检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:张远学 陶青川[1] 王维 ZHANG Yuan-xue TAO Qing-chuan;WANG Wei(College of Electronics and Information,Sichuan University,Chengdu 610065)
机构地区:[1]四川大学电子信息学院
出 处:《现代计算机》2020年第4期37-41,46,共6页Modern Computer
摘 要:为了限制河岸场景下不文明、违规的垂钓行为,提出一种融入深度学习的垂钓行为检测方法。首先使用基于CNN开发的语义分割模型deeplabV3+来对图像进行区域分割从而实现对人与河流进行准确的分类识别及定位;其次,提出改进的快速高精度EDlines边缘检测算法对河流与人之间的图像进行钓竿检测。实验结果表明:该结合方法能够非常快速并准确实现目标分割及噪声干扰下的钓竿检测,解决传统检测算法一直存在的受波纹、光照以及倒影等因素的干扰。In order to limit uncivilized behaviors and unauthorized fishing along the rivers,this paper introduces a fishing detection method based on Deep Learning.First we use a CNN based semantic segmentation model,deeplabV3 to achieve regional segmentation to achieve accurate classification and identification of people and rivers;Second,we provide an improved EDlines egde detection algorithm to detect the fishing rod in the cutting a-rea between human and the river.The experiment result shows that deeplabV3 combined with the improved EDlines al⁃lows very fast and accurate target segmentation and fishing rod detection with noise interference,meanwhile,it can solve the wave light and reflection problems that long bothered traditional detection algorithm.
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.38