Deep Learning-Based Fish Detection Using Above-Water Infrared Camera for Deep-Sea Aquaculture: A Comparison Study.

Long-term, automated fish detection provides invaluable data for deep-sea aquaculture, which is crucial for safe and efficient seawater aquafarming. In this paper, we used an infrared camera installed on a deep-sea truss-structure net cage to collect fish images, which were subsequently labeled to establish a fish dataset. Comparison experiments with our dataset based on Faster R-CNN as the basic objection detection framework were conducted to explore how different backbone networks and network improvement modules influenced fish detection performances. Furthermore, we also experimented with the effects of different learning rates, feature extraction layers, and data augmentation strategies. Our results showed that Faster R-CNN with the EfficientNetB0 backbone and FPN module was the most competitive fish detection network for our dataset, since it took a significantly shorter detection time while maintaining a high AP50 value of 0.85, compared to the best AP50 value of 0.86 being achieved by the combination of VGG16 with all improvement modules plus data augmentation. Overall, this work has verified the effectiveness of deep learning-based object detection methods and provided insights into subsequent network improvements.

Effect of Fly Ash on Leaching Characteristics of Cement-Stabilized Macadam Base.

To study the leaching characteristics of a cement-stabilized macadam base with fly ash, a calcium leaching test, using varying cement and fly ash dosages in an ammonium chloride solution, was designed to obtain the rate of calcium ion leaching, porosity, and permeability coefficient of cement-stabilized macadam with leaching time. The results showed that the number of leached calcium ions increased with the cement dosage in the leaching of cement-stabilized macadam. With an increase in the cement dosage, the leaching rate of calcium ions decreased, and the leaching process of the material was delayed. The incorporation of fly ash could effectively slow down the degree of calcium ion leaching. The permeability coefficient increased gradually with the extension of leaching time, and the increase in fly ash content had a more significant effect on the improvement of the permeability coefficient than the increase in cement dosage did.