Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

🦉 Introduction


Excerpt

In this section we discribe possibilities to build your own younique smart vison system by using the provided infastructur of iam camera.

Image RemovedImage Added

Introduction

In this section we discribe posibilities to build your own younique smart vison system by using the provided infastructur of iam cameras. There are two possible ways for obtaining a application for iam:

  1. compile native on iam camera: small apps or specific Third Party Libraries.

  2. and more powerfull: cross compiling on a host or server system. Including whole system optimization and FPGA processing.

In this section we introduce our example repositories for both cases. By checking those out our Video Tutorials can assist you.

Example Repositories

There are different example Git repository for the iam camera system.

Smart app example with third party library

Example Name

Compiling

Discription

Repository

opencv_dice

nativ

  • opencv_dice

https://bitbucket.org/net-gmbh/opencv_dice/

sw_scaler_synview

cross

This example uses no hw acceleration.
But it uses the same infrastructure like other hw accelerated examples.
The main processing consists of a simple c-code scaler for horizontal and vertical rescaling.

After processing the image is sent out via gige - server.

https://bitbucket.org/net-gmbh/iam_apps/

Smart app with hardware accelerations and third party libraries

ccode_synview

cross

The example code_synview uses HLS hw acceleration written in c-code.

Main processing method can be selected among following choices:

  • no processing

  • simple c-code sw processing

  • a optimized c-code version with ARM NEON instructions

  • processing with opencv functions

  • hw accelerated processing based on a c-code source

After processing the image is sent out via gige - server.

https://bitbucket.org/net-gmbh/iam_apps/

remap_synview

cross

The example remap_synview uses the hw acceleration function xf::cv::remap from the Vitis vision library.

After processing the image is sent out via gige - server.

https://bitbucket.org/net-gmbh/iam_apps/

dice_synview

cross

The example dice_synview demonstrates dice cube detection and dots counting for each cube. It uses multiple xfOpenCV functions.

https://bitbucket.org/net-gmbh/iam_apps/

rtl_threshold_synview

cross

This example uses RTL hw acceleration written in verilog.

After processing the image is sent out via gige - server.

https://bitbucket.org/net-gmbh/iam_apps/

strm_rtl_threshold_synview

cross

This example uses RTL hw acceleration in the streaming path.
The module is located between the sensor interface and the dma.
It consists of a 32-Bit master and 32-Bit slave axi-stream interface for sensor pixel data and a 32-Bit axi-lite control interface for register access.

After processing the image is sent out via gige - server.

https://bitbucket.org/net-gmbh/iam_apps/

sw_scaler_synview

This example uses no hw acceleration.
But it uses the same infrastructure like other hw accelerated examples.
The main processing consists of a simple c-code scaler for horizontal and vertical rescaling.

After processing the image is sent out via gige - server.

https://bitbucket.org/net-gmbh/iam_apps/

Smart app example with machine learning

dpuClassify

  • Reference application for image classifier training and execution.

  • Different convolutional models are available (VGG, DenseNet, ResNet, Inception)

  • Training code for transfer learning with Keras and Tensorflow

  • Vitis Ai model conversion code

  • iam application for image classification

https://bitbucket.org/net-gmbh/iam_ml/

📚 Content


Child pages (Children Display)
alltrue
depth100
styleh2
excerptTyperich content

🔗 related content

SynView

Third Party Libraries

🌍 external media

Insert excerpt
MasterContent: external media
MasterContent: external media
nopaneltrue

👥 contact NET

Insert excerpt
MasterContent: Contact NET
MasterContent: Contact NET
nopaneltrue