为了提升汽车辅助驾驶系统对前方车辆的检测效果,进一步获取精确的距离信息,本文提出一种改进的YOLOv5s的目标车辆检测算法,并用双目对前方车辆进行测距。以YOLOv5s(you only look once v5s, YOLOv5s)检测网络为基础,首先在网络中引入...为了提升汽车辅助驾驶系统对前方车辆的检测效果,进一步获取精确的距离信息,本文提出一种改进的YOLOv5s的目标车辆检测算法,并用双目对前方车辆进行测距。以YOLOv5s(you only look once v5s, YOLOv5s)检测网络为基础,首先在网络中引入卷积注意力模块(convolutional block attention module, CBAM)有效提取检测目标的轮廓特征;其次将Neck中PANet网络替换为BiFPN提升特征的融合能力,使用DIoU优化损失函数,增强对车辆检测的准确性;采用SURF算法进行立体匹配,并对特征匹配点进行约束获得最优视差值,最后通过双目视觉测距原理求得前车距离信息。测试表明,在20 m的距离范围内,车辆识别率准确率为92.1%,提升了1.54%,测距平均误差率为2.75%。展开更多
The stationary Gamma-OU processes are recommended to be the volatility of the financial assets. A parametric estimation for the Gamma-OU processes based on the discrete observations is considered in this paper. The es...The stationary Gamma-OU processes are recommended to be the volatility of the financial assets. A parametric estimation for the Gamma-OU processes based on the discrete observations is considered in this paper. The estimator of an intensity parameter A and its convergence result are given, and the simulations show that the estimation is quite accurate. Assuming that the parameter A is estimated, the maximum likelihood estimation of shape parameter c and scale parameter a, whose likelihood function is not explicitly computable, is considered. By means of the Gaver-Stehfest algorithm, we construct an explicit sequence of approximations to the likelihood function and show that it converges the true (but unkown) one. Maximizing the sequence results in an estimator that converges to the true maximum likelihood estimator and the approximation shares the asymptotic properties of the true maximum likelihood estimator. Some simulation experiments reveal that this method is still quite accurate in most of rational situations for the background of volatility.展开更多
快速识别和精准定位周围目标是自动驾驶车辆安全、自主行驶的前提和基础。针对基于体素的点云三维目标检测方法识别与定位不准的问题,提出一种基于改进SECOND算法的点云三维目标检测算法。首先,在二维卷积骨干网络中引入自适应的空间特...快速识别和精准定位周围目标是自动驾驶车辆安全、自主行驶的前提和基础。针对基于体素的点云三维目标检测方法识别与定位不准的问题,提出一种基于改进SECOND算法的点云三维目标检测算法。首先,在二维卷积骨干网络中引入自适应的空间特征融合模块融合不同尺度的空间特征,提高模型的特征表达能力。其次,充分利用边界框参数之间的关联性,采用three-dimensional distance-intersection over union (3D DIoU)损失作为边界框的定位回归损失函数,使得回归任务更加高效。最后,同时考虑候选框的分类置信度和定位精度,通过一个新的候选框质量评价标准,获得更平滑的回归结果。在KITTI测试集的实验结果表明,所提算法的3D检测精度优于许多以往的算法,与基准算法SECOND相比,在简单难度下的car类和cyclist类分别提高2.86百分点和3.84百分点,中等难度下分别提高2.99百分点和3.89百分点,困难难度下分别提高7.06百分点和4.27个百分点。展开更多
基金This work was supported by National Natural Science Foundation of China (Grant No. 10371074).
文摘The stationary Gamma-OU processes are recommended to be the volatility of the financial assets. A parametric estimation for the Gamma-OU processes based on the discrete observations is considered in this paper. The estimator of an intensity parameter A and its convergence result are given, and the simulations show that the estimation is quite accurate. Assuming that the parameter A is estimated, the maximum likelihood estimation of shape parameter c and scale parameter a, whose likelihood function is not explicitly computable, is considered. By means of the Gaver-Stehfest algorithm, we construct an explicit sequence of approximations to the likelihood function and show that it converges the true (but unkown) one. Maximizing the sequence results in an estimator that converges to the true maximum likelihood estimator and the approximation shares the asymptotic properties of the true maximum likelihood estimator. Some simulation experiments reveal that this method is still quite accurate in most of rational situations for the background of volatility.
文摘快速识别和精准定位周围目标是自动驾驶车辆安全、自主行驶的前提和基础。针对基于体素的点云三维目标检测方法识别与定位不准的问题,提出一种基于改进SECOND算法的点云三维目标检测算法。首先,在二维卷积骨干网络中引入自适应的空间特征融合模块融合不同尺度的空间特征,提高模型的特征表达能力。其次,充分利用边界框参数之间的关联性,采用three-dimensional distance-intersection over union (3D DIoU)损失作为边界框的定位回归损失函数,使得回归任务更加高效。最后,同时考虑候选框的分类置信度和定位精度,通过一个新的候选框质量评价标准,获得更平滑的回归结果。在KITTI测试集的实验结果表明,所提算法的3D检测精度优于许多以往的算法,与基准算法SECOND相比,在简单难度下的car类和cyclist类分别提高2.86百分点和3.84百分点,中等难度下分别提高2.99百分点和3.89百分点,困难难度下分别提高7.06百分点和4.27个百分点。
