基于AGAST角点域特征的垃圾识别算法  

Recognition Algorithm of Garbage Based on Feature of AGAST Corner

作　　者：申新杰 兰浩[1] 曾渝 SHEN Xin-jie;LAN Hao;ZENG Yu(College of Engineering and Design,Hunan Normal University,Changsha 410000,China)

机构地区：[1]湖南师范大学工程与设计学院,湖南长沙410000

出　　处：《电脑知识与技术》2020年第20期183-186,共4页Computer Knowledge and Technology

摘　　要：为了提高垃圾自动分类回收再利用的效率,提出了一种快速匹配识别垃圾的算法。采用一款自带摄像头,具有图像识别作用的机器视觉开发组件Open MV,基于AGAST(Adaptive and Generic Accelerated Segment Test)角点域的特征匹配算法,以塑料瓶为研究对象,对算法进行了检验。该算法能够有效识别特定垃圾,一定程度上实现了垃圾分类的功能,为有效提高垃圾利用率提供了参考。In order to improve the efficiency of garbage automatic classification and recycling,a fast matching algorithm for garbage recognition is proposed.Using a machine vision development component with camera and image recognition Open MV,based on the AGAST(Adaptive and Generic Accelerated Segment Test)corner region feature matching algorithm,taking plastic bottles as the research object,the algorithm can effectively identify specific garbage,achieve the garbage classification function in a certain degree,and provide a reference for effectively improving the garbage utilization rate.

关 键 词：识别 AGAST 角点域 特征描述 FAST 垃圾分类 

分 类 号：T18[一般工业技术]