<p>Accurately estimating depth from underwater monocular images is essential for the target tracking task of unmanned underwater vehicles. This work proposes a method based on the Lpg-Lap Unet architecture. First, the Unet architecture integrates Laplacian pyramid depth residuals and Sobel operators to improve the boundary details in depth images, which may suffer from the feature loss caused by upsampling and the blurriness of underwater images. Multiscale local planar guidance layers then fully exploit the intermediate depth features, and a comprehensive loss function ensures robustness and accuracy. Experimental results on benchmarks demonstrate the effectiveness of Lpg-Lap Unet and its superior performance over state-of-the-art models. An underwater target tracking system is then designed to further validate its real-time capabilities in the AirSim simulation platform.</p>