Lightweight marine biological target detection algorithm based on YOLOv5

Abstract

Underwater object detection currently faces many challenges, such as the large number of parameters in existing object detection models, slow inference speed, blurring of underwater images, and aggregation of small targets, making it difficult to conduct efficient underwater object detection. This paper proposes a lightweight underwater object detection algorithm based on YOLOv5.The method uses depth-wise separable convolution instead of ordinary convolution to reduce the number of parameters and computational complexity. A C3 module based on Ghost convolution is designed to further compress the model size and improve the computational speed. In the feature extraction stage, a RepVgg module based on structural reparameterization is used to convert the multi -branch structure into a single-branch structure in the inference stage, improving the feature extraction ability of the model and increasing the inference speed. A Rep-ECA module is designed to embed the efficient channel attention module ECANet into the RepVGG module, selecting more effective channel information and improving the model’s feature extraction ability for small objects in blurred images, thereby improving detection precision. Experimental results show that in the URPC underwater object detection dataset, the proposed algorithm has a 39% lower model parameter count compared to the original model, a 42% reduction in computational complexity. The model can achieve a frame rate of 85 on a single Nvidia GTX 1080ti GPU, which is a 24% improvement over the original model, while mAP reaches 85.1%, a 1.1% improvement over the original model. The algorithm can improve the detection precision and achieve lightweight, which lays a foundation for the deployment of underwater equipment.

Utilizing Deep Neural Networks for Chrysanthemum Leaf and Flower Feature Recognition

“…ANN [34] 89.8% 89.3% 93.5% PVT [35] 87.5% 85.2% 89.6% EfficientNet v2 [36] 90.5% 91.4% 92.3% GoogLeNet [37] 91.4% 92.6% 92.2% RepVGG [38,39] 90.3% 94.5% 91.8% SVM [1] 92.1% 94.2% 93.5% MLP [10] 93.9% 95.3% 94.5%…”

Red Blood Cell-Derived Exosomal Oncogenic MicroRNA Promote Cancer Development and Progression

“…Red blood cells (RBCs), conventionally recognized for their essential role in oxygen transport and regulation of the body's metabolic demands. However, RBCs have recently been uncovered to play multifaceted roles beyond their conventional functions, including engaging in phagocytosis, antimicrobial defense, antigen recognition, and immune adherence (1,2). Furthermore, an association between RBC and cancer has been observed (2).…”

“…Hypoxia within tumors, a condition caused by inadequate oxygen supply by RBCs, can lead to the selection of more aggressive cancer cell phenotypes, and increase resistance to chemotherapy and radiation therapy (5). Liang et al recently demonstrated that mature RBCs can acquire DNA from lung cancer tissues, and the acquired mutated DNA could be used for early cancer detection (1). However, the contribution of RBCs to tumorigenesis and the mechanisms behind this remain unclear.…”

Yangtze finless porpoise sexual behavior object detection algorithm based on YOLOv8

“…However, due to the unclear visibility of fish in some images and the presence of considerable background noise, the detection accuracy remains relatively low. [7,13,17]. These methods are all limited facing the issue of target overlap、blur in images and other background noise.…”