YOLOv3目标检测算法在检测目标时没有考虑边界框坐标定位存在的不确定性,因此有时不能得出正确的检测结果。针对此问题,提出YOLO-wLU(YOLO with Localization Uncertainty)算法。该算法借鉴深度学习中的不确定性思想,使用高斯分布函数...YOLOv3目标检测算法在检测目标时没有考虑边界框坐标定位存在的不确定性,因此有时不能得出正确的检测结果。针对此问题,提出YOLO-wLU(YOLO with Localization Uncertainty)算法。该算法借鉴深度学习中的不确定性思想,使用高斯分布函数建立边界框坐标的概率分布模型以考虑边界框坐标定位不确定性;设计新的边界框损失函数,在检测过程中移除定位不确定性较大的检测结果;通过融合周围边界框坐标信息提高了边界框坐标辨识结果的准确性。实验结果表明,该算法可有效减少误报率,提高检测精度;COCO数据集上测试结果显示,相比YOLOv3算法,该算法的mAP最高可提升4.1个百分点。展开更多
Clearances at joints cause an uncertainty in the actual posture of the end-effector of any mechanism. This uncertainty relays on the clearance dimension and the way these clearances are taken up by the mechanism under...Clearances at joints cause an uncertainty in the actual posture of the end-effector of any mechanism. This uncertainty relays on the clearance dimension and the way these clearances are taken up by the mechanism under the load and the inertial effects at every instant. As a matter of fact, the actual measure of the pose error is often replaced by an uncertainty measure. However, a side effect of the existence of clearances is that they can cause sudden changes in the posture of the mechanism as a motion is performed. Such discontinuities in the position produce task defects and impacts. In this work a tool to determine the pose error due to clearances is presented together with a discontinuity analysis. In addition, effects of mass distribution and inertial effects on such discontinuities are expounded, taking a 3-PRS robot as example.展开更多
The span of coordinate time series affects the determination of an optimal noise model. We analyzed position data recorded for 10 continuous Global Positioning System （GPS） sites from 1998.0 to mid-2009 on the Austr...The span of coordinate time series affects the determination of an optimal noise model. We analyzed position data recorded for 10 continuous Global Positioning System （GPS） sites from 1998.0 to mid-2009 on the Australian Plate to estimate the best noise model and thereafter obtain the true uncertainties of the velocity, employing the maximum likelihood estimation （MLE） method. MLE was employed to analyze the data in four ways. In the first two analyses, the noise was assumed to be a combination of flicker noise and white noise for the raw time series and spatially filtered time series. In the final two analyses, the spectral indices and amplitudes were simultaneously estimated for a power law noise plus white noise model for the raw time series and spatially filtered time series. We conclude that the noise model of GPS time series in Australia can be best described as the combination of flicker noise and white noise. Velocity uncertainties fall below -0.2 mm/yr when the time span exceeds -9.5 years. A comparison of noise amplitudes and maximum likelihood estimation values between the raw and spatially filtered time series suggests that traditional spatial filtering to remove common-mode errors might not be applicable to the raw time series of this region.展开更多
文摘YOLOv3目标检测算法在检测目标时没有考虑边界框坐标定位存在的不确定性,因此有时不能得出正确的检测结果。针对此问题,提出YOLO-wLU(YOLO with Localization Uncertainty)算法。该算法借鉴深度学习中的不确定性思想,使用高斯分布函数建立边界框坐标的概率分布模型以考虑边界框坐标定位不确定性;设计新的边界框损失函数,在检测过程中移除定位不确定性较大的检测结果;通过融合周围边界框坐标信息提高了边界框坐标辨识结果的准确性。实验结果表明,该算法可有效减少误报率,提高检测精度;COCO数据集上测试结果显示,相比YOLOv3算法,该算法的mAP最高可提升4.1个百分点。
文摘Clearances at joints cause an uncertainty in the actual posture of the end-effector of any mechanism. This uncertainty relays on the clearance dimension and the way these clearances are taken up by the mechanism under the load and the inertial effects at every instant. As a matter of fact, the actual measure of the pose error is often replaced by an uncertainty measure. However, a side effect of the existence of clearances is that they can cause sudden changes in the posture of the mechanism as a motion is performed. Such discontinuities in the position produce task defects and impacts. In this work a tool to determine the pose error due to clearances is presented together with a discontinuity analysis. In addition, effects of mass distribution and inertial effects on such discontinuities are expounded, taking a 3-PRS robot as example.
基金supported by the National Natural Science Foundation of China(Grant Nos.41304007,41074022)the Chinese Universities Scientific Fund(Grant No.121103)+1 种基金the Surveying and Mapping Basic Research Program of the National Administration of Surveying,Mapping and Geoinformation(Grant No.11-02-02)the China Scholarship Council and College of Science of the University of Nevada,Reno
文摘The span of coordinate time series affects the determination of an optimal noise model. We analyzed position data recorded for 10 continuous Global Positioning System （GPS） sites from 1998.0 to mid-2009 on the Australian Plate to estimate the best noise model and thereafter obtain the true uncertainties of the velocity, employing the maximum likelihood estimation （MLE） method. MLE was employed to analyze the data in four ways. In the first two analyses, the noise was assumed to be a combination of flicker noise and white noise for the raw time series and spatially filtered time series. In the final two analyses, the spectral indices and amplitudes were simultaneously estimated for a power law noise plus white noise model for the raw time series and spatially filtered time series. We conclude that the noise model of GPS time series in Australia can be best described as the combination of flicker noise and white noise. Velocity uncertainties fall below -0.2 mm/yr when the time span exceeds -9.5 years. A comparison of noise amplitudes and maximum likelihood estimation values between the raw and spatially filtered time series suggests that traditional spatial filtering to remove common-mode errors might not be applicable to the raw time series of this region.
