2014-02-10T17:35:54Z

Mtaiana:

[[Image:ChicoHead.jpg|frame|left|caption|Chico head.]]
The storage memory of Chico head is a USB stick. [[Image:ChicoHeadUsbStick.jpg]] There are 2 images (~4GB each) for that data on Blackhole:
smb://blackhole/Database/CHICO_HEAD/CHICO_BACKUP_image1.7-oc.bin
smb://blackhole/Database/CHICO_HEAD/CHICO_HEAD_BACKUP_image1.8_2014_02_10.bin
The second image is more recent and features some improvements respect to the first one. 
An image can be dumped on a new USB stick with the "dd" command:
sudo dd bs=4096 if=CHICO_HEAD_BACKUP_image1.8_2014_02_10.bin of=/dev/sdXXXXX
Specify the correct sd device istead of sdXXXXX (sdb, sdc or the like). Pay attention not to overwrite the wrong disk!
DD doesn't give you progress information while it's running, you can make it write such information on the screen by sending it a special message:
sudo kill -USR1 $(pgrep ^dd)
Before removing the USB stick, run sync to ensure that all data has been written:
sync
People who know about the image are Matteo, Ricardo Ferreira and Alex.

In case you improve the content of the USB stick and want to make a new image of it, you can use a command like this:
sudo dd if=/dev/sdXXXXX1 of=/home/matteo/sdXXXXX1.bin

=readme.txt=
This is the content of the readme.txt file in the home directory of Chico head:

Log in: like the one for the iCub

==Demos==

To start the X server:
startx (or startxfce4)

When you are in the X interface you can open terminals and start the various processes from there.
Scripts 1 and 2 start the YARP server and the iCubInterface (used for moving the robot).
Scripts 3_1..3_3 start the right camera, start a viewer and connect the two.
Scripts 4_1..4_4 start the emotion system and cycle emotions in a fixed sequence.
Script 6 moves the head and the eyes in a fixed sequence.

All of this was running together smoothly on Feb. 6 2014.

==Known problems==
* The ethernet adapter on the bottom of the robot does not work.
* Turning on the robot with a cable plugged into the ethernet connector in the head of the robot gets the system stuck. You can plug the cable in after boot and initialize the ethernet connection with: sudo dhclient eth0.
* Something can block one application (typically the terminal and gedit) for 10..20 seconds.
The freezing seems to be triggered both by some disk read and write operations.
The system is still responsive, the affected application freezes, other applications can also freeze at that time if they need to access the disk (I suppose).
It doesn't give problems to the demos once they have been started.
* It is common to get this USB-related error at boot time:
>>USB 3-2: device descriptor read/64, error -71
>>device not accepting addres 4, error -71
>>device not accepting addres 5, error -71
After which the system booted normally.
It seems to happen every time that the USB connector for the facial expression is connected to the board.
It might mean that the USB connectors as a whole are requiring too much current.
Even if the system is started and run without the facial expression connector plugged in, the system still freezes.

USB PEN DRIVE TEST
* I ran hdparm 4 times and got these results (with low variation):
$ sudo hdparm -tT /dev/sda
/dev/sda:
Timing cached reads: 5390 MB in 2.00 seconds = 2697.28 MB/sec
Timing buffered disk reads: 74 MB in 3.05 seconds = 24.27 MB/sec
* I tried to run "bonnie", but it didn't work.
sudo bonnie -u1000
* I used iostat, I did an "ls" after the first measurement
$iostat -dkx 5 (displays measures every 5 seconds)
Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util
sda 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
sda 0.00 13.39 0.00 0.81 0.00 56.80 140.00 0.01 9.00 4.00 0.32
sda 0.00 3.69 0.00 0.65 0.00 2.60 8.00 8.27 1216.00 716.00 46.59
sda 0.00 2.72 0.00 3.09 0.00 24.68 16.00 15.81 2809.18 294.12 90.74
sda 0.00 0.00 0.00 1.00 0.00 4.80 9.60 32.69 4841.60 1000.00 100.00
sda 0.00 0.00 0.00 2.20 0.00 11.18 10.18 25.63 10185.82 454.55 99.80
sda 0.00 0.00 0.00 2.19 0.00 17.53 16.00 12.01 13870.91 454.55 99.60
sda 0.00 0.00 0.00 1.00 0.00 4.00 8.00 5.96 20111.20 1000.00 100.00
sda 0.00 0.20 0.00 1.00 0.00 4.78 9.60 0.45 13737.60 152.00 15.14
sda 0.00 0.40 0.00 0.40 0.00 3.20 16.00 0.00 0.00 0.00 0.00

svctm = service time in milliseconds (not including the time spent in queue.
await = service time including waiting in queue. it peaks at 20 seconds!

