A kind of turbo joint detection scheme based on parallel interference cancellation （PIC） is studied; then, the eigenvalues of iteration matrix is deeply analyzed for studying the ping-pong effects in PIC JD and the ...A kind of turbo joint detection scheme based on parallel interference cancellation （PIC） is studied; then, the eigenvalues of iteration matrix is deeply analyzed for studying the ping-pong effects in PIC JD and the corresponding compensation approach is introduced. Finally, the proposed algorithm is validated through computer simulation in TDD CDMA uplink transmission. The result shows that the ping-pong effects are almost avoided completely in the presence of the compensation scheme, and system performance is greatly improved.展开更多
在工业检测场景下,按照是否引入正常样本中不存在的异常,可以将异常检测问题分为结构异常检测和逻辑异常检测两类,逻辑异常检测对网络的全局理解能力提出了更高的要求。针对现有无监督异常检测模型在结构异常上已有较好的检测精度,但无...在工业检测场景下,按照是否引入正常样本中不存在的异常,可以将异常检测问题分为结构异常检测和逻辑异常检测两类,逻辑异常检测对网络的全局理解能力提出了更高的要求。针对现有无监督异常检测模型在结构异常上已有较好的检测精度,但无法适应逻辑异常检测需求的问题,提出一种包含空间聚合模块和通道聚合模块的双自编码器结构,主要由3部分组成。首先设计了并行空空间通道双自编码器架构,从空间和通道两个方向得到包含全局信息的特征向量,提升网络的长程依赖关系;其次设计一个选择性融合模块,融合双自编码器信息,放大包含重要信息的特征,以进一步提高对逻辑异常的表达能力;最后提出在自编码器与学生网络的损失函数中加入余弦损失,避免网络对单个像素差异过于敏感,从而关注于全局差异。在MVTec LOCO AD数据集上进行实验,逻辑异常检测精度达到89.4%,结构异常检测精度达到94.9%,平均检测精度92.1%,超越了基线方法和其他无监督缺陷检测方法,验证了方法的有效性和优越性。展开更多
The paper designs a peripheral maximum gray differ-ence(PMGD)image segmentation method,a connected-compo-nent labeling(CCL)algorithm based on dynamic run length(DRL),and a real-time implementation streaming processor ...The paper designs a peripheral maximum gray differ-ence(PMGD)image segmentation method,a connected-compo-nent labeling(CCL)algorithm based on dynamic run length(DRL),and a real-time implementation streaming processor for DRL-CCL.And it verifies the function and performance in space target monitoring scene by the carrying experiment of Tianzhou-3 cargo spacecraft(TZ-3).The PMGD image segmentation method can segment the image into highly discrete and simple point tar-gets quickly,which reduces the generation of equivalences greatly and improves the real-time performance for DRL-CCL.Through parallel pipeline design,the storage of the streaming processor is optimized by 55%with no need for external me-mory,the logic is optimized by 60%,and the energy efficiency ratio is 12 times than that of the graphics processing unit,62 times than that of the digital signal proccessing,and 147 times than that of personal computers.Analyzing the results of 8756 images completed on-orbit,the speed is up to 5.88 FPS and the target detection rate is 100%.Our algorithm and implementation method meet the requirements of lightweight,high real-time,strong robustness,full-time,and stable operation in space irradia-tion environment.展开更多
文摘A kind of turbo joint detection scheme based on parallel interference cancellation （PIC） is studied; then, the eigenvalues of iteration matrix is deeply analyzed for studying the ping-pong effects in PIC JD and the corresponding compensation approach is introduced. Finally, the proposed algorithm is validated through computer simulation in TDD CDMA uplink transmission. The result shows that the ping-pong effects are almost avoided completely in the presence of the compensation scheme, and system performance is greatly improved.
文摘在工业检测场景下,按照是否引入正常样本中不存在的异常,可以将异常检测问题分为结构异常检测和逻辑异常检测两类,逻辑异常检测对网络的全局理解能力提出了更高的要求。针对现有无监督异常检测模型在结构异常上已有较好的检测精度,但无法适应逻辑异常检测需求的问题,提出一种包含空间聚合模块和通道聚合模块的双自编码器结构,主要由3部分组成。首先设计了并行空空间通道双自编码器架构,从空间和通道两个方向得到包含全局信息的特征向量,提升网络的长程依赖关系;其次设计一个选择性融合模块,融合双自编码器信息,放大包含重要信息的特征,以进一步提高对逻辑异常的表达能力;最后提出在自编码器与学生网络的损失函数中加入余弦损失,避免网络对单个像素差异过于敏感,从而关注于全局差异。在MVTec LOCO AD数据集上进行实验,逻辑异常检测精度达到89.4%,结构异常检测精度达到94.9%,平均检测精度92.1%,超越了基线方法和其他无监督缺陷检测方法,验证了方法的有效性和优越性。
文摘The paper designs a peripheral maximum gray differ-ence(PMGD)image segmentation method,a connected-compo-nent labeling(CCL)algorithm based on dynamic run length(DRL),and a real-time implementation streaming processor for DRL-CCL.And it verifies the function and performance in space target monitoring scene by the carrying experiment of Tianzhou-3 cargo spacecraft(TZ-3).The PMGD image segmentation method can segment the image into highly discrete and simple point tar-gets quickly,which reduces the generation of equivalences greatly and improves the real-time performance for DRL-CCL.Through parallel pipeline design,the storage of the streaming processor is optimized by 55%with no need for external me-mory,the logic is optimized by 60%,and the energy efficiency ratio is 12 times than that of the graphics processing unit,62 times than that of the digital signal proccessing,and 147 times than that of personal computers.Analyzing the results of 8756 images completed on-orbit,the speed is up to 5.88 FPS and the target detection rate is 100%.Our algorithm and implementation method meet the requirements of lightweight,high real-time,strong robustness,full-time,and stable operation in space irradia-tion environment.
