RF-Net: Unsupervised Low-Light Image Enhancement Based on Retinex and Exposure Fusion

Low-light image enhancement methods have limitations in addressing issues such as color distortion,lack of vibrancy,and uneven light distribution and often require paired training data.To address these issues,we propose a two-stage unsupervised low-light image enhancement algorithm called Retinex and Exposure Fusion Network(RFNet),which can overcome the problems of over-enhancement of the high dynamic range and under-enhancement of the low dynamic range in existing enhancement algorithms.This algorithm can better manage the challenges brought about by complex environments in real-world scenarios by training with unpaired low-light images and regular-light images.In the first stage,we design a multi-scale feature extraction module based on Retinex theory,capable of extracting details and structural information at different scales to generate high-quality illumination and reflection images.In the second stage,an exposure image generator is designed through the camera response mechanism function to acquire exposure images containing more dark features,and the generated images are fused with the original input images to complete the low-light image enhancement.Experiments show the effectiveness and rationality of each module designed in this paper.And the method reconstructs the details of contrast and color distribution,outperforms the current state-of-the-art methods in both qualitative and quantitative metrics,and shows excellent performance in the real world.

Convolutional Neural Network Based on Spatial Pyramid for Image Classification

A novel convolutional neural network based on spatial pyramid for image classification is proposed.The network exploits image features with spatial pyramid representation.First,it extracts global features from an original image,and then different layers of grids are utilized to extract feature maps from different convolutional layers.Inspired by the spatial pyramid,the new network contains two parts,one of which is just like a standard convolutional neural network,composing of alternating convolutions and subsampling layers.But those convolution layers would be averagely pooled by the grid way to obtain feature maps,and then concatenated into a feature vector individually.Finally,those vectors are sequentially concatenated into a total feature vector as the last feature to the fully connection layer.This generated feature vector derives benefits from the classic and previous convolution layer,while the size of the grid adjusting the weight of the feature maps improves the recognition efficiency of the network.Experimental results demonstrate that this model improves the accuracy and applicability compared with the traditional model.

VMMAO-YOLO:an ultra-lightweight and scale-aware detector for real-time defect detection of avionics thermistor wire solder joints

The quality of the exposed avionics solder joints has a significant impact on the stable operation of the inorbit spacecrafts.Nevertheless,the previously reported inspection methods for multi-scale solder joint defects generally suffer low accuracy and slow detection speed.Herein,a novel real-time detector VMMAO-YOLO is demonstrated based on variable multi-scale concurrency and multi-depth aggregation network(VMMANet)backbone and“one-stop”global information gather-distribute(OS-GD)module.Combined with infrared thermography technology,it can achieve fast and high-precision detection of both internal and external solder joint defects.Specifically,VMMANet is designed for efficient multi-scale feature extraction,which mainly comprises variable multi-scale feature concurrency(VMC)and multi-depth feature aggregation-alignment(MAA)modules.VMC can extract multi-scale features via multiple fix-sized and deformable convolutions,while MAA can aggregate and align multi-depth features on the same order for feature inference.This allows the low-level features with more spatial details to be transmitted in depth-wise,enabling the deeper network to selectively utilize the preceding inference information.The VMMANet replaces inefficient highdensity deep convolution by increasing the width of intermediate feature levels,leading to a salient decline in parameters.The OS-GD is developed for efficacious feature extraction,aggregation and distribution,further enhancing the global information gather and deployment capability of the network.On a self-made solder joint image data set,the VMMAOYOLO achieves a mean average precision mAP@0.5 of 91.6%,surpassing all the mainstream YOLO-series models.Moreover,the VMMAO-YOLO has a body size of merely 19.3 MB and a detection speed up to 119 frame per second,far superior to the prevalent YOLO-series detectors.