Underwater object detection is a challenging task with profound implications for fields such as aquaculture, marine ecological protection, and maritime rescue operations. The presence of numerous small aquatic organisms in the underwater environment often leads to issues of missed detections and false positives. Additionally, factors such as the water quality result in weak target features, which adversely affect the extraction of target feature information. Furthermore, the lack of illumination underwater causes image blur and low contrast, thereby increasing the difficulty of the detection task. To address these issues, we propose a novel underwater object detection algorithm called YOLO-GE (GCNet-EMA). First, we introduce an image enhancement module to mitigate the impact of underwater image quality issues on the detection task. Second, a high-resolution feature layer is added into the network to improve the problems of missed detections and false positives for small targets. Third, we propose GEBlock, an attention-based fusion module that captures long-range contextual information and suppresses noise from lower-level feature layers. Finally, we combine an adaptive spatial fusion module with the detection head to filter out conflicting feature information from different feature layers. Experiments on the UTDAC2020, DUO and RUOD datasets show that the proposed method achieves an optimal detection accuracy.
A low-light image enhancement method based on a deep symmetric encoder–decoder convolutional network (LLED-Net) is proposed in the paper. In surveillance and tactical reconnaissance, collecting visual information from a dynamic environment and accurately processing that data is critical to making the right decisions and ensuring mission success. However, due to the cost and technical limitations of camera sensors, it is difficult to capture clear images or videos in low-light conditions. In this paper, a special encoder–decoder convolution network is designed to utilize multi-scale feature maps and join jump connections to avoid gradient disappearance. In order to preserve the image texture as much as possible, by using structural similarity (SSIM) loss to train the model on the data sets with different brightness level, the model can adaptively enhance low-light images in low-light environments. The results show that the proposed algorithm provides significant improvements in quantitative comparison with RED-Net and several other representative image enhancement algorithms.
28 June 2018 in The International Journal of Medical Robotics and Computer Assisted Surgery
Limited by GPU memory, high-resolution image segmentation is a highly challenging task. To improve the accuracy of high-resolution segmentation, High-Resolution Refine Net (HRRNet) is proposed. The network is divided into a rough segmentation module and a refinement module. The former improves DeepLabV3+ by adding the shallow features of 1/2 original image size and the corresponding skip connection to obtain better rough segmentation results, the output of which is used as the input of the latter. In the refinement module, first, the global context information of the input image is obtained by a global process. Second, the high-resolution image is divided into patches, and each patch is processed separately to obtain local details in a local process. In both processes, multiple refine units (RU) are cascaded for refinement processing, and two cascaded residual convolutional units (RCU) are added to the different output paths of RU to improve the mIoU and the convergence speed of the network. Finally, according to the context information of the global process, the refined patches are pieced to obtain the refined segmentation result of the whole high-resolution image. In addition, the regional non-maximum suppression is introduced to improve the Sobel edge detection, and the Pascal VOC 2012 dataset is enhanced, which improves the segmentation accuracy and robust performance of the network. Compared with the state-of-the-art semantic segmentation models, the experimental results show that our model achieves the best performance in high-resolution image segmentation.