Renesas‘ Application of Deep Learning Algorithms in The Field of Defect Detection
Defect detection is a very important application in the electronics manufacturing industry. However, due to the variety of possible defects, it is difficult for traditional machine vision algorithms to completely model and migrate defect features. The reusability is not great, and working conditions must be distinguished, which will waste a lot of human costs. As a result, more and more engineers have begun to introduce deep learning algorithms into the field of defect detection, as deep learning has achieved very good results in feature extraction and positioning.
The following will introduce RENESAS' application of deep learning algorithms in the field of defect detection, using PCB circuit board defect detection as an example.
Here, Renesas presents a defect detection solution using the tiny variation of the You Only Look Once, Version 3 (YOLOv3-tiny) deep learning algorithm. YOLOv3-tiny is a lightweight object detection algorithm. The network structure of YOLOv3-tiny is as follows.
Compared with the original YOLOv3 model, YOLOv3-tiny reduces some layers and parameters to improve the inference speed and efficiency on embedded devices. The algorithm has high real-time performance and good accuracy, which is very suitable for industrial defect detection applications.
The defect detection solution can be deployed on RZ/V2L and RZ/V2M MPU chips. The deployment process is shown in the figure below.
ONNX is an open format built to represent machine learning models. ONNX defines a common set of operators - the building blocks of machine learning and deep learning models and a common file format to enable AI developers to use models with a variety of frameworks, tools, runtimes, and compilers.
The hardware setup of this application in the RZ/V2M MPU is as follows.
The hardware setup of this application in RZ/V2L MPU is as follows.
The YOLOv3-tiny defect detection solution is deployed on RZ/V2M and RZ/V2L. Low power consumption (less than 5W), has a high-performance inference effect, 52fps in RZ/V2M and 35fps in RZ/V2L (both don't include pre- and post-process).
Defect detection on the embedded side is not only used for PCB defect detection in electronic manufacturing, but it also has a wide range of application scenarios, the following are some common examples:
Industrial automation: In manufacturing, defects in products such as incorrect product assembly, missing parts, or damage can be detected in real-time.
Agricultural field: In agricultural production, it can be used to detect defects in crops or vegetables, such as diseases, insect pests, or fruit defects.
