Image dehazing combining polarization properties and deep learning.

In order to solve the problems of color shift and incomplete dehazing after image dehazing, this paper proposes an improved image self-supervised learning dehazing algorithm that combines polarization characteristics and deep learning. First, based on the YOLY network framework, a multiscale module and an attention mechanism module are introduced into the transmission feature estimation network. This enables the extraction of feature information at different scales and allocation of weights, and effectively improves the accuracy of transmission map estimation. Second, a brightness consistency loss based on the YCbCr color space and a color consistency loss are proposed to constrain the brightness and color consistency of the dehazing results, resolving the problems of darkened brightness and color shifts in dehazed images. Finally, the network is trained to dehaze polarized images based on the atmospheric scattering model and loss function constraints. Experiments are conducted on synthetic and real-world data, and comparisons are made with six contrasting dehazing algorithms. The results demonstrate that, compared to the contrastive dehazing algorithms, the proposed algorithm achieves PSNR and SSIM values of 23.92 and 0.94, respectively, on synthetic image samples. For real-world image samples, color restoration is more authentic, contrast is higher, and detailed information is richer. Both subjective and objective evaluations show significant improvements. This validates the effectiveness and superiority of the proposed dehazing algorithm.

Single-view calibration of a catadioptric camera based on a theodolite model.

The catadioptric panoramic imaging system may provide 360° panoramic imaging by employing the convex surface of a quadric surface with rotational symmetry as the reflector, which effectively compensates for the disadvantages of the narrow field of view in typical camera systems. First, this paper proposes a theodolite-based catadioptric camera image model based on the rotational symmetry of a catadioptric camera mirror, which simplifies the 2D modeling problem to a 1D problem. Simultaneously, the equivalence of the theodolite imaging model and the standard spherical imaging model also is demonstrated in this work. Second, this paper presents a method to calibrate the theodolite model parameters using only a single view and explains the calculation of model parameter initialization and iterative optimization steps in detail. Then, this paper demonstrates how to calibrate the theodolite model parameters using only a single view, as well as how to calculate the model parameter initialization and iterative optimization steps. Finally, simulation experiments and actual experiments have confirmed the correctness and stability of the method. The experimental results show that the average and standard deviation of the back-projection error are, respectively, 0.1983125 pixels and 0.0006153 pixels, in this model. We believe the theodolite model suggested in this paper offers a viable approach to catadioptric camera image modeling.

Calibration of a Catadioptric System and 3D Reconstruction Based on Surface Structured Light.

In response to the problem of the small field of vision in 3D reconstruction, a 3D reconstruction system based on a catadioptric camera and projector was built by introducing a traditional camera to calibrate the catadioptric camera and projector system. Firstly, the intrinsic parameters of the camera and the traditional camera are calibrated separately. Then, the calibration of the projection system is accomplished by the traditional camera. Secondly, the coordinate system is introduced to calculate, respectively, the position of the catadioptric camera and projector in the coordinate system, and the position relationship between the coordinate systems of the catadioptric camera and the projector is obtained. Finally, the projector is used to project the structured light fringe to realize the reconstruction using a catadioptric camera. The experimental results show that the reconstruction error is 0.75 mm and the relative error is 0.0068 for a target of about 1 m. The calibration method and reconstruction method proposed in this paper can guarantee the ideal geometric reconstruction accuracy.

High-Resolution Drone Detection Based on Background Difference and SAG-YOLOv5s.

To solve the problem of low accuracy and slow speed of drone detection in high-resolution images with fixed cameras, we propose a detection method combining background difference and lightweight network SAG-YOLOv5s. First, background difference is used to extract potential drone targets in high-resolution images, eliminating most of the background to reduce computational overhead. Secondly, the Ghost module and SimAM attention mechanism are introduced on the basis of YOLOv5s to reduce the total number of model parameters and improve feature extraction, and α-DIoU loss is used to replace the original DIoU loss to improve the accuracy of bounding box regression. Finally, to verify the effectiveness of our method, a high-resolution drone dataset is made based on the public data set. Experimental results show that the detection accuracy of the proposed method reaches 97.6%, 24.3 percentage points higher than that of YOLOv5s, and the detection speed in 4K video reaches 13.2 FPS, which meets the actual demand and is significantly better than similar algorithms. It achieves a good balance between detection accuracy and detection speed and provides a method benchmark for high-resolution drone detection under a fixed camera.

