In order to improve the tracking accuracy and robustness of the rotating mirror servo system, a modified sliding mode-active disturbance rejection control (MSM-ADRC) strategy is proposed. Firstly, the structure and working principle of the rotating mirror servo system are analysed, and its mathematical model is established to prepare for the design of the controller. Then, a MSM-ADRC is proposed to reduce the influence of unknown disturbance and improve the tracking accuracy. Among them, the modified sliding mode extended state observation (MSM-ESO) is designed by replacing the traditional nonlinear function with the designed optimal control function, which enhances the observation accuracy of the system state quantity and total disturbance. Meanwhile, an improved approach law is proposed, and an improved sliding mode nonlinear error feedback control law (MSM-NLSEF) is designed based on this approach law, which improves the convergence speed and accuracy of the control law. In addition, the stability of the designed MSM-ESO and MSM-NLSEF is proved. Finally, the proposed control method is validated by simulation and experimental comparison with other state-of-the-art controllers. Results reveal that the proposed control method has satisfying tracking performance and strong disturbance rejection ability.

To address the issues of insufficient restoration of texture details in deblurred images and inadequate learning of frequency domain features, an image deblurring algorithm based on frequency domain feature enhancement and convolutional neural networks is proposed. In this architecture, firstly, a Fourier residual module with a parallel structure is constructed to achieve collaborative learning and modeling of spatial and frequency domain features, aiming to improve frequency domain feature learning capability and the restoration effect of the texture details; secondly, a gated controlled feed-forward unit acts on the Fourier residual module to further enhance the nonlinear expression ability of the algorithm; thirdly, a supervised attention module is improved and added to the decoder to promote more effective capture of key features for image reconstruction; finally, the weighted sum of spatial domain Charbonnier loss function and frequency domain loss function is defined as a novel total loss function. In addition, to verify the performance of our proposed algorithm, we conducted experiments on the GOPRO and HIDE datasets. Through experiments on the GOPRO, we obtained an SSIM and an LPIPS of 0.961 and 0.0278, respectively. With regard to the experiments on the HIDE datasets, we obtained an SSIM and an LPIPS of 0.941 and 0.0286, respectively. As for parameter count and running time, their values were 1.197 and 9.15 × 10⁶, respectively, obtained by the experiments on the GOPRO. In all algorithms, the values of our proposed algorithm are optimal. However, the PSNR of our proposed algorithm is very close to that of the latest comparison algorithm and is suboptimal. In a word, experimental results have demonstrated that our proposed algorithm effectively removes blur while better preserving the details and edges of the image. Therefore, it has more practical value and prospects in computer vision tasks.

To address the issues of insufficient restoration of texture details in deblurred images and inadequate learning of frequency domain features, an image deblurring algorithm based on frequency domain feature enhancement and convolutional neural networks is proposed. First, a Fourier residual module with a parallel structure is constructed to achieve collaborative learning and modeling of spatial and frequency domain features. By introducing the Fourier transform, the frequency domain feature learning is enhanced to improve the restoration of texture details. Second, after a gated feed-forward unit is applied to Fourier residual module, its nonlinear representation capability is further improved. In addition, a supervised attention module is introduced at the decoder stage to promote more effective extraction of key features essential for image reconstruction. Experimental results have demonstrated that the proposed algorithm effectively removes blur while better preserving image details.

A challenge in video tracking is effectively utilizing temporal correlation to navigate the complexity of a tracking scene without imposing additional computational requirements. Different from trackers that rely on online update templates, our methodology introduces a concise and efficient Siamese tracker, which assimilates temporal information via an offline strategy, named SiamGPF. Given the potential for a target to display varied appearances over time, a dependence solely on static template information proves inadequate for addressing extreme deformations and occlusions. Accordingly, we integrate the historical state of the target as pseudo-priori information into our framework, using global and local cross-correlation to fuse features accurately. Furthermore, we introduce a state fusion module to enhance the interplay of information across disparate temporal points of the target. In the inference phase, we implement a cost-effective prior frame dynamic selector, adept at eliminating low-quality target information, thereby substantially augmenting the robustness of the tracker. Our tracker exhibits competitive performance across prominent tracking benchmark datasets (OTB100, LaSOT, LaSOTExt, UAV123, NFS, TC128, GOT-10k, and VOT2016), with the official GOT-10k server evaluation results demonstrating an impressive operational speed of 212 FPS.