Infrared and visible image fusion technologies make full use of different image features obtained by different sensors, retain complementary information of the source images during the fusion process, and use redundant information to improve the credibility of the fusion image. In recent years, many researchers have used deep learning methods (DL) to explore the field of image fusion and found that applying DL has improved the time-consuming efficiency of the model and the fusion effect. However, DL includes many branches, and there is currently no detailed investigation of deep learning methods in image fusion. In this work, this survey reports on the development of image fusion algorithms based on deep learning in recent years. Specifically, this paper first conducts a detailed investigation on the fusion method of infrared and visible images based on deep learning, compares the existing fusion algorithms qualitatively and quantitatively with the existing fusion quality indicators, and discusses various fusions. The main contribution, advantages, and disadvantages of the algorithm. Finally, the research status of infrared and visible image fusion is summarized, and future work has prospected. This research can help us realize many image fusion methods in recent years and lay the foundation for future research work.

Images captured in low-light or underwater environments are often accompanied by significant degradation, which can negatively impact the quality and performance of downstream tasks. While convolutional neural networks (CNNs) and Transformer architectures have made significant progress in computer vision tasks, there are few efforts to harmonize them into a more concise framework for enhancing such images. To this end, this study proposes to aggregate the individual capability of self-attention (SA) and CNNs for accurate perturbation removal while preserving background contents. Based on this, we carry forward a Retinex-based framework, dubbed as Mutual Retinex, where a two-branch structure is designed to characterize the specific knowledge of reflectance and illumination components while removing the perturbation. To maximize its potential, Mutual Retinex is equipped with a new mutual learning mechanism, involving an elaborately designed mutual representation module (MRM). In MRM, the complementary information between reflectance and illumination components are encoded and used to refine each other. Through the complementary learning via the mutual representation, the enhanced results generated by our model exhibit superior color consistency and naturalness. Extensive experiments have shown the significant superiority of our mutual learning based method over thirteen competitors on the low-light task and ten methods on the underwater image enhancement task. In particular, our proposed Mutual Retinex respectively surpasses the state-of-the-art method MIRNet-v2 by 0.90 dB and 2.46 dB in PSNR on the LOL 1000 and FIVEK datasets, while with only 19.8% model parameters.

To address the problem that existing deep learning methods are not sufficiently accurate to detect rice pests with changeable shapes or similar appearances, a self-attention feature fusion model for rice pest detection (SAFFPest) was proposed. The model was based on VarifocalNet. First, a deformable convolution module was added to the feature extraction network, to improve the feature extraction ability of pests with changeable shapes. Second, by obtaining the balance features of multiple feature maps, the self-attention mechanism was introduced to refine the balance feature, in order to better restore the semantic information of some pests with similar appearances. Subsequently, the group normalization method was used to replace the batch normalization method in the original model, to reduce the impact of batch size on model training. The IP102 rice pest dataset was used to train and verify this model. The experimental results showed that the model can accurately detect nine kinds of rice pests, such as rice leaf rollers and rice leaf caterpillars. Compared with FasterRCNN, RetinaNet, CP-FCOS, VFNet and BiFA-YOLO, the mean average precision of the model improved by 33.7%, 6.5%, 4.5%, 2.9% and 2% respectively.

In recent years, jute, as an important natural fiber crop, has become more and more significant in the production process of insect pests, causing serious harm to agricultural production. Especially in the field of crop pest identification with complex backgrounds, fuzzy features, and multiple small targets, the lack of datasets specifically for jute pests has led to the large limitations of traditional pest identification models in terms of generalization. At the same time, the research on models specifically for jute pest detection is still in its infancy. To solve this problem, we constructed a large-scale image dataset containing nine types of jute pests, which was highly targeted and could effectively support model training and evaluation. In this study, we developed a deep convolutional neural network model based on YOLOv7, namely JutePest-YOLO. The model has optimized the Backbone, Head, and loss functions of the baseline model, and introduced the new ELAN-P module and P6 detection layer, which effectively improved the model’s ability to identify jute pests in complex backgrounds. The experimental results showed that compared with the baseline model, the Precision, Recall, and F1 scores of the JutePest-YOLO model were improved by 3.45%, 1.76%, and 2.58%, respectively; the mAP@0.5 and mAP@0.5:0.95 was improved by 2.24% and 3.25%, and the overall model’s computation (GFLOPS) was reduced by 16.05%. Compared to other advanced methods such as YOLOv8s, JutePest-YOLO has achieved superior performance in terms of detection accuracy, with a precision of 98.7% and mAP@0.5 reaching 95.68%. As a result, JutePest-YOLO not only achieved significant improvement in recognition accuracy but also optimized computational efficiency. It’s a high-performance, lightweight solution for jute pest detection.

The prediction of soil heavy metal content is an important part of the management of soil heavy metal pollution, but it is often ignored. At present, there are few studies on the prediction of soil heavy metal content, and it is an urgent problem to choose an efficient method for soil heavy metal content prediction. In this paper, a collaborative compound neural network model (CCNN) was put forward to predict the soil heavy metal content, this model uses wavelet neural network (WNN) as the basic prediction model, and at the same time proposes a parallel bird swarm algorithm (PBSA) to solve the parameter optimization problem of WNN, based on the bird swarm algorithm (BSA), the PBSA not only increases the gathering behavior of individual, but also adopts sine transformation based on fitness difference ratio to carry out the following behavior of beggars to improve the global optimization ability, besides that, the acceptance criterion is used to compare the fitness of individuals after updating to avoid falling into a local optimum. Soil heavy metal content data from Yinchuan city of Ningxia and six new urban areas in Wuhan, China are used to make prediction experiments respectively, through compare with support vector machine (SVM), radial basis function neural network (RBFNN), WNN and bird swarm algorithm optimizes wavelet neural network (BSA-WNN), the experimental results demonstrate that the predicted value of the CCNN is closer to the actual value and has better prediction performance.