在计算机视觉研究领域,采集到的图像通常由于被测物体局部高亮或局部镜面反射导致局部过饱和,从而影响测量系统的后续数据处理。针对此问题,根据反射式硅基液晶能够逐像素调节入射光的发射率的性质,采用高解析度硅基液晶(liquidcrystal ...在计算机视觉研究领域,采集到的图像通常由于被测物体局部高亮或局部镜面反射导致局部过饱和,从而影响测量系统的后续数据处理。针对此问题,根据反射式硅基液晶能够逐像素调节入射光的发射率的性质,采用高解析度硅基液晶(liquidcrystal on silicon,LCoS)和图像传感器(CCD或CMOS)相结合,设计了基于LCoS的图像亮度调节硬件系统。根据硅基液晶与图像传感器的光学性质,确立了摄像机模型像平面和LCoS掩膜平面之间的映射关系,提出了基于空间映射的像素对应算法,实验证明,该算法准确、可靠,可以实现图像亮度的像素级调整。展开更多
The ECT （eddy current test） system is in use for Nb surface quality control in many laboratories. This system can inspect Nb surthce quickly using high resolution probe. The ECT system for RAON＇s cavity was made wi...The ECT （eddy current test） system is in use for Nb surface quality control in many laboratories. This system can inspect Nb surthce quickly using high resolution probe. The ECT system for RAON＇s cavity was made with these features： it has a 3-axis acting probe movenlent system, it can inspect a big size of Nb sheet, which is 1,200 mm × 365 mm and it contains the analysis program that can show the result as a 2D and 3D images as well as the relative figure of the surface level. The standard sample was made with various sizes of defects using the same Nb sheet that was used to make RISP （Rare Isotope Science Project） cavity. The ECT system conditioning was carried out to optimize the ECT operation on the frequency of which the range is from 300 KHZ to 2 MHz. The result of 900 KHZ showed the strongest signal. The conditioning experiment on other parameter will be carried out in the near future.展开更多
In this paper,we introduce a novel approach to automatically regulate receptive fields in deep image parsing networks.Unlike previous work which placed much importance on obtaining better receptive fields using manual...In this paper,we introduce a novel approach to automatically regulate receptive fields in deep image parsing networks.Unlike previous work which placed much importance on obtaining better receptive fields using manually selected dilated convolutional kernels,our approach uses two affine transformation layers in the network’s backbone and operates on feature maps.Feature maps are inflated or shrunk by the new layer,thereby changing the receptive fields in the following layers.By use of end-to-end training,the whole framework is data-driven,without laborious manual intervention.The proposed method is generic across datasets and different tasks.We have conducted extensive experiments on both general image parsing tasks,and face parsing tasks as concrete examples,to demonstrate the method’s superior ability to regulate over manual designs.展开更多
文摘在计算机视觉研究领域,采集到的图像通常由于被测物体局部高亮或局部镜面反射导致局部过饱和,从而影响测量系统的后续数据处理。针对此问题,根据反射式硅基液晶能够逐像素调节入射光的发射率的性质,采用高解析度硅基液晶(liquidcrystal on silicon,LCoS)和图像传感器(CCD或CMOS)相结合,设计了基于LCoS的图像亮度调节硬件系统。根据硅基液晶与图像传感器的光学性质,确立了摄像机模型像平面和LCoS掩膜平面之间的映射关系,提出了基于空间映射的像素对应算法,实验证明,该算法准确、可靠,可以实现图像亮度的像素级调整。
文摘The ECT （eddy current test） system is in use for Nb surface quality control in many laboratories. This system can inspect Nb surthce quickly using high resolution probe. The ECT system for RAON＇s cavity was made with these features： it has a 3-axis acting probe movenlent system, it can inspect a big size of Nb sheet, which is 1,200 mm × 365 mm and it contains the analysis program that can show the result as a 2D and 3D images as well as the relative figure of the surface level. The standard sample was made with various sizes of defects using the same Nb sheet that was used to make RISP （Rare Isotope Science Project） cavity. The ECT system conditioning was carried out to optimize the ECT operation on the frequency of which the range is from 300 KHZ to 2 MHz. The result of 900 KHZ showed the strongest signal. The conditioning experiment on other parameter will be carried out in the near future.
基金supported by the National Natural Science Foundation of China (Nos.U1536203,61572493)the Cutting Edge Technology Research Program of the Institute of Information Engineering,CAS (No.Y7Z0241102)+1 种基金the Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of the Ministry of Education (No.Y6Z0021102)Nanjing University of Science and Technology (No.JYB201702)
文摘In this paper,we introduce a novel approach to automatically regulate receptive fields in deep image parsing networks.Unlike previous work which placed much importance on obtaining better receptive fields using manually selected dilated convolutional kernels,our approach uses two affine transformation layers in the network’s backbone and operates on feature maps.Feature maps are inflated or shrunk by the new layer,thereby changing the receptive fields in the following layers.By use of end-to-end training,the whole framework is data-driven,without laborious manual intervention.The proposed method is generic across datasets and different tasks.We have conducted extensive experiments on both general image parsing tasks,and face parsing tasks as concrete examples,to demonstrate the method’s superior ability to regulate over manual designs.
