eIQ® OpenCV Neural Network and ML Algorithm Support | NXP Semiconductors

Automotive

Industrial

Consumer

Technologies

eIQ® OpenCV Neural Network and ML Algorithm Support

eIQOpenCV

NXP’s eIQ software supports the OpenCV library – a well-known industry standard comprised of programming functions that can perform image processing, video encoding/decoding, video analysis and object detection, in addition to processing of deep neural networks (DNN) and classical machine learning algorithms (ML). The cross-platform eIQ for OpenCV library is free for use under the open-source BSD license. eIQ for OpenCV NN targets Arm® Cortex®-A cores and utilizes Arm Neon™ technology acceleration to process TensorFlow and Caffe trained NN models.

Diagram

eIQ OpenCV Neural Network and ML Algorithm Support

eIQ OpenCV Neural Network and ML Algorithm Support
Get diagram PDF

Features

  • An open-source computer vision and machine learning software library
  • Includes OpenCV DNN module for processing TensorFlow and Caffe trained neural network models
  • Includes OpenCV ML module for classical machine learning algorithms like support vector machine (SVM)
  • Uses Arm Neon™ SIMD architecture for processors which implement the Armv7-A or Armv7-R profile
  • Fully integrated into Yocto recipe for OpenCV 4.0 supporting i.MX 8, i.MX 6, and i.MX 7
  • Learn more about OpenCV library

Supported Devices

Downloads

Quick reference to our software types.
Filters

1 download

  • Software Development Resources

    eIQ Machine Learning Software for i.MX Linux 4.14.y

    EXTERNALRev 0Jun 24, 20191 KBEIQ-MLSOFTWARE
    Download

Note: For better experience, software downloads are recommended on desktop.

Documentation

Quick reference to our documentation types.

Filters

2 documents

Compact List

Hardware

Quick reference to our board types.
Filters

3 hardware offerings

Related Software

Quick reference to our software types.

Filters

Training

Filters

1 training

Support

What do you need help with?

Search

Recently viewed products

There are no recently viewed products to display.