Robotic Implementation of Object-Based Visual Attention
Results
Introduction
Fig. 1: Image of the system setup. The robot consisted of a camera, mounted on a pan-tilt unit.
The robotic eye makes a series of saccades to different objects across the visual scene: the foveated object is the attentional target, and a number of unattended objects are also present in the perifovea. A reward can be given for a saccade to the red, the white or neither object, but colour is not used as a feature in the object recognition process.
Experiment 1: Offline Learning
Fig. 2: Histogram characterising the likelihood of making a saccade to a target cue. Y-axis, number of hits over 100 trials; 5 trials were used to create this graph. Results for the case where the triangle is rewarding are shown in the upper panel.
Fig. 3: Cumulative number of saccades (out of 100) to each category during the 3 different reward conditions.
Experiment 2: Online Learning
In the second experiment, the system learned visual features online. Features took the form of a 6 x 6 pixel patch of the image luminance.
Fig. 4:
Link to videos
Illustrative Example of SOM at work:
Meetings
Issues from Meeting 03-05-11
- Interaction between feature maps and retinotopic maps
- Nature of features
- Implementation of the number of features used to identify an object
- Kevin to send papers and an example of the SOM
Issues from Meeting 04-05-11
- Continuation of implementation (Selection of attentional target, now calibrating the camera to initiate saccade)
- SOM is now working in APRON
- Pan-tilt controller working
Issues from Meeting 06-05-11
- Implementation is complete, but poor performance.
- Work to understand if this is a bug or an algorithmic problem
- Issues considered: size of the matching templates, variation in positions of the training templates, interference between similar features, poor representation on the SOM
Issues from Meeting 9-05-11
- Poor performance persists despite numerous attempts to improve
- Discussion of algorithm
- Kevin to gather large feature set for Jan
Issues from Meeting 10-05-11
- Nice results in the offline version
- Discussion of algorithm for SOM
- Tao will try to generate sparse feature set. Kevin to gather 500 images for this.
Attachments
-
ER_KB.pdf
(1.1 MB) - added by kevinbrohan
13 months ago.
Epirob Abstract
-
Epirob.pdf
(1.2 MB) - added by kevinbrohan
13 months ago.
Epirob Poster
-
SOM.m
(2.2 KB) - added by kevinbrohan
13 months ago.
Demo of self-organising map
-
E15_Hist.tif
(0.7 MB) - added by kevinbrohan
12 months ago.
-
E15_Rewards.tif
(0.7 MB) - added by kevinbrohan
12 months ago.
-
E15_Hist.JPG
(25.0 KB) - added by kevinbrohan
12 months ago.
-
E15_Rewards.2.tif
(0.7 MB) - added by kevinbrohan
12 months ago.
-
E15_Rewards.JPG
(43.4 KB) - added by kevinbrohan
12 months ago.
-
RL_offline.tif
(0.7 MB) - added by kevinbrohan
12 months ago.
-
Hist_offline.tif
(0.7 MB) - added by kevinbrohan
12 months ago.
-
RL_online.tif
(0.7 MB) - added by kevinbrohan
12 months ago.
-
Image.jpg
(162.5 KB) - added by kevinbrohan
12 months ago.
-
Hist_offline.JPG
(23.7 KB) - added by kevinbrohan
12 months ago.
-
RL_offline.JPG
(56.4 KB) - added by kevinbrohan
12 months ago.
-
RL_online.JPG
(69.2 KB) - added by kevinbrohan
12 months ago.

