计算机科学 ›› 2021, Vol. 48 ›› Issue (11): 219-225.doi: 10.11896/jsjkx.201100174
原晓佩, 陈小锋, 廉明
YUAN Xiao-pei, CHEN Xiao-feng, LIAN Ming
摘要: 针对目标检测时Haar-like特征值过多、计算时间长、无法描述目标纹理特征且识别率一般的问题,提出一种基于滑窗原点信息的阈值自调节IHL(Improved Haar-like LBP)特征提取算法。该算法首先构造了IHL特征编码方法,将Haar-like特征和局部二值LBP特征融合;然后在计算Haar-like型局部二值化特征时,使用高斯矩阵获得符合像素分布规律的自调节阈值;同时在求特征值时引入中心点像素信息,确保提取的特征值的合理性;最后使用AdaBoost训练得到级联分类器,将其载入系统,并在KITTI车辆数据集和INRIA Person行人数据集上进行实验测试。实验结果表明,该方法可在65 s内识别1 102个行人目标,在114.3 s内识别1 852个车辆目标,相比传统算法其可以明显加快目标识别的速度,对行人和车辆目标的识别率均可达到94%以上,其检测准确性相比其他方法也有显著提升。
中图分类号:
[1]QIN Y,JIA L M,ZHANG Y.Railway intelligent transportation system and its applications[J].Journal of China Engineering Science(English Edition),2011,9(1):53-59. [2]WANG T M,TAO Y,LIU H.Current Researches and Future Development Trend of Intelligent Robot:A Review[J].International Journal of Automation & Computing,2018,15(9):1-22. [3]SONG X S,DENG W,XIA Y Y.Theory Model Based on Transformation Mechanisms and Solute ransportation of Nitrogen in Subflow Constructed Wetlands[J].Advances in Earth Science,2007,22(10):1041-1047. [4]ZHAN L Y.Traffic monitoring system based on CMMI configuration management application study[J].China's Public Security Comprehensive,2019(9):86-89. [5]YAMATO T P,POMPEU J E,POMPEU S M,et al.VirtualReality for Stroke Rehabilitation[J].Physical Therapy,2016(10):10. [6]WAN Y,HAN Y,LU H Q.Discussion on moving target detection algorithm[J].Computer Simulation,2006,23(10):221-226. [7]WANG H Z,SUTER D.A Novel Robust Statistical Method forBackground Initialization and Visual Surveillance[C]//7th Asian Conference on Computer Vision(ACCV 2006).2006:328-337. [8]COLOMBARI A,FUSIELLO A.Patch-Based Background Ini-tialization in Heavily Cluttered Video[J].IEEE Transactions on Image Processing,2010,19(4):926-933. [9]QU J J,XIN Y H.Moving target detection method based on the fusion of continuous frame difference and background difference[J].Acta Photonica Sinica,2014,43(7):213-220. [10]YU Y,CAO M W,YUE F.EVibe:an improved Vibe movingtarget detection algorithm[J].Chinese Journal of Scientific Instrument,2014(4):206-213. [11]PAUL V,MICHAEL J.Rapid Object Detection using a Boosted Cascade of Simple Features[C]//2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR'01).2001:511-518. [12]OJALA T,PIETIKAINEN M,MAENPAA T.A GeneralizedLocal Binary Pattern Operator for Mul-tiresolution Gray Scale and Rotation Invariant Texture Classification[C]//Advances in Pattern Recognition-ICAPR 2001.2001:397-406. [13]DALAL N,TRIGGS B.Histograms of oriented gradients forhuman detection[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2005:886-893. [14]FELZENSZWALB P F,GIRSHICK R B,MCALLESTER D,et al.Object Detection with Discriminatively Trained Part-Based Models[J].IEEE Transactions on Software Engineering,2010,32(9):1627-1645. [15]ZHOU S R,YIN J P.LBP texture features based on Haar cha-racteristics[J].Journal of Software,2013(8):1909-1926. [16]CUI K,CAI H,CHEN G Q,et al.Multi-view face detection algorithm based on multi-texture CS-LBP features[J].Journal of Jilin University(Science Edition),2018,56(3):610-616. [17]DONG T Y,RUAN T H,WU J M,et al.Research on a traffic video vehicle recognition method combining Haar-like and HOG features[J].Journal of Zhejiang University of Technology,2015,43(5):503-507. [18]VIOLA P,JONES M J.Robust Real-Time Face Detection[J].International Journal of Computer Vision,2004,57(2):137-154. [19]JAE-DO K,SANG-HEE K,YOUNG-JOON H,et al.Night Vehicle Detection Using Variable Haar-Like Feature[J].Test Science and Instrument,2011,2(4):337-340. [20]LEE K,JEONG T,WOO S,et al.Octagonal prism LBP representation for