An Efficient Vehicle Model Recognition Method
An Efficient Vehicle Model Recognition Method
复制标题
一种高效的车型识别方法
DOI：
10.4304/jsw.8.8.1952-1959
复制
发表时间：
2013-01
期刊：
影响因子：
--
通讯作者：
Zhenbing Liu
中科院分区：
文献类型：
--
作者：
Lei Zhai;Huihua Yang;Zhenbing Liu
提出了一种基于自适应哈里斯角点检测器的高效车辆模型识别方法。首先，选取车辆散热器网格作为ROI，采用Harris角点检测方法检测角点作为车辆模型特征，解决不同车型之间或同一车型在不同环境下角点个数不一致的问题；其次，构造自适应阈值函数，控制替换固定阈值的角点个数，保证图像总能产生一定数量的强角点；第三，利用GPU/CPU异构计算模型，设计了一种加速车辆识别算法以满足实时性要求的并行方案，包括算法的并行化和过程的并行化。在Intel Core i5 2400和NVIDIA C2075平台上，对12种车型的1096张大卡车图像进行了实验，识别准确率达到99.5%，平均提速达到58倍。结果表明，该方法能够满足实际应用的要求。
An efficient vehicle model recognition method based on Adaptive Harris corner detector is presented in this paper. First, the vehicle radiator grid is selected as ROI and Harris corner detection is used to detect corner as vehicle model features, to solve a problem of inconsistencies in the number of corner between different models or the same model in different environment. Second, an adaptive threshold function is constructed to control the number of corner replacing a fixed threshold, ensuring that the image is always able to produce a certain number of strong corners. Third, a parallel scheme is designed to accelerate the vehicle recognition algorithm via GPU/CPU heterogeneous computing model to meet real-time requirement, which includes parallelization of algorithm and parallelization of process. The experiments on 1096 big truck images of 12 vehicle models obtain the recognition accuracy rate of 99.5%, and achieve 58x speedup on average by a platform with Intel Core i5 2400 and NVIDIA C2075. The results show that our proposed method can meet the requirements of practical application.
登录
查看更多内容
DOI：
10.4304/jsw.7.12.2695-2702
发表时间：
2012-01
期刊：
J. Softw.
影响因子：
--
作者：
Yechen Gui;Guijuan Zhang
通讯作者：
Yechen Gui;Guijuan Zhang
影响因子：
3.8
作者：
Che, Shuai;Boyer, Michael;Skadron, Kevin
通讯作者：
Skadron, Kevin
影响因子：
--
作者：
Jiang Peng
通讯作者：
Jiang Peng
DOI：
10.1109/icsmc.2004.1400967
发表时间：
2004-10
期刊：
2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583)
影响因子：
--
作者：
Hiroki Maemoto;Yoshikazu Okuma;S. Yano
通讯作者：
Hiroki Maemoto;Yoshikazu Okuma;S. Yano
DOI：
--
发表时间：
2011
期刊：
Computer Science
影响因子：
--
作者：
Zhang Lilun
通讯作者：
Zhang Lilun