www.design-reuse-embedded.com
You are here : design-reuse-embedded.com  > Artificial Intelligence  > Vision
Download Datasheet        Request More Info
All Silicon IP

Overview

The D-MOT-10 FPGA IP core for motion detection in video stream images is a completed module intended to be used in vision systems for various applications (security systems, specialized systems, etc.) that are based on FPGA. The core represents a simple data exchange interface that ensures easy integration into various systems. The algorithms are perfectly suitable for motion detection of ground, surface and aerial objects of any type. The core is connected to the interface controller of DDR memory via a standard interface (the controller is by Xilinx Company). The core reads current images of video sequence and records the results of work. The developer should ensure updating of image frames in the DDR memory according to multi-buffer principle (multiple buffering). Before operation is started, the core needs to be configured (configuration register values have to be written). The observed scene (in the images of the video sequence) should be fixed. Once initialized (switch-on), the core needs some time (2-3 minutes) to adapt to the scene. At this time, the core algorithms initialize filters and form a map of constantly moving objects (e.g. images of treetops swaying in the wind). Once all core filters adapted, all moving objects will be detected with a high degree of reliability.

Applications

The core can be used in any vision applications such as security video surveillance systems and in special robotic vision systems. A simple interface of data exchange with the core makes it possible to integrate it easily into any FPGA project.

Block Diagram

Features

  • Maximum number of detected objects is up to 128
  • Maximum size of detected objects are limited only by the size of video frame
  • Minimum size of detected objects is 8x8 pixels
  • Maximum motion speed of detected objects is up to 30 pixels/frame
  • Detection of objects with a contrast from 10%
  • Dimensions of processed frames are 720x576 (can be adapted to specific conditions)
  • Accuracy of output coordinates is 1 pixel
  • Delay of return of output coordinates is 1 frame
  • Processing of video frames of mono_8 format (1 byte per pixel grayscale)
  • All shapes of detected objects within the video frame

Partner with us

Visit our new Partnership Portal for more information.

Submit your material

Submit hot news, product or article.

List your Products

Suppliers, list and add your products for free.

© 2018 Design And Reuse

All Rights Reserved.

No portion of this site may be copied, retransmitted,
reposted, duplicated or otherwise used without the
express written permission of Design And Reuse.