Although a various of existing techniques are able to improve the performance of detection of the weak interesting sig- nal, how to adaptively and efficiently attenuate the intricate noises especially in the case of n...Although a various of existing techniques are able to improve the performance of detection of the weak interesting sig- nal, how to adaptively and efficiently attenuate the intricate noises especially in the case of no available reference noise signal is still the bottleneck to be overcome. According to the characteristics of sonar arrays, a multi-channel differencing method is presented to provide the prerequisite reference noise. However, the ingre- dient of obtained reference noise is too complicated to be used to effectively reduce the interference noise only using the clas- sical linear cancellation methods. Hence, a novel adaptive noise cancellation method based on the multi-kernel normalized least- mean-square algorithm consisting of weighted linear and Gaussian kernel functions is proposed, which allows to simultaneously con- sider the cancellation of linear and nonlinear components in the reference noise. The simulation results demonstrate that the out- put signal-to-noise ratio （SNR） of the novel multi-kernel adaptive filtering method outperforms the conventional linear normalized least-mean-square method and the mono-kernel normalized least- mean-square method using the realistic noise data measured in the lake experiment.展开更多
针对废墟环境下红外图像人体检测任务中存在的图像分辨率低且人体特征不明显的问题,基于YOLO框架设计了一种包含重参数化(re-parameterization)和多尺度大核卷积(multi-scale large kernel convolution)的红外图像人体检测网络RML-YOLO(...针对废墟环境下红外图像人体检测任务中存在的图像分辨率低且人体特征不明显的问题,基于YOLO框架设计了一种包含重参数化(re-parameterization)和多尺度大核卷积(multi-scale large kernel convolution)的红外图像人体检测网络RML-YOLO(re-parameterization multi-scale large kernel convolution)。该网络通过空间和通道重构注意力模块,将注意值集中到对检测任务更重要的区域。通过Sobel算子强化边缘特征,提高对不同姿态人体的检测能力。RML-YOLO的有效性在自制数据集上得到验证。在只有1.8×10~6可学习参数的情况下,模型的AP50和AP50-75分别达到了91.2%和87.3%,与参数量相近的YOLOv8-n相比分别提高了4.4%和5.3%。结果表明,RML-YOLO显著提高了利用红外图像进行废墟环境下人体检测的精度。展开更多
基金supported by the National Natural Science Foundation of China(6100115361271415)+2 种基金the Opening Research Foundation of State Key Laboratory of Underwater Information Processing and Control(9140C231002130C23085)the Fundamental Research Funds for the Central Universities(3102014JCQ010103102014ZD0041)
文摘Although a various of existing techniques are able to improve the performance of detection of the weak interesting sig- nal, how to adaptively and efficiently attenuate the intricate noises especially in the case of no available reference noise signal is still the bottleneck to be overcome. According to the characteristics of sonar arrays, a multi-channel differencing method is presented to provide the prerequisite reference noise. However, the ingre- dient of obtained reference noise is too complicated to be used to effectively reduce the interference noise only using the clas- sical linear cancellation methods. Hence, a novel adaptive noise cancellation method based on the multi-kernel normalized least- mean-square algorithm consisting of weighted linear and Gaussian kernel functions is proposed, which allows to simultaneously con- sider the cancellation of linear and nonlinear components in the reference noise. The simulation results demonstrate that the out- put signal-to-noise ratio （SNR） of the novel multi-kernel adaptive filtering method outperforms the conventional linear normalized least-mean-square method and the mono-kernel normalized least- mean-square method using the realistic noise data measured in the lake experiment.
文摘针对废墟环境下红外图像人体检测任务中存在的图像分辨率低且人体特征不明显的问题,基于YOLO框架设计了一种包含重参数化(re-parameterization)和多尺度大核卷积(multi-scale large kernel convolution)的红外图像人体检测网络RML-YOLO(re-parameterization multi-scale large kernel convolution)。该网络通过空间和通道重构注意力模块,将注意值集中到对检测任务更重要的区域。通过Sobel算子强化边缘特征,提高对不同姿态人体的检测能力。RML-YOLO的有效性在自制数据集上得到验证。在只有1.8×10~6可学习参数的情况下,模型的AP50和AP50-75分别达到了91.2%和87.3%,与参数量相近的YOLOv8-n相比分别提高了4.4%和5.3%。结果表明,RML-YOLO显著提高了利用红外图像进行废墟环境下人体检测的精度。
