合成孔径雷达相干与非相干干扰性能分析

推导了合成孔径雷达(synthetic aperture radar,SAR)非相干干扰、一维卷积干扰和二维相干干扰成像前后的功率表达式,建立了成像处理增益(imaging processing gain,IPG)关于SAR系统参数和干扰区面积的关系模型和干信比(interference-signal power rate, ISR)方程。分析结果表明,在一定范围内,相干干扰的IPG随干扰区面积增大而减小,当一维卷积干扰的干扰区宽度大于SAR成像前距离分辨率时,其IPG与非相干干扰相同,当二维相干干扰的干扰区宽度和长度分别大于SAR成像前距离分辨率和方位分辨率时,其IPG与非相干干扰之比等于方位过采样率,3种干扰的ISR与IPG具有相同特性。仿真验证分析了所得出的结论。     

红外图像中的行人检测

为了有效地检测红外图像中的行人,提出了一种基于神经网络的检测方法。采用三维中值滤波来提取背景图像,用图像差分法提取目标区域(regions of interest,ROIs),提出傅里叶描述子作为目标区域形状特征;设计了BP神经网络分类器并用来对ROIs进行识别。通过大量不同种类不同形状的样本对分类器进行验证,结果表明该分类器具有较高的识别率和较低的虚警率,能够快速有效地识别ROIs,具有良好的分类能力。     

Non-identical residual learning for image enhancement via dynamic multi-level perceptual loss

Residual learning based deep generative networks have achieved promising performance in image enhancement.However,due to the large color gap between a low-quality image and its highquality version,the identical mapping in conventional residual learning cannot explore the elaborate detail differences,resulting in color deviations and texture losses in enhanced images.To address this issue,an innovative non-identical residual learning architecture is proposed,which views image enhancement as two c...