When underwater camera is used to carry out the visual inspection after fuel reloading in nuclear power plants, heat exchange between fuel assemblies and water can generate underwater turbulence, which causes imaging distortion. Turbulence severely affects core verification of nuclear fuel assemblies, serial number of which should be identified. With the aim to recover the images from a video sequence severely distorted by turbulence, an image enhancement method is proposed. At first, an image quality assessment metric FSIM is used to select the better quality frames. Next an iterative robust registration algorithm is used to eliminate most geometric deformations and recover the water surface. The temporal mean of the sequence is utilized to overcome the structured turbulence of the waves through the algorithm. Finally, the sparse errors are extracted from the sequence through rank minimization to remove unstructured sparse noise. After image processing, optical character recognition is performed by KNN and CNN, obtaining high recognition rates of 99.33%, 100% respectively. The experimental results show that the suggested method significantly performs better in distorted image restoration and image text recognition on the task of visual inspection of nuclear fuel assemblies.
When underwater camera is used to carry out the visual inspection after fuel reloading in nuclear power plants, heat exchange between fuel assemblies and water can generate underwater turbulence effect, which causes imaging distortion, and then affects position measurement accuracy of nuclear fuel assemblies. A new online visual inspection method for fuel assemblies in nuclear power plants is proposed in this paper. The method consists of image restoration and deformation inspection. A turbulence image degradation model is established at first. In the model that water turbulence weakly satisfy a Gaussian distribution. A temporal high pass filter by image quality assessment and a mean filter in time domain are used to remove the morphing of acquired original sequence images according to the degradation model. And then a spatial Wiener deconvolution filter is used to remove the image blurring that is caused by the above mentioned mean filter. The next step is using the deformation inspection algorithm to get the fuel assembles precise position. The distance of feature holes (S-hole) is solved by calibrated underwater parametric camera model. The experimental results show that the underwater image restoration method can effectively remove the image morphing that is generated by turbulence effect. The proposed online visual inspection method has a high detection precision. And the average error of the solved feature holes’ distance is less than 0.1 mm when the execution time of the method is lower than 0.5 s.