| 摘要: |
| 针对红外小目标在复杂背景下难以检测的问题，提出了一种利用局部强度和梯度融合来增强目标抑制背景杂波的算法。首先通过双边滤波技术得到去噪图像，然后利用目标区域与局部邻域的强度差异和梯度向量获得融合图像，最后采用自适应阈值分隔技术成功检测出小目标。理论分析和实验评估结果表明，该算法能够很好地抑制高斯噪声和背景边缘，相比于传统的检测算法，其检测性能显著提高，鲁棒性能较好。 |
| 关键词: 红外图像 小目标检测 双边滤波 局部强度 局部梯度 图像融合 |
| DOI： |
|
| 基金项目:国家自然科学基金资助项目（61563049） |
|
| Small Target Detection of Local Intensity and Gradient Fusion under Bilateral Filtering |
| ZHANG Guofeng,Askar Hamdulla |
| (1.College of Information Science and Engineering,Xinjiang University,Urumqi 830046,China;
2.School of Mechanic and Electronic，Changji Vocational and Technical College,Changji 831100,China) |
| Abstract: |
| For the problem that it is difficult to detect the infrared small targets in complex background,an algorithm using local intensity and gradient fusion to enhance targets and suppress background clutter is proposed.Firstly,a denoising image is obtained by bilateral filtering technology.Then,a fused image is derived by using the intensity difference and gradient vector between the target region and local neighborhood.Finally,small targets are detected successfully by adaptive threshold separation technique.Theoretical analysis and experimental evaluation results show that this algorithm can effectively suppress Gaussian noise and background edge.Compared with that of the traditional detection algorithms,the detection performance of the proposed method is significantly improved and the robustness is better. |
| Key words: infrared image small target detection bilateral filtering local intensity local gradient image fusion |
《电讯技术》编辑部 