1 / 12

Video Surveillance with Motion Detection

Video Surveillance with Motion Detection. Application: Surveillance Data-Stream Compression. Need: Continuous monitoring of scene with video camera Security (ATM booth, parking lot), Intelligent Highways, Bio/Pharmaceuticals, etc.

parry
Download Presentation

Video Surveillance with Motion Detection

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Video Surveillance with Motion Detection

  2. Application:Surveillance Data-Stream Compression • Need: Continuous monitoring of scene with video camera • Security (ATM booth, parking lot), Intelligent Highways, Bio/Pharmaceuticals, etc. • Problem: Generates large volumes of data to record, archive, and review • Preferable to reduce data stream at the source (embedded compression) • Solution: Shrink data storage requirements • Reduce sizeof each video frame to record, and/or • Reduce total number of video frames to record • Simple Idea: Motion within camera’s field of viewtriggers storage of “interesting” frames Design Requirement:Identify and record only these “interesting” video frames

  3. Principle of Operation Input Frames Estimatemotion energy Record/Display Frames  thrsh? Yes M

  4. Principle of Operation Display Control Display Frame Count Display Record Recorded Image Display SAD Input Frames Absolute Differences Image Sum of Absolute Differences (Motion Energy) Trigger Threshold Threshold Display

  5. Motion Energy Motion Energy (Sum of Absolute Differences) Current Frame Previous Frame

  6. The Simulink® Model Recorded FramesAperiodic rate(<< 30 fps) Source FramesHigh rate: 30 fps Total # of RecordedFrames

  7. Simulink Model Hierarchy Estimatemotion Compare to threshold Record frames& update count System Design and Simulation

  8. The Simulink Model Estimatemotion Compare to threshold Record frames& update count

  9. SAD Algorithm uintN: N-bit unsigned integer intN: N-bit signed integer • Sum of Absolute Differences • Very simple method of inter- frame video motion detection • Has efficient fixed-point (integer) implementation in hardware

  10. Motion levels Video Motion Estimate Detection Threshold Captured Video Frames Motion Detection via Thresholding

  11. Migration to Real-Time Replace Virtual Sinks/Sources by TCP/IP Receive/Transmit Blocks with Byte Unpack/Pack

  12. Real-time Visualization Host-side visualization Simulink PC Model Monitor video capture Motion Estimates

More Related