Process signatures of the fusion area directly determine the quality of the part in Laser Powder Bed Fusion (LPBF). The geometric contour of the fusion area is one of the most important indicators of manufacturing quality. The accurate detection of the contour has been generating considerable interest. However, due to the complex operating condition in LPBF, the 2D images of the fusion area suffer from shortcomings such as poor contrast, high noise, and vary illumination. This makes the location of the contour extremely difficult for traditional detection methods. In this study, a robust contour detection method of the fusion area in LPBF is proposed. In order to raise the contrast of the contour, the phase image with clear contour details will be calculated from a series of fringe images with phase shift projected onto the fusion area. A phase-guided contour extraction method is conducted to accurately locate the center of contour which reduces significantly the impact of the severe manufacturing condition. Experimental results reveal that the proposed method can obtain the contours of the fusion area in a very short time, with higher accuracy and repeatability. In addition, it also holds the potential to be an effective way to monitor the geometric defects layer-wise.
In this paper , we choose four different variances of 1,3,6 and 12 to conduct FPGA design with three kinds of Gaussian filtering algorithm ,they are implementing Gaussian filter with a Gaussian filter template, Gaussian filter approximation with mean filtering and Gaussian filter approximation with IIR filtering. By waveform simulation and synthesis, we get the processing results on the experimental image and the consumption of FPGA resources of the three methods. We set the result of Gaussian filter used in matlab as standard to get the result error. By comparing the FPGA resources and the error of FPGA implementation methods, we get the best FPGA design to achieve a Gaussian filter. Conclusions can be drawn based on the results we have already got. When the variance is small, the FPGA resources is enough for the algorithm to implement Gaussian filter with a Gaussian filter template which is the best choice. But when the variance is so large that there is no more FPGA resources, we can chose the mean to approximate Gaussian filter with IIR filtering.
Detection of the moving targets is a challenging problem in the fields of computer vision especially on complex circumstance. It plays a very important role for the subsequent advanced task such as tracking and behavior understanding are only related to the moving pixels. To well model the moving detection issue, a novel spatial-temporal multi-scale method is proposed to solve the problem of detecting multiple moving objects on complex background in this paper. Moving objects have multi-scale features both in spatial and temporal domain essentially, which means each object has an optimum temporal-spatial detection window. Hence, the problem of detecting moving objects can be transformed into searching optimal spatial-temporal sub-spaces within different scales. A region growing and splitting recursive algorithm in 3D space and an optimal determinant criterion for estimating motion salience and a real time processing architecture are proposed, which can detect multiple objects at different spatial-temporal scales and extract their features on complex background. Experimental results demonstrated that the proposed method is superior to some of the traditional algorithms and works efficiently in detecting multiple moving objects.
Matching the template image in the target image is the fundamental task in the field of computer vision. Aiming at the
deficiency in the traditional image matching methods and inaccurate matching in scene image with rotation, illumination
and view changing, a novel matching algorithm using local features are proposed in this paper. The local histograms of
the edge pixels (LHoE) are extracted as the invariable feature to resist view and brightness changing. The merits of the
LHoE is that the edge points have been little affected with view changing, and the LHoE can resist not only illumination
variance but also the polution of noise. For the process of matching are excuded only on the edge points, the computation
burden are highly reduced. Additionally, our approach is conceptually simple, easy to implement and do not need the
training phase. The view changing can be considered as the combination of rotation, illumination and shear
transformation. Experimental results on simulated and real data demonstrated that the proposed approach is superior to
NCC(Normalized cross-correlation) and Histogram-based methods with view changing.
According to the role of the current large-scale storage system, this paper introduces a novel metadata service strategy
that separates read from write for the larger proportion of read. It centralizes control and reduces the access workload
through the multi-metadata server architecture of the master/slave mode. Through the sharing of original metadata server
to read the response to the large scale to reduce the load on the reading pattern to form a viable structure of the system. It
not only can bring the system better scalability and usability, but can well control metadata consistency. Finally,
compared to Active/Active structure, Read/Write strategy has shown a relatively good result in the aspect of the access
efficiency and System costs. As a service management strategy, it effectively reduces the load of the data access of