High performance hardware architecture for depth measurement by using binocular-camera is proposed.In the system,at first,video streams of the target are captured by left and right charge-coupled device(CCD)cameras to...High performance hardware architecture for depth measurement by using binocular-camera is proposed.In the system,at first,video streams of the target are captured by left and right charge-coupled device(CCD)cameras to obtain an image including the target.Then,two different images with two different view points are obtained,and they are used in calculating the position deviation of the image's pixels based on triangular measurement.Finally,the three-dimensional coordinate of the object is reconstructed.All the video data is processed by using field-programmable gate array(FPGA)in real-time.Hardware implementation speeds up the performance and reduces the power,thus,this hardware architecture can be applied in the portable environment.展开更多
传统松科球果采摘面临效率低、风险高和成本不可控等挑战,针对自动化松科球果采摘对果实的实时识别与定位问题,提出改进的YOLOv5s-7.0(You Only Look Once)目标检测模型,基于此模型,构建基于双目深度相机的松科球果检测与定位网络。为...传统松科球果采摘面临效率低、风险高和成本不可控等挑战,针对自动化松科球果采摘对果实的实时识别与定位问题,提出改进的YOLOv5s-7.0(You Only Look Once)目标检测模型,基于此模型,构建基于双目深度相机的松科球果检测与定位网络。为提高目标检测精度及效率,对YOLOv5s模型进行改进,将部分卷积PConv嵌入到模型的颈部网络neck多分枝堆叠结构中,面对松科球果的复杂场景增强对稀疏特征的处理能力,提升鲁棒性,减轻特征信息的冗余。在骨干网络backbone的深层及backbone与neck的连接处嵌入简单注意力机制SimAM,在不引入过多参数的基础上优化模型复杂背景下特征提取能力和信息传递的有效性。为满足高效率检测定位,基于双目深度相机测距原理和改进的YOLOv5s模型搭建目标检测及实时定位代码,通过深度匹配,构建松科球果检测与定位系统。根据构建的大兴安岭樟子松球果与小兴安岭红松球果数据集,改进后YOLOv5s模型目标检测精确率达96.8%,召回率和平均精度分别达94%、96.3%,松科球果检测与定位系统在x轴、y轴、z轴的平均绝对误差分别为0.644、0.620、0.740 cm,顺、侧、逆光照下定位试验成功率93.3%,暗光下定位成功率83.3%,视场角等其他性能符合松科球果采摘需求。研究提出的松科球果检测与定位系统为机械化采摘的实时目标检测与定位问题提供可靠的解决方案。展开更多
文摘High performance hardware architecture for depth measurement by using binocular-camera is proposed.In the system,at first,video streams of the target are captured by left and right charge-coupled device(CCD)cameras to obtain an image including the target.Then,two different images with two different view points are obtained,and they are used in calculating the position deviation of the image's pixels based on triangular measurement.Finally,the three-dimensional coordinate of the object is reconstructed.All the video data is processed by using field-programmable gate array(FPGA)in real-time.Hardware implementation speeds up the performance and reduces the power,thus,this hardware architecture can be applied in the portable environment.
文摘传统松科球果采摘面临效率低、风险高和成本不可控等挑战,针对自动化松科球果采摘对果实的实时识别与定位问题,提出改进的YOLOv5s-7.0(You Only Look Once)目标检测模型,基于此模型,构建基于双目深度相机的松科球果检测与定位网络。为提高目标检测精度及效率,对YOLOv5s模型进行改进,将部分卷积PConv嵌入到模型的颈部网络neck多分枝堆叠结构中,面对松科球果的复杂场景增强对稀疏特征的处理能力,提升鲁棒性,减轻特征信息的冗余。在骨干网络backbone的深层及backbone与neck的连接处嵌入简单注意力机制SimAM,在不引入过多参数的基础上优化模型复杂背景下特征提取能力和信息传递的有效性。为满足高效率检测定位,基于双目深度相机测距原理和改进的YOLOv5s模型搭建目标检测及实时定位代码,通过深度匹配,构建松科球果检测与定位系统。根据构建的大兴安岭樟子松球果与小兴安岭红松球果数据集,改进后YOLOv5s模型目标检测精确率达96.8%,召回率和平均精度分别达94%、96.3%,松科球果检测与定位系统在x轴、y轴、z轴的平均绝对误差分别为0.644、0.620、0.740 cm,顺、侧、逆光照下定位试验成功率93.3%,暗光下定位成功率83.3%,视场角等其他性能符合松科球果采摘需求。研究提出的松科球果检测与定位系统为机械化采摘的实时目标检测与定位问题提供可靠的解决方案。
