摘要
针对尺度不变特征变换(Scale Invariant Feature Transform,SIFT)算法在航拍场景分类中提取特征时,易造成边界模糊和细节丢失且无法描述颜色信息的问题,结合视觉词袋模型,提出了非线性尺度空间下融合颜色特征的新型颜色风式特征检测子(Color-KAZE,C-KAZE).通过KAZE构造非线性尺度空间来检测特征信息;对颜色模型(Hue,Saturation,Value,HSV)非等间隔量化获取颜色量化矩阵,进而生成C-KAZE特征描述子;利用视觉词袋和空间金字塔匹配模型融合多特征.实验表明,该算法相比SIFT算法在场景分类准确率方面提高了约8%.C-KAZE描述子增强了KAZE的特征描述能力,突破了SIFT算法特征描述单一、边缘细节模糊的局限性,显著提升了无人机航拍图像的分类效果.
In aerial scene classification, scale invariant feature transform (SIFT) uses linear Gaussian decomposition to extract feature points. The algorithm has many problems, such as fuzzy boundary and loss of detail. Besides, the SIFT cannot describe the color information. Combined with bag-of-visual-words (BoVW) model, C-KAZE (color-KAZE) descriptor which fuses color feature in nonlinear scale space is proposed to solve these problems. KAZE is used to detect the characteristic information by constructing nonlinear scale space. Color quantization matrix is calculated by non-interval quantization in the HSV (hue, saturation, value) space, and the C-KAZE feature descriptor is generated by the quantization matrix. Finally, high-level semantic features and spatial layout information are extracted and fused. Experi- mental results show that the average classification accuracy of the proposed algorithm, compared to the classification algorithm based on SIFT, is improved by about 8%. The proposed algorithm improves the feature description ability of KAZE, and breaks the limitation of the SIFT classification algorithm. Besides, for the unmanned aerial vehicle (UAV) scene image, the accuracy can be greatly improved.
作者
陈苏婷
王卓
王奇
CHEN Suting WANG Zhuo WANG Qi(Jiangsu Key Laboratory of Meteorological Observation and Information Processing, Nanjing University of Information Science and Technology, Nanjing 210044, China)
出处
《上海交通大学学报》
EI
CAS
CSCD
北大核心
2017年第10期1228-1234,共7页
Journal of Shanghai Jiaotong University
基金
国家自然科学基金(61302188)
中国博士后特别资助基金(2012T50510
2011M500940)
六大人才高峰项目(2013-DZXX-020)
江苏省高校重大自然科学基金项目(12KJA510001)资助