The precision in evaluating global ambient light profoundly impacts the performance of image-dehazing technologies. Many approaches for quantifying atmospheric light intensity suffer from inaccuracies, leading to a decrease in dehazing effectiveness. To address this challenge, we introduce an approach for estimating atmospheric light based on the polarization contrast between the sky and the scene. By employing this method, we enhance the precision of atmospheric light estimation, enabling the more accurate identification of sky regions within the image. We adapt the original dark channel dehazing algorithm using this innovative technique, resulting in the development of a polarization-based dehazing imaging system employed in practical engineering applications. Experimental results reveal a significant enhancement in the accuracy of atmospheric light estimation within the dark channel dehazing algorithm. Consequently, this method enhances the overall perceptual quality of dehazed images. The proposed approach demonstrates a 28 percent improvement in SSIM and a contrast increase of over 20 percent when compared to the previous method. Additionally, the created dehazing system exhibits real-time processing capabilities.

Space object recognition in high Earth orbits (between 2000 km and 36,000 km) is affected by moonlight and clouds, resulting in some bright or saturated image areas and uneven image backgrounds. It is difficult to separate dim objects from complex backgrounds with gray thresholding methods alone. In this paper, we present a segmentation method of star images with complex backgrounds based on correlation between space objects and one-dimensional (1D) Gaussian morphology, and the focus is shifted from gray thresholding to correlation thresholding. We build 1D Gaussian functions with five consecutive column data of an image as a group based on minimum mean square error rules, and the correlation coefficients between the column data and functions are used to extract objects and stars. Then, lateral correlation is repeated around the identified objects and stars to ensure their complete outlines, and false alarms are removed by setting two values, the standard deviation and the ratio of mean square error and variance. We analyze the selection process of each thresholding, and experimental results demonstrate that our proposed correlation segmentation method has obvious advantages in complex backgrounds, which is attractive for object detection and tracking on a cloudy and bright moonlit night.

To overcome the influence of the daytime skylight background on long-distance optical detection, a new type of shearing interference detection system was proposed to improve the detection performance of the traditional detection system for finding dark objects such as dim stars during the daytime. This article focuses on the basic principle and mathematical model as well as the simulation and experimental research of the new type of shearing interference detection system. The comparison of the detection performance between this new-type detection system and the traditional system is also carried out in this article. The experimental results show that the detection performance of the new type of shearing interference detection system is significantly better than that of the traditional system, and the image signal-to-noise ratio of this new-type system (about 13.2) is much higher than that of the best result of the traditional detection system (about 5.1).

Depth estimation represents a prevalent research focus within the realm of computer vision. Existing depth estimation methodologies utilizing LiDAR (Light Detection and Ranging) technology typically obtain sparse depth data and are associated with elevated hardware expenses. Multi-view image-matching techniques necessitate prior knowledge of camera intrinsic parameters and frequently encounter challenges such as depth inconsistency, loss of details, and the blurring of edges. To tackle these challenges, the present study introduces a monocular depth estimation approach based on an end-to-end convolutional neural network. Specifically, a DNET backbone has been developed, incorporating dilated convolution and feature fusion mechanisms within the network architecture. By integrating semantic information from various receptive fields and levels, the model’s capacity for feature extraction is augmented, thereby enhancing its sensitivity to nuanced depth variations within the image. Furthermore, we introduce a loss function optimization algorithm specifically designed to address class imbalance, thereby enhancing the overall predictive accuracy of the model. Training and validation conducted on the NYU Depth-v2 (New York University Depth Dataset Version 2) and KITTI (Karlsruhe Institute of Technology and Toyota Technological Institute) datasets demonstrate that our approach outperforms other algorithms in terms of various evaluation metrics.