基于改进ORB的复杂场景煤矸石匹配算法
Feature matching algorithm of gangue in complex scene based on improved ORB
曹现刚 1王虎生 1王鹏 1吴旭东 1向敬芳 1李虎1
作者信息
- 1. 西安科技大学 机械工程学院,陕西 西安 710054;陕西省矿山机电装备智能检测与控制重点实验室,陕西 西安 710054
- 折叠
摘要
在煤矸石分拣过程中,传统方法通过视觉识别与胶带速度预测煤矸石实时位姿,然而,由于煤矸石随胶带高速长距离运输过程中常发生打滑和跑偏现象,预测位姿与分拣区域实际位姿不一致,导致机械臂空抓、误抓,影响分拣效率.针对这一问题,提出了一种改进的ORB匹配算法用于煤矸石在分拣区域的二次定位,首先引入局部自适应伽马校正的oFAST特征检测,提高低光照下的匹配准确率;此外,针对矸石在高速移动中由于动态干扰产生的较多误匹配点,结合BEBLID描述子和GMS算法进行快速特征匹配,并运用随机抽样一致性算法优化匹配点选择,增强算法鲁棒性;最终,通过得到的匹配点计算最小外接矩形完成位姿获取.实验结果显示,所提算法相较于传统ORB 算法在尺度、光照、视角变化下煤矸石匹配正确率分别提升了 16.7%、36%和22%,平均误差为1.29 mm,平均匹配耗时在40 ms以内,适用于复杂场景下煤矸石的匹配定位.
Abstract
In the process of coal gangue sorting,traditional methods use visual identification and belt speed to predict the real-time position of coal gangue.However,due to slippage and deviation of the coal gangue during high-speed,long-distance transportation on the belt,the actual position often differs from the predicted position,leading to issues like missed or incorrect grabs by robotic arms,thus affecting sorting efficiency.To address this problem,we proposed an improved ORB matching algorithm for the secondary positioning of coal gangue.Firstly,we introduced local adaptive gamma correction to oFAST feature detection,enhancing matching accuracy under low lighting conditions.Additionally,to counter the dynamic interference caused by high-speed movement of the gangue,we combined BEBLID descriptors and the GMS algorithm for rapid feature matching,and employed the RANSAC algorithm to optimize feature point selection,thereby enhancing the robustness of the algorithm.Ultimately,the minimum bounding rectangle was calculated through matching points to obtain the position.Experimental results show that the proposed algorithm improves the matching accuracy of coal gangue under scale,illumination,and angle changes by 16.7%,36%,and 22%,respectively,compared to the traditional ORB algorithm,with an average error of 1.29 mm and an average matching time within 40 ms.This effectively enables gangue matching and positioning in complex scenarios.
关键词
图像处理/特征匹配/煤矸分拣机器人/BEBLID/网格运动统计/ORBKey words
image processing/feature matching/coal gangue sorting robot/BEBLID/grid-based motion statistics/ORB引用本文复制引用
基金项目
国家自然科学基金面上项目(51975468)
陕西省重点研发计划(2018GY-160)
陕西省自然科学基础研究计划(2023)(2023-JC-YB-362)
陕西省教育厅自然科学研究项目(23JK0548)
出版年
2024
NETL
NSTL
万方数据