A Semantic SLAM System for Catadioptric Panoramic Cameras in Dynamic Environments.

When a traditional visual SLAM system works in a dynamic environment, it will be disturbed by dynamic objects and perform poorly. In order to overcome the interference of dynamic objects, we propose a semantic SLAM system for catadioptric panoramic cameras in dynamic environments. A real-time instance segmentation network is used to detect potential moving targets in the panoramic image. In order to find the real dynamic targets, potential moving targets are verified according to the sphere's epipolar constraints. Then, when extracting feature points, the dynamic objects in the panoramic image are masked. Only static feature points are used to estimate the pose of the panoramic camera, so as to improve the accuracy of pose estimation. In order to verify the performance of our system, experiments were conducted on public data sets. The experiments showed that in a highly dynamic environment, the accuracy of our system is significantly better than traditional algorithms. By calculating the RMSE of the absolute trajectory error, we found that our system performed up to 96.3% better than traditional SLAM. Our catadioptric panoramic camera semantic SLAM system has higher accuracy and robustness in complex dynamic environments.

Pose Estimation of Omnidirectional Camera with Improved EPnP Algorithm.

The omnidirectional camera, having the advantage of broadening the field of view, realizes 360° imaging in the horizontal direction. Due to light reflection from the mirror surface, the collinearity relation is altered and the imaged scene has severe nonlinear distortions. This makes it more difficult to estimate the pose of the omnidirectional camera. To solve this problem, we derive the mapping from omnidirectional camera to traditional camera and propose an omnidirectional camera linear imaging model. Based on the linear imaging model, we improve the EPnP algorithm to calculate the omnidirectional camera pose. To validate the proposed solution, we conducted simulations and physical experiments. Results show that the algorithm has a good performance in resisting noise.

Improved difference model applied in the Fourier-transform-based integration method based on Taylor theory.

The two-dimensional Fourier-transform-based integration algorithm is widely used in shape or wavefront reconstruction from gradients. However, its reconstruction accuracy is limited by the truncation error of the difference model. The truncation error is affected by the distribution of the sampling points. It increases when the sampling points are unevenly distributed and arranged irregularly. For improving, a novel way to calculate the difference is proposed based on Taylor expansion theory of binary functions. The first-order partial derivative terms are used to estimate the second- and third-order partial derivative terms for reducing the truncation error. The proposed difference model is applied to Fourier-transform-based integration. The reconstruction results show that it can get better results when the sampling points are irregularly distributed.

Methods based on 1D homography for camera calibration with 1D objects.

This paper focuses on camera calibration with one-dimensional (1D) objects, and novel methods are proposed in this paper. Different from the known 1D object-based camera calibration algorithms, which define the camera coordinate system as the world coordinate system, we assume that the 1D calibration object is located along the X axis of the world coordinate system. Based on this new model, a 3×2 1D homography is defined to relate the points in the 1D objects to the perspective image points thereof. Then, the basic constraint for camera calibration using 1D objects from a single image is derived. Subsequently, two existing motions, namely, rotating around a fixed point and moving on a plane, are discussed, and new algorithms are proposed. In our methods, if the number of points in the 1D objects is more than three, more compact constraints can be obtained when the 1D objects rotate around a fixed point. In the case of planar motion, the estimation of vanishing points is not needed, and the calibration accuracy is significantly improved. Finally, both computer simulations and experiments are performed to validate the effectiveness and robustness of our algorithms.

Performance evaluation of coherent free space optical communications with a double-stage fast-steering-mirror adaptive optics system depending on the Greenwood frequency.

The Greenwood frequency (GF) is influential in performance improvement for the coherent free space optical communications (CFSOC) system with a closed-loop adaptive optics (AO) unit. We analyze the impact of tilt and high-order aberrations on the mixing efficiency (ME) and bit-error-rate (BER) under different GF. The root-mean-square value (RMS) of the ME related to the RMS of the tilt aberrations, and the GF is derived to estimate the volatility of the ME. Furthermore, a numerical simulation is applied to verify the theoretical analysis, and an experimental correction system is designed with a double-stage fast-steering-mirror and a 97-element continuous surface deformable mirror. The conclusions of this paper provide a reference for designing the AO system for the CFSOC system.