Authors

Abstract

In order to recognize the road effectively, agricultural robots mainly rely on the tracking and detection data of road obstacles. Traditional obstacle detection mainly studies how to use multiple fusion methods such as vision and laser to analyze structured and simplified indoor scenes. The working environment of agricultural robots is a typical unstructured outdoor environment. Therefore, based on the environmental characteristics of agricultural robot navigation, the mean displacement algorithm is introduced to detect and study the obstacles aiming at the road edge. After explaining the advantages and principle flow of the mean displacement algorithm to effectively realize motion capture, the feasibility of target location and tracking research is discussed. After that, the bottom data acquisition and analysis model is constructed based on the road navigation data of agricultural robots. To capture the movement obstacles of road edge and build the foundation of road recognition technology. In order to improve the effectiveness of motion obstacle capture and detection, a moving target detection algorithm is proposed to optimize and update the mean displacement algorithm, and constructs a feature-oriented hybrid algorithm motion capture model. The simulation results indicate that the proposed optimization model can effectively improve the tracking efficiency of non-rigid targets in outdoor environment, and the number of evaluation iterations can reach 3.5621 times per frame, which shows that the research has good theoretical and practical value.

Abstract in Chinese

为了有效地识别道路，农业机器人主要依靠道路障碍物的跟踪检测数据。传统的障碍物检测主要研究如何利用视觉、激光等多种融合方法对结构化、简化的室内场景进行分析。农业机器人的工作环境是典型的非结构化户外环境。因此，根据农业机器人导航的环境特点，引入了平均位移算法来检测和研究针对道路边缘的障碍物。在阐述了平均位移算法有效实现运动捕获的优点和原理流程后，讨论了目标定位跟踪研究的可行性。然后，基于农业机器人的道路导航数据，建立了底层数据采集与分析模型。捕捉道路边缘的运动障碍，为道路识别技术奠定基础。为了提高运动障碍物捕获和检测的有效性，提出了一种运动目标检测算法，对平均位移算法进行优化和更新，并构建了一种面向特征的混合算法运动捕获模型。仿真结果表明，该优化模型能有效提高室外环境下非刚性目标的跟踪效率，每帧评估迭代次数可达3.5621次，具有良好的理论和实用价值。