Clear underwater images serve to explore and measure ocean resources. However, underwater images suffer from color deviations and hazy effects due to wavelength-dependent light attenuation and scattering. To address this problem, we propose a multi-scale dual-color space underwater image enhancement network (MSDC-Net) comprising a color correction block and a deep learning-based network. Concretely, the color correction block compensates for the most absorbed color and limits the least one. First, the color histogram distributions of all channels are shifted to a similar range, which smoothes and generalizes color deviations to a certain extent. Second, the corrected multi-scale images are fed into a deep learning-based asymmetric multi-scale encoder-decoder architecture, which works in RGB and HSV color spaces to extract rich and varied features. Then, the extracted features are integrated through the selective kernel concatenation (SKC) module. Finally, the decoder produces competitive outputs from the integrated features. Extensive experiments on real-world and synthetic underwater images demonstrate that the proposed MSDC-Net achieves outstanding results in subjective visual comparisons and objective metrics.

This study presents an improved weed detection model, ADL-YOLOv8, designed to enhance detection accuracy for small targets while achieving model lightweighting. It addresses the challenge of attaining both high accuracy and low memory usage in current intelligent weeding equipment. By overcoming this issue, the research not only reduces the hardware costs of automated impurity removal equipment but also enhances software recognition accuracy, contributing to reduced pesticide use and the promotion of sustainable agriculture. The ADL-YOLOv8 model incorporates a lighter AKConv network for better processing of specific features, an ultra-lightweight DySample upsampling module to improve accuracy and efficiency, and the LSKA-Attention mechanism for enhanced detection, particularly of small targets. On the same dataset, ADL-YOLOv8 demonstrated a 2.2% increase in precision, a 2.45% rise in recall, a 3.07% boost in mAP@0.5, and a 1.9% enhancement in mAP@0.95. The model’s size was cut by 15.77%, and its computational complexity was reduced by 10.98%. These findings indicate that ADL-YOLOv8 not only exceeds the original YOLOv8n model but also surpasses the newer YOLOv9t and YOLOv10n in overall performance. The improved algorithm model makes the hardware cost required for embedded terminals lower.

Unsupervised Domain Adaptation (UDA) mitigates the domain shift between the source and target domains. Some conventional methods are based on guiding semantic segmentation across domains using depth information. Nevertheless, these methods are constrained and inadequate for the use of depth knowledge. In this work, we propose a Depth-aware Adaptation Framework (DAF) and an Intra-domain Adaptation (IDA) strategy to improve semantic segmentation in the context of UDA. We design a novel depth estimation network based on the channel-wise attention mechanism to provide additional depth information. In our approach, DAF aims to adapt domains by exploiting the inherent correlations of semantic and depth information, where we construct a depth-aware space for the alignment between source and target domains. Furthermore, IDA bridges the gap within the target domain through a proposed depth-aware ranking strategy. This strategy is based on dividing the target domain into a sub-source domain and a sub-target domain. The distribution discrepancies between these domains are then aligned. Extensive experiments on SYNTHIA→Cityscapes and SYNTHIA→Mapillary cross-domain tasks confirm that our method overperforms the conventional depth guidance methods with mean IOU values of 46.7% and 73.3% on the above two tasks, respectively.