Fishing with artificial light has become one of the most advanced,efficient,and common methods for the night-time purse seining in Vietnam.This study evaluated the radiation spectrum,CIE chromaticity coordinates,corre...Fishing with artificial light has become one of the most advanced,efficient,and common methods for the night-time purse seining in Vietnam.This study evaluated the radiation spectrum,CIE chromaticity coordinates,correlated color temperature(CCT),catch rate,fuel consumption,and CO_(2)emissions when using Light emitting diode(LED)lamps(0.196 kW)in comparison with the use of metal halide(MH)lights(1 kW)in the offshore purse seine fishery in Quang Tri province,Vietnam.The fishing efficiency of the purse seine fishing boats using LED lamps has increased 1.58 times in catch rate than MH lights,although the energy consumption of LED lamp is 4 times smaller.Fuel consumption of boats per trip using LED lamps was one third of that using MH lights.The use of LED reduced the radiation spectrum,especially the intense UV radiation which negatively affects the health of fishermen.This study also showed the potential of CO_(2)emission reduction up to 1.09 tons of CO_(2)per trip per boat from the use of LED lamps in the offshore purse seine fishing boats.展开更多
针对目前基于深度学习的OCC(Optical Camera Communication)系统目标LED(Light Emitting Diode)阵列检测算法网络结构复杂、参数量大、计算复杂度高的问题,提出了一种基于Effeps-YOLOv11(Effeps-You Only Look Onceversion 11)的LED阵...针对目前基于深度学习的OCC(Optical Camera Communication)系统目标LED(Light Emitting Diode)阵列检测算法网络结构复杂、参数量大、计算复杂度高的问题,提出了一种基于Effeps-YOLOv11(Effeps-You Only Look Onceversion 11)的LED阵列检测算法。在Effeps-YOLOv11特征提取的主干网中采用轻量型EfficientNetV2网络平衡网络宽度、深度、图像分辨率;使用ECA(Efficient Channel Attention)注意力机制替换原有的复杂注意力模块,简化了网络结构;设计使用轻量级C3PC(C3 Part Convolution)模块,降低计算复杂度;采用Shape_IoU损失函数提高边界框的定位精度,提升LED阵列的定位准确性,为正确解码提供了先期保障。依托OCC系统实验平台实现数据的采集,建立完成训练所需数据集。实验结果表明,在室外复杂环境下该Effeps-YOLOv11算法能满足OCC系统目标LED阵列检测任务需求。展开更多
基金funded by the Hue University DHH 2019-02-109 grant for the project:“Study on the applied LED lamps in offshore seine fishery in Quang Trịprovince”from Hue University,Hue city,Vietnam.
文摘Fishing with artificial light has become one of the most advanced,efficient,and common methods for the night-time purse seining in Vietnam.This study evaluated the radiation spectrum,CIE chromaticity coordinates,correlated color temperature(CCT),catch rate,fuel consumption,and CO_(2)emissions when using Light emitting diode(LED)lamps(0.196 kW)in comparison with the use of metal halide(MH)lights(1 kW)in the offshore purse seine fishery in Quang Tri province,Vietnam.The fishing efficiency of the purse seine fishing boats using LED lamps has increased 1.58 times in catch rate than MH lights,although the energy consumption of LED lamp is 4 times smaller.Fuel consumption of boats per trip using LED lamps was one third of that using MH lights.The use of LED reduced the radiation spectrum,especially the intense UV radiation which negatively affects the health of fishermen.This study also showed the potential of CO_(2)emission reduction up to 1.09 tons of CO_(2)per trip per boat from the use of LED lamps in the offshore purse seine fishing boats.
文摘针对目前基于深度学习的OCC(Optical Camera Communication)系统目标LED(Light Emitting Diode)阵列检测算法网络结构复杂、参数量大、计算复杂度高的问题,提出了一种基于Effeps-YOLOv11(Effeps-You Only Look Onceversion 11)的LED阵列检测算法。在Effeps-YOLOv11特征提取的主干网中采用轻量型EfficientNetV2网络平衡网络宽度、深度、图像分辨率;使用ECA(Efficient Channel Attention)注意力机制替换原有的复杂注意力模块,简化了网络结构;设计使用轻量级C3PC(C3 Part Convolution)模块,降低计算复杂度;采用Shape_IoU损失函数提高边界框的定位精度,提升LED阵列的定位准确性,为正确解码提供了先期保障。依托OCC系统实验平台实现数据的采集,建立完成训练所需数据集。实验结果表明,在室外复杂环境下该Effeps-YOLOv11算法能满足OCC系统目标LED阵列检测任务需求。