Security monitoring: It can be used for defect detection in security monitoring systems, such as detecting abnormal objects, intrusion behaviors, or safety hazards in buildings or public places.
Medical imaging: In the medical field, it can be applied to medical image analysis to detect disease markers, tumors or abnormal tissues, etc.
Vehicle detection: In intelligent transportation systems, it can be used for vehicle detection, such as traffic flow monitoring, illegal vehicle detection, or parking lot management.
- |
- +1 赞 0
- 收藏
- 评论 0
本文由翊翊所思转载自RENESAS Blogs,原文标题为:RZ/V Defect Detection in the Industrial Field,本站所有转载文章系出于传递更多信息之目的,且明确注明来源,不希望被转载的媒体或个人可与我们联系,我们将立即进行删除处理。
相关推荐
【经验】RZ/T2M使用瑞萨工具生成IAR开发环境软件项目驱动的方法
瑞萨RZ家族发布了最新的MPU型号RZ/T2系列,那么对于该系列MPU如何使用瑞萨软件工具生成IAR开发环境代码呢,如下步骤主要介绍使用瑞萨RZT Smart Configurator工具生成RZ/T2M IAR开发环境软件项目驱动方法。
【经验】解析瑞萨MPU RZ/T1 SPI总线通信功能配置方法
当我们使用瑞萨(Renesas)MPU RZ/T1做项目开发时,基本都会用到SPI总线通信的功能,SPI总线通信速率较快很适合在单片机板级之间进行数据交互,本文将介绍使用瑞萨开发环境配置生成RZ/T1 SPI总线驱动程序的方法。
【经验】瑞萨MPU RZ/T1使用SSC生成EtherCAT CiA402协议栈方法
瑞萨MPU RZ/T1支持EtherCAT网络设计,如何使用协议栈工具生成相对应的EtherCAT从机栈代码呢,本文主要就Beckhoff工具生成EtherCAT CiA402协议栈方法做相关介绍。
【经验】瑞萨RZ/T2M系列MPU使用IAR开发环境时的调试方法和注意事项
瑞萨RZ/T2M系列MPU可以使用IAR开发环境进行开发,当我们使用IAR开发环境加载一些瑞萨RZ/T2M相关例程项目时,总是会遇到一些编译报错问题,烧写异常问题,此文主要介绍使用IAR开发环境连接调试RZ/T2M系列MPU的方法和一些注意事项。
RZ/G MPU G2L、LC、UL组
型号- RZ/G3YYY,RZ/G2L,RZ/G2M,RZ/G2LC,RZ/G2UL,RZ/G1M,RZ/G2N,RZ/G1N,RZ/G,RZ/G1C,RZ/G2E,RZ/G1E,RZ/G2H,RZ/G1H,RZ/G3YY,RZ/G3XX,RZ/G3ZZ,RZ/G4X,RZ/G3X,RZ/G3Y,RZ/G4XX,RZ/G3Z
【经验】瑞萨MPU RZ/T1使用code generator生成SCI的初始代码方法
工程师初次使用瑞萨(Renesas)RZ/T1系列MPU时,可能不知道SCI该如何配置波特率,中断入口,中断标志位等。本文将介绍RZ/T1系列MPU利用code generator生产SCI的配置方法。
【经验】瑞萨MPU RZ/T1使用中断方式DMA传输的方法介绍
瑞萨(Renesas)MPU RZ/T1系列可以用于工业通信,伺服等领域项目中,这些领域往往需要主控与外设进行大量数据的交互,当我们使用RZ/T1的DMA中断传输功能接收大量数据时,在程序及配置中具体我们该怎么操作呢,本文主要介绍中断方式操作DMA传输的方法。
RZ/G MPU G2H,M,N,N组
型号- RZ/G3YYY,RZ/G2L,RZ/G2M,RZ/G2LC,RZ/G2UL,RZ/G1M,RZ/G2N,RZ/G1N,RZ/G1C,RZ/G2E,RZ/G1E,RZ/G2H,RZ/G1H,RZ/G3XX,RZ/G3YY,RZ/G3ZZ,RZ/G4X,RZ/G3X,RZ/G3Y,RZ/G4XX,RZ/G3Z
【经验】解析瑞萨MPU RZ/T1在e2 studio环境下的双核仿真步骤方法
瑞萨(Renesas)RZ/T1为基于32位和64位Arm的高端MPU,广泛应用工业控制领域,本文主要介绍使用瑞萨RZ/T1的双核CR4和CM3在e2 studio下的双核仿真步骤方法,帮助大家快速的进阶RZ/T1项目开发。
Renesas(瑞萨电子)RZ系列64位/32位基于Arm的微处理器(MPU)选型指南
目录- RZ Series MPU RZ/A Series MPU RZ/G Series MPU RZ/T Series MPU RZ/N Series MPU RZ Family MPU Package overview
型号- RZ/A1M,RZ/A1L,RZ/N1D,RZ/G1M,RZ/G1N,RZ/A1H,R8A774BX,RZ/A1LU,RZ/G1C,RZ/G1E,RZ/G1H,RZ/A1,RZ/A,RZ/G2,RZ/N,RZ/A2M,RZ/G2M,RZ/G2N,RZ/G2M 96,R8A774EX,RZ/G,RZ/N1,RZ/G2E 96,RZ/A1LC,RZ/T1,RZ/G2E,RZ/T,RZ/G2H,R8A774C0,RZ/N1S,RZ FAMILY,R8A774AX,RZ/G2M-96CE,RZ/N1L
【经验】瑞萨MPU RZ/T1使用双寄存器切换开启DMA传输的方法介绍
在项目中使用瑞萨(Renesas)MPU RZ/T1做从机接收大量数据时,为了传输和接收数据效率,我们会启用DMA传输的功能,有时候项目中需要传输的是两块数据,这时候我们可以使用双寄存器切换的方式来完成,本文主要介绍启用双寄存器切换启用DMA传输的方法。
【经验】RZ/T1系列MPU批量生产两种烧录程序方式:在线烧录&直接FLASH烧录
瑞萨的RZ/T1系列的MPU没有内置的FLASH,程序一般是保存在外部SPI接口的FLASH中,在产品的批量生产时可以使用两种烧录程序的方式,一种是在线烧录,一种是直接FLASH烧录。
电子商城
现货市场
登录 | 立即注册
提交评论