欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
提出了一种复杂背景下红外图像序列中圆形目标提取、判别以及跟踪的系统框架。在目标提取阶段,采用支持向量回归的方法选择种子点,用自适应选择阈值区域的生长方法进行分割提取目标。对于目标判别,采用最多共圆像素点数除以总像素点数作为圆形程度的度量进行圆形判别,并提出改进的标准Hough变换来找到共圆点。跟踪算法中,应用了粒子滤波的跟踪方法,并针对红外目标的特点,建立实现粒子滤波算法的细节。实验证明了整个框架体系的有效性和稳健性。
英文摘要：
One whole framework,consists of object extraction,justification and tracking in infrared cluttered image sequence,is proposed.To extract objects,support vector regression is exploited to find seeds,and an adaptive threshold function is established.Then,to justify the roundness,the criterion is set as the value of number of the largest amount pixels localized in the same circle divided by the total number of pixels,which is implemented through an improved Hough transform presented in this paper.The particle filter method is exploited to track objects,the details are implemented according to the characteristics of infrared images.At last,the experiments result shows the effectiveness and robustness of the proposed framework.
同期刊论文项目
同项目期刊论文
Multi-information incorporation approach to kernel-based infrared target model construction with app
Multi-feature based Ensemble Classification and Regression Tree (ECART) for target tracking in infra
Automatically detect and track infrared small targets with kernel Fukunaga-Koontz transform and Kalm
Automatic extraction of infrared small target based on support vector regression and adaptive region
Infrared target tracking with kernel-based performance metric and eigenvalue-based similarity measur
Integrating affinity propagation clustering method with linear discriminant analysis for face recogn
期刊信息
位置：