Aiming to address the issues of missing detailed information, the blurring of significant target information, and poor visual effects in current image fusion algorithms, this paper proposes an infrared and visible-light image fusion algorithm based on discrete wavelet transform and convolutional neural networks. Our backbone network is an autoencoder. A DWT layer is embedded in the encoder to optimize frequency-domain feature extraction and prevent information loss, and a bottleneck residual block and a coordinate attention mechanism are introduced to enhance the ability to capture and characterize the low- and high-frequency feature information; an IDWT layer is embedded in the decoder to achieve the feature reconstruction of the fused frequencies; the fusion strategy adopts the $l_1-norm$ fusion strategy to integrate the encoder’s output frequency mapping features; a weighted loss containing pixel loss, gradient loss, and structural loss is constructed for optimizing network training. DWT decomposes the image into sub-bands at different scales, including low-frequency sub-bands and high-frequency sub-bands. The low-frequency sub-bands contain the structural information of the image, which corresponds to the important target information, while the high-frequency sub-bands contain the detail information, such as edge and texture information. Through IDWT, the low-frequency sub-bands that contain important target information are synthesized with the high-frequency sub-bands that enhance the details, ensuring that the important target information and texture details are clearly visible in the reconstructed image. The whole process is able to reconstruct the information of different frequency sub-bands back into the image non-destructively, so that the fused image appears natural and harmonious visually. Experimental results on public datasets show that the fusion algorithm performs well according to both subjective and objective evaluation criteria and that the fused image is clearer and contains more scene information, which verifies the effectiveness of the algorithm, and the results of the generalization experiments also show that our network has good generalization ability.

This paper presents an algorithm for infrared and visible image fusion using significance detection and Convolutional Neural Networks with the aim of integrating discriminatory features and improving the overall quality of visual perception. Firstly, a global contrast-based significance detection algorithm is applied to the infrared image, so that salient features can be extracted, highlighting high brightness values and suppressing low brightness values and image noise. Secondly, a special loss function is designed for infrared images to guide the extraction and reconstruction of features in the network, based on the principle of salience detection, while the more mainstream gradient loss is used as the loss function for visible images in the network. Afterwards, a modified residual network is applied to complete the extraction of features and image reconstruction. Extensive qualitative and quantitative experiments have shown that fused images are sharper and contain more information about the scene, and the fused results look more like high-quality visible images. The generalization experiments also demonstrate that the proposed model has the ability to generalize well, independent of the limitations of the sensor. Overall, the algorithm proposed in this paper performs better compared to other state-of-the-art methods.

This study presents an innovative method to optimize convolutional neural networks (CNNs) tailored for the prevalent low-power platforms in IoT and embedded devices, which are integral to smart city infrastructures. Our approach introduces a novel “Rotating Convolutional Kernel” technique, designed to significantly reduce the computational load of CNNs while maintaining high accuracy, an essential feature for the constrained processing capabilities of devices produced by Hisilicon, MediaTek, and Novatek, among others. By leveraging the intelligent video engine (IVE) capabilities inherent in low-end CPUs, our optimized YOLOv3-Tiny model, with fewer than 100 K parameters and specifically fine-tuned for pedestrian and vehicle detection, demonstrates impressive processing speeds of 52 ms/frame on the HI3516EV200 chip and 66 ms/frame on the MSC313E chip, with minimal accuracy compromise. Despite a substantial reduction in parameter count compared to that in MobileNetV2, our model’s top-1 accuracy only slightly decreases by 2.6%, showcasing the effectiveness of our optimization technique. Our findings highlight the potential and applicability of our method in enhancing the performance and utility of IoT and embedded devices within smart cities. By achieving an optimal balance between computational efficiency and detection accuracy, our approach offers a promising avenue for advancing the capabilities of low-power devices in urban surveillance, traffic management, and other smart city applications, thereby contributing to the development of more intelligent, efficient, and responsive urban environments.

Aiming to address the issues of detail loss, salient target blurring, and poor visual effects in current image fusion algorithms, we propose a dual-branch feature extraction image fusion method based on Transformers and convolutional neural networks (CNNs). By leveraging the advantages of CNNs for extracting local contextual information and Transformers for capturing global feature representations, we propose a dual-branch feature extraction image fusion method based on Transformers and CNNs. This method aims to balance local detail information with global information during the fusion of infrared and visible light images. We designed a shared feature extraction module to extract key feature information from the source images and facilitate the channeling of modal features. In addition, we developed a low-frequency base feature extraction branch based on a context-aware CNN-Transformer hybrid module and a high-frequency detail feature extraction branch based on a residual dense attention module. These branches separately extract and fuse low-frequency global base feature information and high-frequency detail texture feature information, achieving complementary information between the input source images and resulting in high-quality fused images with excellent performance metrics such as contrast and clarity.

Aiming at the problem that the traditional physical layer technology cannot realize secure transmission due to the large number of users and wide dispersion in the multicast system, a layered transmission method is proposed, and a scheme for the secure transmission of the multicast group physical layer is designed. Firstly, the hierarchical transmission system model is established. Then, the array weighted vector of each layer is optimized according to the design criterion of maximizing the artificial noise interference power. At the same time, in the case where the number of users in a single multicast group is greater than the number of transmitting antennas, a multicast grouping strategy is introduced, and the singular value decomposition and Lagrange multiplier algorithms are utilized to obtain the optimal solution. Simulation results show that the proposed method can realize the secure communication of users with different distances in the same direction and can distinguish the multicast users with the same direction angle and different distances under the premise of mutual non-interference, thus realizing the secure communication of large-scale multicast users.