Little data is written, almost no data is read. Lots of time is spent in queue...
Why? Could it be that the USB pen is "asleep" and needs to be woken up?

==Wishlist==
*Once the face detector+gaze demo was working on this platform. Maybe it could be restored with little effort.

==IMPROVEMENTS SINCE PREVIOUS IMAGE==
*The demos work out of the box.
*The keyboard layout is Portuguese both for the real terminals and the X session.
*The browser doesn't write chache to the disk (freezing at almost every click)
*The sources lists have been updated, so more packages can be installed.
*Added the readme file

[[Category:Robots]]
[[Category:Vislab]]

File:ChicoHeadUsbStick.jpg

2014-02-10T17:35:45Z

Mtaiana: uploaded a new version of "File:ChicoHeadUsbStick.jpg"

2014-02-07T19:59:02Z

Mtaiana:

Chico head

2014-02-07T19:57:46Z

Mtaiana:

[[Image:ChicoHead.jpg|frame|left|caption|Chico head.]]
The storage memory of Chico head is a USB stick. The image for that data is on Blackhole:
smb://blackhole/database/ICUB/CHICO_BACKUP_image1.7-oc
The image can be dumped on a new USB stick with the "dd" command:
sudo dd bs=4096 if=CHICO_BACKUP_image1.7-oc.bin of=/dev/sdXXXXX
Specify the correct sd device istead of sdXXXXX (sdb, sdc or the like). Pay attention not to overwrite the wrong disk!
Before removing the USB stick, run sync to ensure that all data has been written:
rsync
People who know about the image are Ricardo Ferreira and Alex.

=readme.txt=
This is the content of the readme.txt file in the home directory of Chico head:

<code>
Log in: like the one for the iCub

==Demos==

To start the X server:
startx (or startxfce4)

When you are in the X interface you can open terminals and start the various processes from there.
Scripts 1 and 2 start the YARP server and the iCubInterface (used for moving the robot).
Scripts 3_1..3_3 start the right camera, start a viewer and connect the two.
Scripts 4_1..4_4 start the emotion system and cycle emotions in a fixed sequence.
Script 6 moves the head and the eyes in a fixed sequence.

All of this was running together smoothly on Feb. 6 2014.

==Known problems==
* The ethernet adapter on the bottom of the robot does not work.
* Turning on the robot with a cable plugged into the ethernet connector in the head of the robot gets the system stuck. You can plug the cable in after boot and initialize the ethernet connection with: sudo dhclient eth0.
* Something can block one application (typically the terminal and gedit) for 10..20 seconds.
The freezing seems to be triggered both by some disk read and write operations.
The system is still responsive, the affected application freezes, other applications can also freeze at that time if they need to access the disk (I suppose).
It doesn't give problems to the demos once they have been started.
* It is common to get this USB-related error at boot time:
>>USB 3-2: device descriptor read/64, error -71
>>device not accepting addres 4, error -71
>>device not accepting addres 5, error -71
After which the system booted normally.
It seems to happen every time that the USB connector for the facial expression is connected to the board.
It might mean that the USB connectors as a whole are requiring too much current.
Even if the system is started and run without the facial expression connector plugged in, the system still freezes.

USB PEN DRIVE TEST
* I ran hdparm 4 times and got these results (with low variation):
$ sudo hdparm -tT /dev/sda
/dev/sda:
Timing cached reads: 5390 MB in 2.00 seconds = 2697.28 MB/sec
Timing buffered disk reads: 74 MB in 3.05 seconds = 24.27 MB/sec
* I tried to run "bonnie", but it didn't work.
sudo bonnie -u1000
* I used iostat, I did an "ls" after the first measurement
$iostat -dkx 5 (displays measures every 5 seconds)
Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util
sda 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
sda 0.00 13.39 0.00 0.81 0.00 56.80 140.00 0.01 9.00 4.00 0.32
sda 0.00 3.69 0.00 0.65 0.00 2.60 8.00 8.27 1216.00 716.00 46.59
sda 0.00 2.72 0.00 3.09 0.00 24.68 16.00 15.81 2809.18 294.12 90.74
sda 0.00 0.00 0.00 1.00 0.00 4.80 9.60 32.69 4841.60 1000.00 100.00
sda 0.00 0.00 0.00 2.20 0.00 11.18 10.18 25.63 10185.82 454.55 99.80
sda 0.00 0.00 0.00 2.19 0.00 17.53 16.00 12.01 13870.91 454.55 99.60
sda 0.00 0.00 0.00 1.00 0.00 4.00 8.00 5.96 20111.20 1000.00 100.00
sda 0.00 0.20 0.00 1.00 0.00 4.78 9.60 0.45 13737.60 152.00 15.14
sda 0.00 0.40 0.00 0.40 0.00 3.20 16.00 0.00 0.00 0.00 0.00

svctm = service time in milliseconds (not including the time spent in queue.
await = service time including waiting in queue. it peaks at 20 seconds!

