The D-S evidential reasoning algorithm is invalid when the evidence is completely contradicted. Therefore,a modified algorithm is proposed based on the elemental correlation and the influence of elemental weights in t...The D-S evidential reasoning algorithm is invalid when the evidence is completely contradicted. Therefore,a modified algorithm is proposed based on the elemental correlation and the influence of elemental weights in the evidence. The modified algorithm is more powerful ability to rectify errors and less computational complexity in the circumstance of multi-evidence fusion processing than those of the D-S evidential reasoning algorithm.展开更多
为了快速准确地检测无人驾驶方程式大赛中赛道锥桶的特征信息,提出一种融合激光雷达点云数据和相机图像数据的检测方法.首先对点云数据进行感兴趣区域(region of interest, ROI)提取并对噪点进行滤波,针对目前地面欠分割和过分割问题引...为了快速准确地检测无人驾驶方程式大赛中赛道锥桶的特征信息,提出一种融合激光雷达点云数据和相机图像数据的检测方法.首先对点云数据进行感兴趣区域(region of interest, ROI)提取并对噪点进行滤波,针对目前地面欠分割和过分割问题引入自适应地面分割算法,并采用欧式聚类对锥桶空间位置信息进行提取;其次采集和标注图像数据集,并使用YOLOv5进行训练后检测,完成锥桶颜色信息的提取;然后将激光雷达检测的锥桶空间位置信息和相机检测的锥桶颜色信息进行融合;最后设计试验进行验证,结果表明:所提出的融合检测方法能够弥补单传感器检测锥桶带来的问题,快速准确地检测出赛道中的锥桶,为规划和决策提供了保障.展开更多
Multi-laser-target tracking is an important subject in the field of signal processing of laser warners. A clustering method is applied to the measurement of laser warner, and the space-time fusion for measurements in ...Multi-laser-target tracking is an important subject in the field of signal processing of laser warners. A clustering method is applied to the measurement of laser warner, and the space-time fusion for measurements in the same cluster is accomplished. Real-time tracking of multi-laser-target and real-time picking of multi-laser-signal are introduced using data fusion of the measurements. A prototype device of the algorithm is built up. The results of experiments show that the algorithm is very effective.展开更多
文摘The D-S evidential reasoning algorithm is invalid when the evidence is completely contradicted. Therefore,a modified algorithm is proposed based on the elemental correlation and the influence of elemental weights in the evidence. The modified algorithm is more powerful ability to rectify errors and less computational complexity in the circumstance of multi-evidence fusion processing than those of the D-S evidential reasoning algorithm.
文摘为了快速准确地检测无人驾驶方程式大赛中赛道锥桶的特征信息,提出一种融合激光雷达点云数据和相机图像数据的检测方法.首先对点云数据进行感兴趣区域(region of interest, ROI)提取并对噪点进行滤波,针对目前地面欠分割和过分割问题引入自适应地面分割算法,并采用欧式聚类对锥桶空间位置信息进行提取;其次采集和标注图像数据集,并使用YOLOv5进行训练后检测,完成锥桶颜色信息的提取;然后将激光雷达检测的锥桶空间位置信息和相机检测的锥桶颜色信息进行融合;最后设计试验进行验证,结果表明:所提出的融合检测方法能够弥补单传感器检测锥桶带来的问题,快速准确地检测出赛道中的锥桶,为规划和决策提供了保障.
基金University Doctor Subject Foundation of China (20060699024)
文摘Multi-laser-target tracking is an important subject in the field of signal processing of laser warners. A clustering method is applied to the measurement of laser warner, and the space-time fusion for measurements in the same cluster is accomplished. Real-time tracking of multi-laser-target and real-time picking of multi-laser-signal are introduced using data fusion of the measurements. A prototype device of the algorithm is built up. The results of experiments show that the algorithm is very effective.
