Infrared Non-uniformity Correction Method Based on Scene-adaptive Directional Guided Filtering
Infrared imaging non-uniformity severely degrades the quality of infrared images,reducing their clarity and sensitivity,and thereby limiting the effective application of various subsequent infrared image algorithms.To eliminate infrared imaging non-uniformity and improve the quality of infrared images,this paper proposes a novel infrared imaging non-uniformity correction method based on scene-adaptive directional guided filtering,extending the traditional neural network non-uniformity correction algorithm.First,this paper analyzes the causes of non-uniformity in infrared images and proposes a model for infrared non-uniformity generation.It is concluded that infrared non-uniformity manifests as vertical stripe patterns in the vertical direction.Based on this characteristic,the paper improves the Canny extraction algorithm with dual-threshold characteristics and uses the improved Canny algorithm to extract detailed features of infrared images.The dual-threshold characteristic can suppress infrared non-uniformity while extracting detailed image features.This extracted feature is then used to adaptively adjust the regularization factor of the traditional guided filter,resulting in the proposed scene-adaptive directional guided filter.Traditional guided filters process the entire image using uniform linear models and regularization factors,which cannot adequately preserve detailed image information.Although guided filters can protect image edges and textures while smoothing the image,there are still deficiencies when estimating the desired image for the neural network correction algorithm:1)Guided filters use the same regularization factor for all local windows in the image,without considering the differences in detailed textures within different windows.Therefore,the original guided filter does not sufficiently protect the detailed features of the image.2)The uncorrected infrared image contains stripe non-uniformity and pixel response non-uniformity.Although the intensity of these non-uniformities is weaker than that of the scene edge features,their presence causes a large local window variance even in flat areas of the image.The guided filter cannot adapt to the characteristics of infrared non-uniformity,leading to a lack of smoothing in local areas that should be smoothed,thus retaining the non-uniformity.The regularization factor is an inherent parameter of the guided filter,used to enhance the stability of the guided filter.The original guided filter applies the same regularization factor to all areas,failing to reflect the differences in detailed features across different regions.Therefore,it is necessary to adjust the penalty factor based on image details,i.e.,to adaptively adjust the regularization factor by calculating the penalty factor using local edge detail features of the image.The proposed scene-adaptive directional guided filter adaptively calculates the Canny edge feature response of non-uniform images within local windows and uses this response feature to compute a penalty factor to adjust the guided filter's regularization factor.This method estimates a more realistic scene image,preserving image details and improving the robustness of the correction algorithm.The scene-adaptive directional guided filter enables the neural network correction process to obtain infrared expected images closer to the real scene,significantly enhancing the overall performance of the neural network non-uniformity correction algorithm.Additionally,to address the issue of ghosting commonly associated with neural network correction algorithms,this paper employs a motion detection mechanism and adaptive adjustment of the neural network learning rate to suppress ghosting artifacts.Extensive experiments on infrared non-uniformity image correction validate that the proposed method effectively preserves detailed image information while suppressing infrared pixel non-uniformity and stripe non-uniformity.This enhances the effectiveness and robustness of the non-uniformity correction algorithm.In conclusion,the proposed scene-adaptive directional guided filter-based infrared imaging non-uniformity correction method effectively corrects infrared non-uniformity,preserves detailed image information,and improves the robustness and effectiveness of neural network-based non-uniformity correction algorithms.This advancement facilitates the application of subsequent infrared target detection algorithms,significantly enhancing the quality and reliability of infrared imaging.
万方数据
维普