Little data is written, almost no data is read. Lots of time is spent in queue...
Why? Could it be that the USB pen is "asleep" and needs to be woken up?

====================================================================
***Wishlist***
*Once the face detector+gaze demo was working on this platform. Maybe it could be restored with little effort.

====================================================================
***IMPROVEMENTS SINCE PREVIOUS IMAGE***
*The demos work out of the box.
*The keyboard layout is Portuguese both for the real terminals and the X session.
*The browser doesn't write chache to the disk (freezing at almost every click)
*The sources lists have been updated, so more packages can be installed.
*Added the readme file

</code>

[[Category:Robots]]
[[Category:Vislab]]

Chico head

2014-02-07T19:55:33Z

Mtaiana:

[[Image:ChicoHead.jpg|frame|left|caption|Chico head.]]
The storage memory of Chico head is a USB stick. The image for that data is on Blackhole:
smb://blackhole/database/ICUB/CHICO_BACKUP_image1.7-oc
The image can be dumped on a new USB stick with the "dd" command:
sudo dd bs=4096 if=CHICO_BACKUP_image1.7-oc.bin of=/dev/sdXXXXX
Specify the correct sd device istead of sdXXXXX (sdb, sdc or the like). Pay attention not to overwrite the wrong disk!
Before removing the USB stick, run sync to ensure that all data has been written:
rsync
People who know about the image are Ricardo Ferreira and Alex.

=readme.txt=
This is the content of the readme.txt file in the home directory of Chico head:

<code>
Log in: like the one for the iCub

====================================================================
***Demos***

To start the X server:
startx (or startxfce4)

When you are in the X interface you can open terminals and start the various processes from there.
Scripts 1 and 2 start the YARP server and the iCubInterface (used for moving the robot).
Scripts 3_1..3_3 start the right camera, start a viewer and connect the two.
Scripts 4_1..4_4 start the emotion system and cycle emotions in a fixed sequence.
Script 6 moves the head and the eyes in a fixed sequence.

All of this was running together smoothly on Feb. 6 2014.

====================================================================
***Known problems***
* The ethernet adapter on the bottom of the robot does not work.
* Turning on the robot with a cable plugged into the ethernet connector in the head of the robot gets the system stuck. You can plug the cable in after boot and initialize the ethernet connection with: sudo dhclient eth0.
* Something can block one application (typically the terminal and gedit) for 10..20 seconds.
The freezing seems to be triggered both by some disk read and write operations.
The system is still responsive, the affected application freezes, other applications can also freeze at that time if they need to access the disk (I suppose).
It doesn't give problems to the demos once they have been started.
* It is common to get this USB-related error at boot time:
>>USB 3-2: device descriptor read/64, error -71
>>device not accepting addres 4, error -71
>>device not accepting addres 5, error -71
After which the system booted normally.
It seems to happen every time that the USB connector for the facial expression is connected to the board.
It might mean that the USB connectors as a whole are requiring too much current.
Even if the system is started and run without the facial expression connector plugged in, the system still freezes.

USB PEN DRIVE TEST
* I ran hdparm 4 times and got these results (with low variation):
$ sudo hdparm -tT /dev/sda
/dev/sda:
Timing cached reads: 5390 MB in 2.00 seconds = 2697.28 MB/sec
Timing buffered disk reads: 74 MB in 3.05 seconds = 24.27 MB/sec
* I tried to run "bonnie", but it didn't work.
sudo bonnie -u1000
* I used iostat, I did an "ls" after the first measurement
$iostat -dkx 5 (displays measures every 5 seconds)
Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util
sda 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
sda 0.00 13.39 0.00 0.81 0.00 56.80 140.00 0.01 9.00 4.00 0.32
sda 0.00 3.69 0.00 0.65 0.00 2.60 8.00 8.27 1216.00 716.00 46.59
sda 0.00 2.72 0.00 3.09 0.00 24.68 16.00 15.81 2809.18 294.12 90.74
sda 0.00 0.00 0.00 1.00 0.00 4.80 9.60 32.69 4841.60 1000.00 100.00
sda 0.00 0.00 0.00 2.20 0.00 11.18 10.18 25.63 10185.82 454.55 99.80
sda 0.00 0.00 0.00 2.19 0.00 17.53 16.00 12.01 13870.91 454.55 99.60
sda 0.00 0.00 0.00 1.00 0.00 4.00 8.00 5.96 20111.20 1000.00 100.00
sda 0.00 0.20 0.00 1.00 0.00 4.78 9.60 0.45 13737.60 152.00 15.14
sda 0.00 0.40 0.00 0.40 0.00 3.20 16.00 0.00 0.00 0.00 0.00

