Demo Saliency
Simple demo of the visual saliency algorithm of Itti et al., IEEE PAMI, 1998.
By Laurent Ittiitti@usc.eduhttp://jevois.orgGPL v3
 Language: C++Supports mappings with USB output: YesSupports mappings with NO USB output: No 
 Video Mapping:   YUYV 176 90 120.0 YUYV 88 72 120.0 JeVois DemoSaliency
 Video Mapping:   YUYV 320 150 60.0 YUYV 160 120 60.0 JeVois DemoSaliency
 Video Mapping:   YUYV 352 180 120.0 YUYV 176 144 120.0 JeVois DemoSaliency
 Video Mapping:   YUYV 352 180 100.0 YUYV 176 144 100.0 JeVois DemoSaliency
 Video Mapping:   YUYV 640 300 60.0 YUYV 320 240 60.0 JeVois DemoSaliency
 Video Mapping:   YUYV 704 360 30.0 YUYV 352 288 30.0 JeVois DemoSaliency
 Video Mapping:   YUYV 1280 600 15.0 YUYV 640 480 15.0 JeVois DemoSaliency
 Video Mapping:   YUYV 320 260 30.0 YUYV 320 240 30.0 JeVois DemoArUco

Module Documentation

Visual saliency algorithm as described at

This algorithm finds the location in the camera's view that is the most attention-grabbing, conspicuous, or so-called salient. This location is marked on every video frame by the pink square. Salient locations detected on each frame are smoothed over time using a Kalman filter. The smoothed attention trajectory is shown with a green circle.

For an introduction to visual saliency computation, see

Serial Messages

This module can send standardized serial messages as described in Standardized serial messages formatting, where all coordinates and sizes are standardized using Helper functions to convert coordinates from camera resolution to standardized. One message is issued on every video frame at the temporally smoothed attended (most salient) location (green circle in the video display):

  • Serial message type: 2D
  • id: always sm (shorthand for saliency map)
  • x, y: standardized 2D coordinates of temporally-filtered most salient point
  • w, h: standardized size of the pink square box around each attended point
  • extra: none (empty string)

See Standardized serial messages formatting for more on standardized serial messages, and Helper functions to convert coordinates from camera resolution to standardized for more info on standardized coordinates.

ParameterTypeDescriptionDefaultValid Values
(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-
(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-
script.cfg file
# Optional script to run each time the module is loaded. Commands should be exactly as you would interactively type into
# the Engine user interface:
Detailed docs:DemoSaliency
Copyright:Copyright (C) 2016 by Laurent Itti, iLab and the University of Southern California
License:GPL v3
Support URL:
Other URL:
Address:University of Southern California, HNB-07A, 3641 Watt Way, Los Angeles, CA 90089-2520, USA