Synthesis and Detection Algorithms for Oblique Stripe Noise of Space-Borne Remote Sensing Images

Oblique stripe noise widely appears in remote sensing images after image correction, exhibiting arbitrary tilt angles and parallel distribution. Because of its arbitrary randomness in tilt angles and lengths, oblique stripe noise increases the difficulty of detection compared to vertical or horizontal stripe noise. For the first time, we propose a group of oblique stripe noise synthesis and detection algorithms combining imaging mechanisms and deep learning. To get controllable synthetic oblique stripe noise data for the training detection model, two sample augmentation methods are presented by the image correction's imaging mechanisms with new linear transformation and the generative adversarial network (GAN) algorithm with Cycle-GAN, respectively. A large-scale simulated stripe noise dataset simulated oblique stripe noise dataset (SOSD) is simulated using these two methods. A new deep learning detection algorithm, robust detection of oblique stripe noise (RDOS), is presented considering the presence of oblique stripe noise. RDOS is trained using both SOSD and a real stripe noise dataset, and it obtains the optimal detection model for testing. The experimental results show that the accuracy reaches 82.93%, the recall rate reaches 85.17%, the F1 score reaches 84.04%, the average precision (AP) reaches 82.34%, and the frames per second (FPS) reaches 33.33. Compared with the general line detection models, our model exceeds ~300% in accuracy and ~60% in speed. In the future, the proposed algorithms will have great potential for application in various areas, such as quality evaluation, image preprocessing, and engineering problems related to multiangle linear object augmentation and detection.