航海,2019(5):72-75.[33] LIU W, ANGUELOV D, ERHAN D, et al. SSD:single shot MultiBox detector[M]//Computer Vision - ECCV 2016. Cham:Springer International Publishing, 2016:21-37.[34] 李兆洋,李柏林,罗建桥,等. 基于改进SSD模型的高铁扣件定位算法[J].铁道标准设计,2020,64(5):24-29.[35] 华夏,王新晴,王东,等. 基于改进SSD的交通大场景多目标检测[J].光学学报,2018,38(12):221-231.[36] LUO L,ZHANG P J,HU P J,et al.Research method of blind path recognition based on DCGAN[M].Advances in Intelligent Systems and Computing.Cham:Springer International Publishing,2020:90-99.[37] 赵文清,周震东,翟永杰. 基于反卷积和特征融合的SSD小目标检测算法[J]. 智能系统学报,2020,15(2): 310-316. [38] 陈凯,祖莉,欧屹. 基于YOLOv3与ResNet50的摄影机器人人脸识别跟踪系统[J]. 计算机与现代化,2020(4): 30-36,41.[39] 许兆鹏,武志东,王顺杰,等. 双线导鱼雷遥测信息辅助机动目标跟踪方法研究[J]. 兵器装备工程学报,2020,41(10): 188-191,227.[40] 李成跃,姚剑敏,林志贤,等. 基于改进YOLO轻量化网络的目标检测方法[J]. 激光与光电子学进展,2020,57(14):141003. [41] SETIADI B, SUPRIYADI T, NUGROHO H, et al. Navigation and object detection for blind persons based on neural network[J]. International Journal Applied Technology Research, 2020, 1(1): 56-65.[42] 陈幻杰,王琦琦,杨国威,等. 多尺度卷积特征融合的SSD目标检测算法[J]. 计算机科学与探索,2019,13(6): 1049-1061.[43] 郇战,陈学杰,梁久祯. 手机惯导与RFID的盲人导航系统设计与实现[J]. 智能系统学报,2019,14(3): 491-499.[44] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO:common objects in context[M]//Computer Vision - ECCV 2014. Cham:Springer International Publishing, 2014:740-755.[45] EVERINGHAM M, ESLAMI S M A, GOOL L, et al. The pascal visual object classes challenge:a retrospective[J]. International Journal of Computer Vision, 2015, 111(1):98-136. [46] GEIGER A, LENZ P, URTASUN R. Are we ready for autonomous driving The KITTI vision benchmark suite[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition. June 16-21, 2012, Providence, RI, USA. IEEE, 2012:3354-3361. [47] ZHOU Z G, LAN X S, LI S X, et al. Feature pyramid SSD:outdoor object detection algorithm for blind people[C]//2019 IEEE 5th International Conference on Computer and Communications (ICCC). December 6-9, 2019, Chengdu, China. IEEE, 2019:650-654.[48] ZHU Z, LIANG D, ZHANG S H, et al. Traffic-sign detection and classification in the wild[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA. IEEE, 2016:2110-2118.[49] TA T L. LabelImg[EB/OL](2017). https://github.com/tzutalin/labelImg.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期:2020-12-17
基金项目:国家自然科学基金资助项目(41361077,41561085);江西省自然科学基金资助项目(20202BAB202025)
作者简介:刘德儿(1976— ),男,博士,教授,主要从事GIS应用开发、激光点云、盲人导航及计算机视觉应用等方面的研究。E-mail: landserver@163.com

更新日期/Last Update: 1900-01-01