Low-light enhancement method with dual branch feature fusion and learnable regularized attention.

Restricted by the lighting conditions, the images captured at night tend to suffer from color aberration, noise, and other unfavorable factors, making it difficult for subsequent vision-based applications. To solve this problem, we propose a two-stage size-controllable low-light enhancement method, named Dual Fusion Enhancement Net (DFEN). The whole algorithm is built on a double U-Net structure, implementing brightness adjustment and detail revision respectively. A dual branch feature fusion module is adopted to enhance its ability of feature extraction and aggregation. We also design a learnable regularized attention module to balance the enhancement effect on different regions. Besides, we introduce a cosine training strategy to smooth the transition of the training target from the brightness adjustment stage to the detail revision stage during the training process. The proposed DFEN is tested on several low-light datasets, and the experimental results demonstrate that the algorithm achieves superior enhancement results with the similar parameters. It is worth noting that the lightest DFEN model reaches 11 FPS for image size of 1224×1024 in an RTX 3090 GPU.

Research on a multi-dimensional image information fusion algorithm based on NSCT transform.

Traditional inspection cameras determine targets and detect defects by capturing images of their light intensity, but in complex environments, the accuracy of inspection may decrease. Information based on polarization of light can characterize various features of a material, such as the roughness, texture, and refractive index, thus improving classification and recognition of targets. This paper uses a method based on noise template threshold matching to denoise and preprocess polarized images. It also reports on design of an image fusion algorithm, based on NSCT transform, to fuse light intensity images and polarized images. The results show that the fused image improves both subjective and objective evaluation indicators, relative to the source image, and can better preserve edge information and help to improve the accuracy of target recognition. This study provides a reference for the comprehensive application of multi-dimensional optical information in power inspection.

A similarity-guided segmentation model for garbage detection under road scene.

The development of computer vision technology provides a possible path for realizing intelligent control of road sweepers to reduce energy waste in urban street cleaning work. For garbage segmentation of seven categories under road scene, we introduce an efficient deep-learning-based method. Our model follows a lightweight structure with a feature pyramid attention (FPA) module employed in the decoder to enhance feature integration at multi-levels. Besides, a similarity guidance (SG) module is added to the decoder branches, which calculates the cosine distance between learned prototypes and feature maps to guide the segmentation results from a metric learning perspective. Our model has less than 3 M parameters and can run at over 65 FPS in an RTX 2070 GPU. Experimental results demonstrate that our method can yield competitive results in terms of speed and accuracy trade-off, with overall mean intersection-over-union (mIoU) reaching 0.87 and 0.67, respectively, on two garbage data sets we built. Besides, our model can perform acceptable category-balanced segmentation from less than 20 annotated images per category by introducing the SG module.

Efficient line-based lens distortion correction for complete distortion with vanishing point constraint.

The line-based correction method has been widely researched to improve the performance of lens distortion correction. However, due to the coupling of the distortion parameters and the inaccuracy of line equation estimation, it is difficult to achieve high-accuracy correction under the complete lens distortion (composed of radial, decentering, and prism distortion). Here, we present a method that utilizes two models to resolve these two problems, respectively: the recursive individual optimization model decouples the distortion parameters by applying Levenberg-Marquardt to optimize the parameters individually, and the vanishing point reprojection model improves the accuracy of line equation estimation with the known vanishing points calculated by a proposed expectation-minimization algorithm. Therefore, accurate correction of complete distortion can be achieved by the line information only. The validity of the proposed method was tested by several synthetic and real data, and the results showed that this method can correct the image with the complete and noncomplete distortion effectively.