In recent years, researches of disseminating wireless network have been conducted for areas without network infrastructure such as disaster situation or military disputes. However, conventional method was to provide a...In recent years, researches of disseminating wireless network have been conducted for areas without network infrastructure such as disaster situation or military disputes. However, conventional method was to provide a communication infrastructure by floating large aircraft as UAV or hot-air balloon in the high air. Therefore, it was difficult to utilize previous method because it requires a lot of time and cost. But it is possible to save money and time by using a drone which is already used in many areas as a small UAV. In this paper, we design a drone that can provide wireless infrastructure using high speed Wi-Fi. After reaching the target area, the drone can provide Wi-Fi using wireless mesh network and transmit the situation of local area through attached camera. And the transmitted videos can be monitored in the control center or cell phone through application in real time. The proposed scheme provides wireless communication of up to 160 Mbps in a coverage of about 200 m and video transmission with a coverage of about 120 m, respectively.展开更多
Recent advances in diagnostics have made image analysis one of the main areas of research and development. Selecting and calculating these characteristics of a disease is a difficult task. Among deep learning techniqu...Recent advances in diagnostics have made image analysis one of the main areas of research and development. Selecting and calculating these characteristics of a disease is a difficult task. Among deep learning techniques, deep convolutional neural networks are actively used for image analysis. This includes areas of application such as segmentation, anomaly detection, disease classification, computer-aided diagnosis. The objective which we aim in this article is to extract information in an effective way for a better diagnosis of the plants attending the disease of “swollen shoot”.展开更多
文摘In recent years, researches of disseminating wireless network have been conducted for areas without network infrastructure such as disaster situation or military disputes. However, conventional method was to provide a communication infrastructure by floating large aircraft as UAV or hot-air balloon in the high air. Therefore, it was difficult to utilize previous method because it requires a lot of time and cost. But it is possible to save money and time by using a drone which is already used in many areas as a small UAV. In this paper, we design a drone that can provide wireless infrastructure using high speed Wi-Fi. After reaching the target area, the drone can provide Wi-Fi using wireless mesh network and transmit the situation of local area through attached camera. And the transmitted videos can be monitored in the control center or cell phone through application in real time. The proposed scheme provides wireless communication of up to 160 Mbps in a coverage of about 200 m and video transmission with a coverage of about 120 m, respectively.
文摘Recent advances in diagnostics have made image analysis one of the main areas of research and development. Selecting and calculating these characteristics of a disease is a difficult task. Among deep learning techniques, deep convolutional neural networks are actively used for image analysis. This includes areas of application such as segmentation, anomaly detection, disease classification, computer-aided diagnosis. The objective which we aim in this article is to extract information in an effective way for a better diagnosis of the plants attending the disease of “swollen shoot”.
文摘为了提高牛场无人机目标跟踪算法的实时性和鲁棒性,试验以无人机跟踪牛只图像为研究对象,提出了一种基于残差累积模板的轻型孪生网络(siamese tracker with residual accumulation template, SiamRAT)目标跟踪算法,即采用轻量级卷积网络MobileNetV2为特征提取网络及以锚框比率变化为契机的模板更新机制,提高了算法的实时性;采用高置信度残差累积模板和多峰欧式距离检测模块来解决因相似牛只干扰而产生的跟踪漂移问题;最后将SiamRAT算法与SiamRPN++、SiamDW、DaSiamRPN、SiamRPN、ECO-HC算法在由无人机采集牧场牛只视频制作的测试数据集和VOT2018数据集中相同属性视频构成的测试数据集上,以平均精确度、鲁棒性及帧率(frames per second, FPS)为指标进行性能比较,并分析改进模块(包括残差累积模板、高置信度更新和峰值距离检测3个模块的改进)对SiamRAT算法的贡献。结果表明:与SiamRPN++、SiamDW、DaSiamRPN、SiamRPN、ECO-HC算法相比,SiamRAT算法鲁棒性最优,平均精确度稍有下降,但仍处于所有算法的第二位;FPS较SiamRPN++算法有了较大提升,性能较优。改进模块的SiamRAT算法的鲁棒性和FPS有了较大提升,平均精确度达到了0.909。说明SiamRAT算法能够很好地适应于牛场无人机跟踪环境。
