This paper discusses the design and implementation of a low cost multi-sensor integrated attitude determination system for small unmanned aerial vehicles( UAVs),which uses strapdown inertial navigation system( SINS) b...This paper discusses the design and implementation of a low cost multi-sensor integrated attitude determination system for small unmanned aerial vehicles( UAVs),which uses strapdown inertial navigation system( SINS) based on micro electromechanical system( MEMS) inertial sensors,commercial GPS receiver,and 3-axis magnetometer.MEMS-SINS initial attitude determination cannot be well performed for the reason that the MEMS inertial sensors biases are time-varying and poor repeatability,therefore in this paper the magnetometer and inclinometer are used to assist the MEMS-SINS initial attitude determination and MEMS inertial sensors field calibration.Furthermore,the attitude determination algorithms are presented to estimate the full attitude during GPS signal outage and non-accelerating situation.Additionally,the attitude information estimation results are compared with the reference of the non-magnetic marble platform and 3-axis turntable.Then the attitude estimation precision satisfies the requirement of attitude measurement for small UAVs during GPS signal outage and availability.Finally,the small UAV autonomous flight test results show that the low cost and real-time attitude determination system can yield continuous,reliable and effective attitude information for small UAVs.展开更多
A gradient descent algorithm with adjustable parameter for attitude estimation is developed,aiming at the attitude measurement for small unmanned aerial vehicle(UAV)in real-time flight conditions.The accelerometer and...A gradient descent algorithm with adjustable parameter for attitude estimation is developed,aiming at the attitude measurement for small unmanned aerial vehicle(UAV)in real-time flight conditions.The accelerometer and magnetometer are introduced to construct an error equation with the gyros,thus the drifting characteristics of gyroscope can be compensated by solving the error equation utilized by the gradient descent algorithm.Performance of the presented algorithm is evaluated using a self-proposed micro-electro-mechanical system(MEMS)based attitude heading reference system which is mounted on a tri-axis turntable.The on-ground,turntable and flight experiments indicate that the estimation attitude has a good accuracy.Also,the presented system is compared with an open-source flight control system which runs extended Kalman filter(EKF),and the results show that the attitude control system using the gradient descent method can estimate the attitudes for UAV effectively.展开更多
无人机高空航拍图像中车辆像素占比极低,目标可视化信息较少,在目标检测任务中容易漏检和误检。因此,本文提出一种基于改进YOLOX(You Only Look Once X)的无人机高空航拍视角下小尺度车辆精确检测方法。首先,为增强网络对低级特征的提...无人机高空航拍图像中车辆像素占比极低,目标可视化信息较少,在目标检测任务中容易漏检和误检。因此,本文提出一种基于改进YOLOX(You Only Look Once X)的无人机高空航拍视角下小尺度车辆精确检测方法。首先,为增强网络对低级特征的提取能力,在原始YOLOX预测头部增加一个160 pixel×160 pixel的浅层特征提取网络;其次,在骨干网络后端嵌入基于归一化的注意力机制模块(Normalization-based Attention Module,NAM),以抑制冗余的非显著特征表达;最后,为了增大小尺度车辆的相对像素比,提升网络捕捉有效特征信息的能力,提出一种基于滑动窗口的图像切分检测方法。试验结果表明,改进YOLOX网络表现出良好的检测效能,检测精度达到了84.58%,优于典型的目标检测网络Faster R-CNN(79.95%)、YOLOv3(83.69%)、YOLOv5(84.31%)及YOLOX(83.10%)。此外,改进YOLOX能够有效解决无人机高空航拍图像中小尺度车辆的漏检和误检问题,且预测框更贴合车辆的实际轮廓;同时,在不同航拍高度的目标检测任务中具有较高的鲁棒性。展开更多
从无人机视角进行目标检测,面临图像目标小、分布密集、类别不均衡等难点,且由于无人机的硬件条件限制了模型的规模,导致模型的准确率偏低。提出一种融合多种注意力机制的YOLOv8s改进模型,在骨干网络中引入感受野注意力卷积和CBAM(conce...从无人机视角进行目标检测,面临图像目标小、分布密集、类别不均衡等难点,且由于无人机的硬件条件限制了模型的规模,导致模型的准确率偏低。提出一种融合多种注意力机制的YOLOv8s改进模型,在骨干网络中引入感受野注意力卷积和CBAM(concentration-based attention module)注意力机制改进卷积模块,解决注意力权重参数在感受野特征中共享问题的同时,在通道和空间维度加上注意力权重,增强特征提取能力;通过引入大型可分离卷积注意力思想,改造空间金字塔池化层,增加不同层级特征间的信息交融;优化颈部结构,增加具有丰富小目标语义信息的特征层;使用inner-IoU损失函数的思想改进MPDIoU(minimum point distance based IoU)函数,以innerMPDIoU代替原损失函数,提升对困难样本的学习能力。实验结果表明,改进后的YOLOv8s模型在VisDrone数据集上mAP、P、R分别提升了16.1%、9.3%、14.9%,性能超过YOLOv8m,可以有效应用于无人机平台上的目标检测任务。展开更多
