To address the issues of insufficient feature extraction and inadequate context modeling in monocular depth estimation， we proposed a multi-scale feature fused monocular depth estimation optimization framework， FCMdepth， to enhance prediction performance. FCMdepth adopted an Encoder-Decoder （ED） structure， where the encoder， FC-Net， consists of MobileNetV3-F and CDBlock， and optimized features through multi-scale features and dilated convolutions， while the decoder， LapMA-Net， combined the Laplacian pyramid with an Efficient Multi-scale Attention （EMA） module to enhance cross-scale feature fusion and output accurate depth maps. Experimental results on the KITTI datasets show that， compared to Lapdepth， FCMdepth achieves lower values for the three error metrics： Root Mean Square Error （RMSE）， Root Mean Square Logarithmic Error （Log_RMSE），and Square Relative error （Sq_Rel）， with reductions of 0.831， 0.009， and 0.145， respectively， and improves three accuracy metrics by of 0.4， 0.8， and 0.3 percentage points， respectively. It can be seen that FCMdepth has superior performance compared to other models in most metrics and provides an effective reference for monocular depth estimation and 3D reconstruction in complex scenes.

In recent years， significant progress has been made in applying Generative Adversarial Network （GAN） in Low-Dose Computed Tomography （LDCT） image denoising. However， the existing methods face challenges such as insufficient modeling capability for complex noise distribution and limited ability to preserve structural details. Therefore， a multi-path GAN for LDCT image denoising — Trident GAN was proposed. Firstly， a feature guided generator Trident Uformer was designed. In this generator， a Feature Polymerization Attention （FPA） module was added at the bottleneck layer of the U-Net structure， thereby solving the problem of low spatial resolution in a U-shaped structure. Secondly， a multi-path feature extraction submodule Trident Block was designed， and in each of the three blocks， a Local Detail Enhancement Block （LDEB） was introduced to extract detailed features， a Lightweight Channel Attention Block （LCAB） was incorporated to enhance channel features， and a Spatial Interaction Attention Block （SIAB） was utilized to capture important spatial features， respectively. Within the SIAB， a multi-level interactive attention function and evaluation mechanism were employed to design a Spatial Context Attention Mechanism （SCAM）， which addresses the limitations of single-attention mechanisms. Finally， a Multi-Feature Fusion （MFF） module was designed to realize feature aggregation at the end of the three blocks， and model both local detail information and global semantic information， and solve the problem of discontinuous details across different levels. Furthermore， the Multi-Scale Pyramid Discriminator （MSPD） was used to check the quality of the generated results at different dimensions， and guide the generation of globally consistent images. Experimental results show that Trident GAN achieves the average Peak Signal-to-Noise Ratio （PSNR） and Structural Similarity Index Measure （SSIM） of 31.519 3 dB/0.883 0 and 33.633 1 dB/0.947 8， respectively， on Mayo and Piglet datasets. Compared with High-Frequency Sensitive GAN （HFSGAN）， this method has the number of parameters reduced by 75.58% and the test time reduced by 36.36%. It can be seen that compared with the existing methods such as HFSGAN， Trident GAN improves image quality with less computational load.

Concerning the problem that pedestrians would be partially or seriously shaded by each other in video monitoring, this paper proposed a people counting algorithm based on human body skeleton feature. At first, the initial human skeleton was extracted by morphological skeleton extraction algorithm. Then the optimal skeleton feature was obtained by eliminating outliers and pseudo branches. Finally, this paper established a head detection response rule through analyzing the characteristics of skeleton in head areas to detect the head of pedestrian, and completed people counting by counting the heads of pedestrians. The experimental results show that the algorithm can solve the problems of partial and serious shading in video monitoring. For relatively sparse scene, the overall people counting accuracy rate of the algorithm is about 95%.

In view of the correction error problem which is caused by some factors such as dithering, the authors presented a new optical tilt correction method based on grating projection. The method was based on the analysis of each pixel of the data array in a sequence of fringe patterns having multiple frequencies, and setup model for pixel coordinates and pixel-slope. Then skew angles of fringes were calculated by trigonometry with the relationship between tilt angle and pixel-slope. At last, tilt correction was realized. The experimental results show that, the algorithm is capable of accurately detecting angle within the range [-90°,90°],accuracy is 99%. Compared with other algorithms such as Hough transform, the proposed algorithm improves precision and accuracy significantly.