摘要
为了使探测到的各种地雷图像更清晰,要求将金属地雷探测器和雷达渗透地面探测器的图像用图像精确配准的方法将二者的图像融合.提出了基于竞争学习和支持向量机的图像配准方法.该方法是用竞争学习的权值标明地雷边缘点,以获得图像中地雷的特征值;然后用支持向量机反复匹配两个待配准图像的支持向量.融合图像信息熵的测定结果表明,基于竞争学习和支持向量机的图像配准方法融合图像携带的信息量大,融合图像质量高,图像配准精确.
Landmine image registration approach by metal sensor and ground penetrating radar （GPR） sensor is presented. An approach which is based on competition learning and support vector machine （SVM） is put forward. Firstly, this approach describes the feature of landmine image by the weights of competition learning in order to decrease the vector numbers of being processed and pay attention to the interesting region. Then it puts the weights into SVM as training vectors to obtain the support vectors in a cycle way. The efficiency of this approach is demonstrated by applying this method to three groups of registration and fusion of metal sensor image and GPR sensor images. The results show that this approach is feasible and would be the base for further image processing of landmine.
出处
《哈尔滨工业大学学报》
EI
CAS
CSCD
北大核心
2007年第7期1114-1116,共3页
Journal of Harbin Institute of Technology
基金
国家自然科学基金资助项目(60671011)
黑龙江省杰出青年科学基金资助项目(JC200611)
哈尔滨工业大学校基金资助项目(HIT.2003.53)
黑龙江省自然科学基金资助项目(留学回国基金)(LC06C08)
黑龙江省博士后基金资助项目(01105238)
哈尔滨海外学人研究基金资助项目(1151hq008)