针对无人机图像中由于目标微小且相互遮挡、特征信息少导致检测精度低的问题,提出一种基于改进YOLOv7的无人机图像目标检测算法。在颈部和检测头中加入了坐标卷积,能更好地感受特征图中目标的位置信息;增加P2检测层,减少小目标特征丢失...针对无人机图像中由于目标微小且相互遮挡、特征信息少导致检测精度低的问题,提出一种基于改进YOLOv7的无人机图像目标检测算法。在颈部和检测头中加入了坐标卷积,能更好地感受特征图中目标的位置信息;增加P2检测层,减少小目标特征丢失、提高小目标检测能力;提出多信息流融合注意力机制——Spatial and Channel Attention Mechanism(SCA),动态调整注意力对空间信息流和语义信息流的关注,获得更丰富的特征信息以提高捕获目标的能力;更换损失函数为SIoU,加快模型收敛速度。在公开数据集VisDrone2019上进行对比实验,改进后算法的mAP50值相比YOLOv7提高了4%,达到了52.4%,FPS为37,消融实验验证了每个模块均提升了检测精度。实验表明,改进后的算法能较好地检测无人机图像中的目标。展开更多
基金Sponsored by the China Postdoctoral Science Foundation(Grant No.2013M540857)the Fundamental Research Funds for the Central Universities(Grant No.FRF-TP-14-019A1)
文摘This paper discusses the design and implementation of a low cost multi-sensor integrated attitude determination system for small unmanned aerial vehicles( UAVs),which uses strapdown inertial navigation system( SINS) based on micro electromechanical system( MEMS) inertial sensors,commercial GPS receiver,and 3-axis magnetometer.MEMS-SINS initial attitude determination cannot be well performed for the reason that the MEMS inertial sensors biases are time-varying and poor repeatability,therefore in this paper the magnetometer and inclinometer are used to assist the MEMS-SINS initial attitude determination and MEMS inertial sensors field calibration.Furthermore,the attitude determination algorithms are presented to estimate the full attitude during GPS signal outage and non-accelerating situation.Additionally,the attitude information estimation results are compared with the reference of the non-magnetic marble platform and 3-axis turntable.Then the attitude estimation precision satisfies the requirement of attitude measurement for small UAVs during GPS signal outage and availability.Finally,the small UAV autonomous flight test results show that the low cost and real-time attitude determination system can yield continuous,reliable and effective attitude information for small UAVs.
基金supported by the Fundamental Research Funds for the Central Universities(No.56XAA17075)
文摘A gradient descent algorithm with adjustable parameter for attitude estimation is developed,aiming at the attitude measurement for small unmanned aerial vehicle(UAV)in real-time flight conditions.The accelerometer and magnetometer are introduced to construct an error equation with the gyros,thus the drifting characteristics of gyroscope can be compensated by solving the error equation utilized by the gradient descent algorithm.Performance of the presented algorithm is evaluated using a self-proposed micro-electro-mechanical system(MEMS)based attitude heading reference system which is mounted on a tri-axis turntable.The on-ground,turntable and flight experiments indicate that the estimation attitude has a good accuracy.Also,the presented system is compared with an open-source flight control system which runs extended Kalman filter(EKF),and the results show that the attitude control system using the gradient descent method can estimate the attitudes for UAV effectively.
文摘无人机高空航拍图像中车辆像素占比极低,目标可视化信息较少,在目标检测任务中容易漏检和误检。因此,本文提出一种基于改进YOLOX(You Only Look Once X)的无人机高空航拍视角下小尺度车辆精确检测方法。首先,为增强网络对低级特征的提取能力,在原始YOLOX预测头部增加一个160 pixel×160 pixel的浅层特征提取网络;其次,在骨干网络后端嵌入基于归一化的注意力机制模块(Normalization-based Attention Module,NAM),以抑制冗余的非显著特征表达;最后,为了增大小尺度车辆的相对像素比,提升网络捕捉有效特征信息的能力,提出一种基于滑动窗口的图像切分检测方法。试验结果表明,改进YOLOX网络表现出良好的检测效能,检测精度达到了84.58%,优于典型的目标检测网络Faster R-CNN(79.95%)、YOLOv3(83.69%)、YOLOv5(84.31%)及YOLOX(83.10%)。此外,改进YOLOX能够有效解决无人机高空航拍图像中小尺度车辆的漏检和误检问题,且预测框更贴合车辆的实际轮廓;同时,在不同航拍高度的目标检测任务中具有较高的鲁棒性。
文摘从无人机视角进行目标检测,面临图像目标小、分布密集、类别不均衡等难点,且由于无人机的硬件条件限制了模型的规模,导致模型的准确率偏低。提出一种融合多种注意力机制的YOLOv8s改进模型,在骨干网络中引入感受野注意力卷积和CBAM(concentration-based attention module)注意力机制改进卷积模块,解决注意力权重参数在感受野特征中共享问题的同时,在通道和空间维度加上注意力权重,增强特征提取能力;通过引入大型可分离卷积注意力思想,改造空间金字塔池化层,增加不同层级特征间的信息交融;优化颈部结构,增加具有丰富小目标语义信息的特征层;使用inner-IoU损失函数的思想改进MPDIoU(minimum point distance based IoU)函数,以innerMPDIoU代替原损失函数,提升对困难样本的学习能力。实验结果表明,改进后的YOLOv8s模型在VisDrone数据集上mAP、P、R分别提升了16.1%、9.3%、14.9%,性能超过YOLOv8m,可以有效应用于无人机平台上的目标检测任务。
文摘针对无人机图像中由于目标微小且相互遮挡、特征信息少导致检测精度低的问题,提出一种基于改进YOLOv7的无人机图像目标检测算法。在颈部和检测头中加入了坐标卷积,能更好地感受特征图中目标的位置信息;增加P2检测层,减少小目标特征丢失、提高小目标检测能力;提出多信息流融合注意力机制——Spatial and Channel Attention Mechanism(SCA),动态调整注意力对空间信息流和语义信息流的关注,获得更丰富的特征信息以提高捕获目标的能力;更换损失函数为SIoU,加快模型收敛速度。在公开数据集VisDrone2019上进行对比实验,改进后算法的mAP50值相比YOLOv7提高了4%,达到了52.4%,FPS为37,消融实验验证了每个模块均提升了检测精度。实验表明,改进后的算法能较好地检测无人机图像中的目标。
