In this work, we irradiated a high-definition (HD) industrial camera based on a commercial-off-the-shelf (COTS) CMOS image sensor (CIS) with Cobalt-60 gamma-rays. All components of the camera under test were fabricated without radiation hardening, except for the lens. The irradiation experiments of the HD camera under biased conditions were carried out at 1.0, 10.0, 20.0, 50.0 and 100.0 Gy/h. During the experiment, we found that the tested camera showed a remarkable degradation after irradiation and differed in the dose rates. With the increase of dose rate, the same target images become brighter. Under the same dose rate, the radiation effect in bright area is lower than that in dark area. Under different dose rates, the higher the dose rate is, the worse the radiation effect will be in both bright and dark areas. And the standard deviations of bright and dark areas become greater. Furthermore, through the progressive degradation analysis of the captured image, experimental results demonstrate that the attenuation of signal to noise ratio (SNR) versus radiation time is not obvious at the same dose rate, and the degradation is more and more serious with increasing dose rate. Additionally, the decrease rate of SNR at 20.0, 50.0 and 100.0 Gy/h is far greater than that at 1.0 and 10.0 Gy/h. Even so, we confirm that the HD industrial camera is still working at 10.0 Gy/h during the 8 h of measurements, with a moderate decrease of the SNR (5 dB). The work is valuable and can provide suggestion for camera users in the radiation field.

In recent years, with the rapid development of unmanned aerial vehicle (UAV) technology, multi-view 3D reconstruction has once again become a hot spot in computer vision. Incremental Structure From Motion (SFM) is currently the most prevalent reconstruction pipeline, but it still faces challenges in reconstruction efficiency, accuracy, and feature matching. In this paper, we use deep learning algorithms for feature matching to obtain more accurate matching point pairs. Moreover, we adopted the improved Gauss–Newton (GN) method, which not only avoids numerical divergence but also accelerates the speed of bundle adjustment (BA). Then, the sparse point cloud reconstructed by SFM and the original image are used as the input of the depth estimation network to predict the depth map of each image. Finally, the depth map is fused to complete the reconstruction of dense point clouds. After experimental verification, the reconstructed dense point clouds have rich details and clear textures, and the integrity, overall accuracy, and reconstruction efficiency of the point clouds have been improved.

This paper proposes a calibration method for a self-rotating, linear-structured-light (LSL) scanning, three-dimensional reconstruction system based on plane constraints. The point cloud of plane target collected by the self-rotating, LSL scanning, 3D reconstruction system should be constrained to the basic principle of the plane equation; it can quickly and accurately calibrate the position parameters between the coordinate system of the LSL module and the coordinate system of the self-rotating, LSL scanning, 3D reconstruction system. Additionally, the transformation equation could be established with the calibrated optimal position parameters. This paper obtains the above-mentioned position parameters through experiments and uses the calibrated self-rotating, LSL scanning, 3D reconstruction system to perform three-dimensional scanning and reconstruction of the test piece. The experimental results show that the calibration method can effectively improve the measurement accuracy of the system.

This work introduces a two-stage framework, named the Distorted underwater image Restoration Network (DR-Net), to address the complex degradation of underwater images caused by turbulence, water flow fluctuations, and optical properties of water. The first stage employs the Distortion Estimation Network (DE-Net), which leverages a fusion of Transformer and U-Net architectures to estimate distortion information from degraded images and focuses on image distortion recovery. Subsequently, the Image Restoration Generative Adversarial Network (IR-GAN) in the second stage utilizes this estimated distortion information to deblur images and regenerate lost details. Qualitative and quantitative evaluations on both synthetic and real-world image datasets demonstrate that DR-Net outperforms traditional methods and restoration strategies from different perspectives, showcasing its broader applicability and robustness. Our approach enables the restoration of underwater images from a single frame, which facilitates the acquisition of marine resources and enhances seabed exploration capabilities.