标题 |
![]() 用于目标识别的变速传感器阵列
相关领域
卷积神经网络
稳健性(进化)
人工智能
传感器阵列
压力传感器
计算机科学
压阻效应
计算机视觉
灵敏度(控制系统)
模式识别(心理学)
目标检测
工程类
电子工程
电气工程
机器学习
基因
机械工程
化学
生物化学
|
网址 | |
DOI | |
其它 | This paper presents a cost-effective pressure sensing system for object detection and identification. The pressure sensing system consists of a $27\times 27$ piezoresistive sensor array made of carbon composite Velostat, a signal processing subsystem for signal scanning, amplification, registration, and enhancement. A convolutional neural network is used to classify various objects through the pressure signals produced and processed by the sensing array. Based on systematic characterizations and calibrations of sensing materials and system sensitivity, three experiment setups are established to recognize 10 objects to be detected. In series of experiments, a pressure image data set consisting of 32264 frames of images is first assembled to represent the 10 objects. Contrast enhancement algorithm was used to process the pressure image data set and combined with a convolutional neural network ResNet-PI to classify the 10 objects |
求助人 | |
下载 | 该求助完结已超 24 小时,文件已从服务器自动删除,无法下载。 |
温馨提示:该文献已被科研通 学术中心 收录,前往查看
科研通『学术中心』是文献索引库,收集文献的基本信息(如标题、摘要、期刊、作者、被引量等),不提供下载功能。如需下载文献全文,请通过文献求助获取。
|