face recognition[J].Multimedia tools and applications,2018,77(16):21751-21770. [21]CHEN X N.Research on Lighting Arrester Recognition andTracking Algorithm base on computer vision [D].Guangzhou:Guangdong University of Technology,2016. [22]HAN S,XI S Q,GENG W D.Low-resolution expression recognition based on central oblique average CS-LBP with adaptive threshold[J].Optoelectronic Express(English Edition),2017,13(6):444-447. [23]WAN Y,LI H H,WU K F,et al.Face recognition based on la-yered feature fusion of LBP and HOG[J].Journal of Computer Aided Design and Graphics,2015(4):640-650. |
[1] | 刘冬梅, 徐洋, 吴泽彬, 刘倩, 宋斌, 韦志辉. 基于边框距离度量的增量目标检测方法 Incremental Object Detection Method Based on Border Distance Measurement 计算机科学, 2022, 49(8): 136-142. https://doi.org/10.11896/jsjkx.220100132 |
[2] | 王灿, 刘永坚, 解庆, 马艳春. 基于软标签和样本权重优化的Anchor Free目标检测算法 Anchor Free Object Detection Algorithm Based on Soft Label and Sample Weight Optimization 计算机科学, 2022, 49(8): 157-164. https://doi.org/10.11896/jsjkx.210600240 |
[3] | 张源, 康乐, 宫朝辉, 张志鸿. 基于Bi-LSTM的期货市场关联交易行为检测方法 Related Transaction Behavior Detection in Futures Market Based on Bi-LSTM 计算机科学, 2022, 49(7): 31-39. https://doi.org/10.11896/jsjkx.210400304 |
[4] | 曾志贤, 曹建军, 翁年凤, 蒋国权, 徐滨. 基于注意力机制的细粒度语义关联视频-文本跨模态实体分辨 Fine-grained Semantic Association Video-Text Cross-modal Entity Resolution Based on Attention Mechanism 计算机科学, 2022, 49(7): 106-112. https://doi.org/10.11896/jsjkx.210500224 |
[5] | 程成, 降爱莲. 基于多路径特征提取的实时语义分割方法 Real-time Semantic Segmentation Method Based on Multi-path Feature Extraction 计算机科学, 2022, 49(7): 120-126. https://doi.org/10.11896/jsjkx.210500157 |
[6] | 郁舒昊, 周辉, 叶春杨, 王太正. SDFA:基于多特征融合的船舶轨迹聚类方法研究 SDFA:Study on Ship Trajectory Clustering Method Based on Multi-feature Fusion 计算机科学, 2022, 49(6A): 256-260. https://doi.org/10.11896/jsjkx.211100253 |
[7] | 刘伟业, 鲁慧民, 李玉鹏, 马宁. 指静脉识别技术研究综述 Survey on Finger Vein Recognition Research 计算机科学, 2022, 49(6A): 1-11. https://doi.org/10.11896/jsjkx.210400056 |
[8] | 祝文韬, 兰先超, 罗唤霖, 岳彬, 汪洋. 改进Faster R-CNN的光学遥感飞机目标检测 Remote Sensing Aircraft Target Detection Based on Improved Faster R-CNN 计算机科学, 2022, 49(6A): 378-383. https://doi.org/10.11896/jsjkx.210300121 |
[9] | 马宾, 付永康, 王春鹏, 李健, 王玉立. 基于GDIoU损失函数的YOLOv4绝缘子高效定位算法 High Performance Insulators Location Scheme Based on YOLOv4 with GDIoU Loss Function 计算机科学, 2022, 49(6A): 412-417. https://doi.org/10.11896/jsjkx.210600089 |
[10] | 陈永平, 朱建清, 谢懿, 吴含笑, 曾焕强. 基于外接圆半径差损失的实时安全帽检测算法 Real-time Helmet Detection Algorithm Based on Circumcircle Radius Difference Loss 计算机科学, 2022, 49(6A): 424-428. https://doi.org/10.11896/jsjkx.220100252 |
[11] | 陈佳舟, 赵熠波, 徐阳辉, 马骥, 金灵枫, 秦绪佳. 三维城市场景中的小物体检测 Small Object Detection in 3D Urban Scenes 计算机科学, 2022, 49(6): 238-244. https://doi.org/10.11896/jsjkx.210400174 |
[12] | 胡伏原, 万新军, 沈鸣飞, 徐江浪, 姚睿, 陶重犇. 深度卷积神经网络图像实例分割方法研究进展 Survey Progress on Image Instance Segmentation Methods of Deep Convolutional Neural Network 计算机科学, 2022, 49(5): 10-24. https://doi.org/10.11896/jsjkx.210200038 |
[13] | 高元浩, 罗晓清, 张战成. 基于特征分离的红外与可见光图像融合算法 Infrared and Visible Image Fusion Based on Feature Separation 计算机科学, 2022, 49(5): 58-63. https://doi.org/10.11896/jsjkx.210200148 |
[14] | 李鹏祖, 李瑶, Ibegbu Nnamdi JULIAN, 孙超, 郭浩, 陈俊杰. 基于多特征融合的重叠组套索脑功能超网络构建及分类 Construction and Classification of Brain Function Hypernetwork Based on Overlapping Group Lasso with Multi-feature Fusion 计算机科学, 2022, 49(5): 206-211. https://doi.org/10.11896/jsjkx.210300049 |
[15] | 徐涛, 陈奕仁, 吕宗磊. 基于改进YOLOv3的机坪工作人员反光背心检测研究 Study on Reflective Vest Detection for Apron Workers Based on Improved YOLOv3 Algorithm 计算机科学, 2022, 49(4): 239-246. https://doi.org/10.11896/jsjkx.210200119 |
|