Real-Time Video Analysis on an Embedded Smart Camera

Report
Real-Time Video Analysis on an Embedded
Smart Camera for Traffic Surveillance
Presenter: Yu-Wei Fan
Outline
• Introduction
• System Architecture
– Hardware
– Software
• Algorithm
– Stationary Vehicle Detection
• Algorithm Mapping
– External memory access
– Data transfer
– Number format issues
• Computing Performance
Introduction
Traffic surveillance consider about:
• Real time.
• Limited resources such like memory and power.
The system include:
•
•
•
•
CMOS image sensor
Performs high-level video analysis
Compresses the video stream using MPEG-4
Transfers the compressed data via an IP-based network
to a base station
Outline
• Introduction
• System Architecture
– Hardware
– Software
• Algorithm
– Stationary Vehicle Detection
• Algorithm Mapping
– External memory access
– Data transfer
– Number format issues
• Computing Performance
Hardware
Hardware
1. Video Sensor:
LM-9618 CMOS sensor
2. Processing Unit :
A rough estimation results in 10 GIPS computing performance.
TMS320C6415 DSPs (600 MHz)
3.Communications Unit:
Intel XScale IXP425 processor
Software
• DSPs:
The DSP/BIOS real-time operating system operates
the DSPs.
• Xscale:
Linux (Kernel 2.6.8.1) operates the network
processor, allowing access to a broad variety of open
source software modules.
Outline
• Introduction
• System Architecture
– Hardware
– Software
• Algorithm
– Stationary Vehicle Detection
• Algorithm Mapping
– External memory access
– Data transfer
– Number format issues
• Computing Performance
Stationary Vehicle Detection
Requirements:
1. A stationary camera position
2. Pretty static ambient light conditions
Stationary Vehicle Detection
Algorithm:
1. The statistics of the pixel’s intensity is computed and stored in the
observation distribution (OD) matrix of size n × m.
2. The OD values are used to adapt the values of the background model
(BG).
Typically :
α=0.1
a=1
3. The algorithm identifies long-term intensity changes
between the BG and the OD distribution.
4. If a connected component exceeds a predefined area a
stationary vehicle has been identified.
Outline
• Introduction
• System Architecture
– Hardware
– Software
• Algorithm
– Stationary Vehicle Detection
• Algorithm Mapping
– External memory access
– Data transfer
– Number format issues
• Computing Performance
External memory access
• Excessive access to external memory is a major source for
poor performance on embedded DSP architectures.
• In many high-level languages memory management is hidden
from the programmer.
External memory access
Consider the example:
For image data at full PAL resolution (720 × 576, 8-bit pixels), this results
in a total of 7.12 MB of transferred data.
The poor performance is poor.
External memory access
Image-based vs. pixel-based
The transferred data is reduced to 2.47 MB
Data transfer
• Direct memory access (DMA) to improve the memory transfer
between the external memory and processor.
• A regular data access pattern is an important precondition for
effective DMA.
• Use “ping-pong” buffers.
Number format issues
• Memory is a crucial resource in embedded systems. Especially,
internal memory has to be handled very carefully.
• Parallelism can be improved by exploiting packed-data
processing capabilities of current DSPs.
Outline
• Introduction
• System Architecture
– Hardware
– Software
• Algorithm
– Stationary Vehicle Detection
• Algorithm Mapping
– External memory access
– Data transfer
– Number format issues
• Computing Performance
Computing Performance
1. SVD algorithm in Matlab 6.1R12 with 2.4 GHz Pentium 4 desktop computer.
2. C++ implementation directly derive from the SVD Matlab code.
3. Use algorithm mapping tactics.

similar documents