🦉 Introduction

Introduction

iam Basic System

The iam basic system is sketched below. In the out-of-the-box state the camera performs as an common GigE-Vision device and makes it easy to install the system and finding the right camera setup.

How to start with the iam camera system is described in the Quick Start  section. The section SynView  gives us more detailed discription of NETs Software Development Kit (SDK). 

iam Customization Possibilities

iam provide 64-bit processor scalability while combining real-time control with soft and hard engines for graphics and video. With the NET SDK and GigE - Vision toolboxes sketched below customers can start from a comfortable starting point to build their unique vision system with iam. The open system architecture of iam enables customers to use both CPU and FPGA processing resources in their application.

In the chapters Applications we provide different example projects to transform iam into your own smart vision system while chapter Third Party Libraries provides step by step guidelines and example codes for the most widely-used commercial vision libraries such as HALCON , MIL (Matrox Imaging Library) and /wiki/spaces/iam/pages/844627987.

In section SynView Smart App Example using iAMGigEServer you will find a simple software example application while in section NET Open Camera Concept (OCC) for iam we briefly described how to optimize the application code by using hardware acceleration with more advanced examples.

iam ML - Machine Learning Ready

iam ML Version is ideal as a platform for Machine Learning tasks. The integrated hardware acceleration efficiently supports common neural networks framework such as Caffe, TensorFlow and MXNet. This means that users get a smart vision system that contributes decentrally to the application solution. iam enables them to develop precisely tailored solutions for their vision-based processes from an toplevel perspective.

Section iam ML - Machine Learning ready provides step by step guidelines and example codes from training- over deploying- until performing convolutional neural network processing with iam.

📚 Content