ABSTRACT Real‐time semantic segmentation is crucial for applications including autonomous driving and augmented reality. While current real‐time semantic segmentation methods achieve a balance between accuracy and speed, an adequate capture of boundary details remains a challenge for many models. Furthermore, as deep learning networks become increasingly complex, certain approaches encounter challenges, including excessive computational overhead and numerous parameters when capturing multi‐scale contextual features. To address these limitations, the boundary‐focused and multi‐scale context fusion network (BFMSNet) is proposed, a lightweight real‐time semantic segmentation model that enhances boundary perception and contextual understanding. A boundary refinement module is designed, which utilizes multi‐level feature fusion and a gating mechanism to precisely capture edge details in complex scenes and achieve pixel‐level boundary alignment and optimization. Furthermore, a hybrid boundary loss is introduced, combining region and boundary supervision signals to effectively guide the network's focus on challenging regions, thereby improving training stability and segmentation accuracy. To reduce model complexity, a lightweight multi‐scale fusion module is implemented based on the multi‐scale frequency‐domain characteristics of wavelet convolution. This module balances context information extraction and computational efficiency, reducing parameters while maintaining feature representation. Experimental results on the Cityscapes and CamVid datasets demonstrate that BFMSNet achieves mIoU of 78.53% and 76.24%, while maintaining real‐time inference speeds of 86.25 FPS and 143.70 FPS, respectively. Preliminary tests indicate that the BFMSNet algorithm effectively balances accuracy and speed requirements.

ABSTRACT The existing image dehazing algorithms perform suboptimal in non‐homogeneous and/or dense haze scenarios. The loss of feature information and alteration of color distribution cause images to deviate from real‐world scenes when haze suppresses image details. To address these issues, we design a dual‐branch non‐homogeneous dehazing network integrating discrete wavelet transform (DWT), multi‐scale feature fusion, and color constraints to achieve dehazed images with more realistic edges, textures, and colors. Specifically, we first introduce DWT into a multi‐scale encoder–decoder network structure to capture more details and edge information. Then, a feature supplement and enhancement module (FSEM) combining features from hazy images at different scales and features from the previous stage is devised to enhance the multi‐scale feature capture capability of rich textures in complex scenes. Finally, we propose a pixel‐wise color consistency loss that combines pixel similarity and angular difference to constrain the dehazed images to closely match the color distribution of clear images. Experimental results indicate that the proposed dehazing network outperforms the state‐of‐the‐art non‐homogeneous dehazing methods on relevant public benchmarks and has more realistic edges, textures, and colors.

In the field of semantic segmentation, the limited receptive field of convolutional neural networks leads to insufficient extraction of global features, thereby affecting the accuracy of network segmentation. To address this issue, a Hierarchical Hybrid Encoder Network (HHEnet) based on Transformers is proposed for semantic segmentation. Firstly, to solve the problem of limited global feature information caused by the network’s limited receptive field, a Hierarchical Hybrid Encoder (HHE) is introduced, which consists of a Hierarchical Convolutional Encoder (HCE) and a Hierarchical Transformer Encoder (HTE). The encoder combines the advantages of convolution and transformers, allowing for effective extraction of both shallow and deep features. In order to further enhance spatial and global semantic information, the Feature Enhancement Module (FEM) was introduced, which consisted of two feature enhancement modules: spatial feature enhancement module (SEM) and global feature enhancement module (GEM), which enhanced spatial detail information and global semantic information respectively. Thus the accuracy of semantic segmentation can be improved. Finally, to alleviate the discrepancy between the features of the convolutional encoder and the transformer encoder, a Feature Guidance Module (FGM) is introduced. Experimental results conducted on Cityscapes, ADE20K and PASCAL VOC2012 datasets achieved mIoU scores of up to 81.9%, 49.4% and 79.1%, respectively. Compared to state-of-the-art networks, the research results confirm the higher segmentation accuracy of the proposed HHEnet in this study.