Burn Test
This is a burn test: run the quad-core saliency demo while also loading up CPU, GPU and NEON in the background.
By Laurent Ittiitti@usc.eduhttp://jevois.orgGPL v3
Video Mapping:   YUYV 640 300 10.0 YUYV 320 240 10.0 JeVois BurnTest

Module Documentation

This burn test exercises all aspects of your JeVois smart camera to the maximum, namely:

  • launch two instances of whetstone (floating point benchmark test) running in the background
  • launch two instances of dhrystone (integer benchmark test) running in the background
  • grab frames from the camera sensor
  • run the quad-core visual attention algorithm
  • in parallel, run the NEON demo
  • in parallel, run the GPU demo that processes the video through 4 image filters (shaders)
  • stream attention video results over USB
  • issue messages over the serial port

This burn test is useful to test JeVois hardware for any malfunction. It should run forever without crashing on JeVois hardware. Demo display layout and markings are the same as for the DemoSaliency module.

This burn test is one of the tests that every JeVois camera produced is tested with at the factory, before the unit is shipped out.

Things to try

Select the burntest video mode (note that it is 640x300 @ 10fps, while the default MicroSD card also includes a mode with 640x300 @ 60fps that runs the DemoSaliency module instead). Observe the CPU temperature at the bottom of the live video window. If it ever reaches 75C (which it should not under normal conditions given the high power fan on the JeVois smart camera), the CPU frequency also shown next to the temperature will drop down below 1344 MHz, and will then come back up as the CPU temperature drops below 75C.

Connect your JeVois camera to your host computer through a USB Tester device that measures voltage, current, and power. You should reach about 3.7 Watts under the burn test, which is the maximum we have ever been able to achieve with a JeVois unit.

ParameterTypeDescriptionDefaultValid Values
(Saliency) cweightbyteColor channel weight255-
(Saliency) iweightbyteIntensity channel weight255-
(Saliency) oweightbyteOrientation channel weight255-
(Saliency) fweightbyteFlicker channel weight255-
(Saliency) mweightbyteMotion channel weight255-
(Saliency) centerminsize_tLowest (finest) of the 3 center scales2-
(Saliency) deltaminsize_tLowest (finest) of the 2 center-surround delta scales3-
(Saliency) smscalesize_tScale of the saliency map4-
(Saliency) mthreshbyteMotion threshold0-
(Saliency) fthreshbyteFlicker threshold0-
(Saliency) msflickboolUse multiscale flicker computationfalse-
(Kalman2D) usevelboolUse velocity tracking, in addition to positionfalse-
(Kalman2D) procnoisefloatProcess noise standard deviation0.003F-
(Kalman2D) measnoisefloatMeasurement noise standard deviation0.05F-
(Kalman2D) postnoisefloatA posteriori error estimate standard deviation0.3F-
Detailed docs:BurnTest, Saliency, Kalman2D, FilterGPU
Copyright:Copyright (C) 2016 by Laurent Itti, iLab and the University of Southern California
License:GPL v3
Support URL:http://jevois.org/doc
Other URL:http://iLab.usc.edu
Address:University of Southern California, HNB-07A, 3641 Watt Way, Los Angeles, CA 90089-2520, USA