In view of the complex and changeable environment in underground coal mines, an improved algorithm based on the principal component analysis-scale invariant feature transform (PCA-SIFT) and mean shift is proposed to address the issues for which existing tracking algorithms are not adequate; for example, when differentiating between moving targets and the background, the tracking in the case of moving objects (e.g., confusion between foreground and background) is not optimal. This results in poor resolution and the inability to deal with very dusty conditions, scale change, and rotation. The proposed feature target tracking model was developed using the scale invariance property of the PCA-SIFT feature-extraction algorithm. Finally, the mean-shift method was used to track moving objects. The experimental results showed that the optimized algorithm for tracking moving objects was significantly better and more robust than the existing algorithm. INDEX TERMS Target tracking, scale invariant feature transform, mean shift, target detection.
Currently, deep-learning-based methods have been the most popular super-resolution techniques owing to the improvement of super-resolution performance. However, they are still lack perceptual fine details and thus result in unsatisfying visual quality. This paper proposes a novel method for high-quality perceptual super-resolution imaging, named SRLRGAN-SN. It aims to recovery visually plausible images with perceptual texture details by using the least squares relativistic generative adversarial network (GAN). The method applies the spectral normalization on the network with the target of enhancing the performance of GAN for super-resolution task. The least squares relativistic discriminator is designed to drive reconstruction images approximating high-quality perceptual manifold. Besides, a novel perceptual loss assembly is proposed to preserve structural texture details as much as possible. Results of experiment show that our method can not only recovery more visually realistic details, but also outperforms other popular methods regarding to quantitative metrics and perceptual evaluations. INDEX TERMS Generative adversarial network, super-resolution imaging, relativistic discriminator, perceptual quality, spectral normalization.
To address problems that the loss function does not correlate well with perceptual vision in super-resolution methods based on the convolutional neural network(CNN), a novel model called the ADTV-SRGAN is designed based on the adaptive diagonal total-variation generative adversarial network. Combined with global perception and the local structure adaptive method, spatial loss based on the diagonal variation model is proposed to make the loss function can be adjusted according to the spatial features. Pixel loss and characteristic loss are in combination with the spatial loss for the fusing optimization of the total loss function such that high-frequency details of the images are maintained to improve their quality. The results of experiment show that the proposed method can obtain competitive results in objective evaluations. In subjective assessment, images reconstructed by it are clear, delicate, and natural, and it preserved edgeand texture-related details.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.