svctm = service time in milliseconds (not including the time spent in queue.
await = service time including waiting in queue. it peaks at 20 seconds!

Little data is written, almost no data is read. Lots of time is spent in queue...
Why? Could it be that the USB pen is "asleep" and needs to be woken up?

====================================================================
***Wishlist***
*Once the face detector+gaze demo was working on this platform. Maybe it could be restored with little effort.

====================================================================
***IMPROVEMENTS SINCE PREVIOUS IMAGE***
*The demos work out of the box.
*The keyboard layout is Portuguese both for the real terminals and the X session.
*The browser doesn't write chache to the disk (freezing at almost every click)
*The sources lists have been updated, so more packages can be installed.
*Added the readme file

</code>

[[Category:Robots]]
[[Category:Vislab]]

Chico head

2014-02-07T19:53:53Z

Mtaiana:

[[Image:ChicoHead.jpg|frame|left|caption|Chico head.]]
The storage memory of Chico head is a USB stick. The image for that data is on Blackhole:
smb://blackhole/database/ICUB/CHICO_BACKUP_image1.7-oc
The image can be dumped on a new USB stick with the "dd" command:
sudo dd bs=4096 if=CHICO_BACKUP_image1.7-oc.bin of=/dev/sdXXXXX
Specify the correct sd device istead of sdXXXXX (sdb, sdc or the like). Pay attention not to overwrite the wrong disk!
Before removing the USB stick, run sync to ensure that all data has been written:
rsync
People who know about the image are Ricardo Ferreira and Alex.

=readme.txt=
This is the content of the readme.txt file in the home directory of Chico head:

Log in: like the one for the iCub

====================================================================
***Demos***

To start the X server:
startx (or startxfce4)

When you are in the X interface you can open terminals and start the various processes from there.
Scripts 1 and 2 start the YARP server and the iCubInterface (used for moving the robot).
Scripts 3_1..3_3 start the right camera, start a viewer and connect the two.
Scripts 4_1..4_4 start the emotion system and cycle emotions in a fixed sequence.
Script 6 moves the head and the eyes in a fixed sequence.

All of this was running together smoothly on Feb. 6 2014.

====================================================================
***Known problems***
* The ethernet adapter on the bottom of the robot does not work.
* Turning on the robot with a cable plugged into the ethernet connector in the head of the robot gets the system stuck. You can plug the cable in after boot and initialize the ethernet connection with: sudo dhclient eth0.
* Something can block one application (typically the terminal and gedit) for 10..20 seconds.
The freezing seems to be triggered both by some disk read and write operations.
The system is still responsive, the affected application freezes, other applications can also freeze at that time if they need to access the disk (I suppose).
It doesn't give problems to the demos once they have been started.
* It is common to get this USB-related error at boot time:
>>USB 3-2: device descriptor read/64, error -71
>>device not accepting addres 4, error -71
>>device not accepting addres 5, error -71
After which the system booted normally.
It seems to happen every time that the USB connector for the facial expression is connected to the board.
It might mean that the USB connectors as a whole are requiring too much current.
Even if the system is started and run without the facial expression connector plugged in, the system still freezes.

USB PEN DRIVE TEST
* I ran hdparm 4 times and got these results (with low variation):
$ sudo hdparm -tT /dev/sda
/dev/sda:
Timing cached reads: 5390 MB in 2.00 seconds = 2697.28 MB/sec
Timing buffered disk reads: 74 MB in 3.05 seconds = 24.27 MB/sec
* I tried to run "bonnie", but it didn't work.
sudo bonnie -u1000
* I used iostat, I did an "ls" after the first measurement
$iostat -dkx 5 (displays measures every 5 seconds)
Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util
sda 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
sda 0.00 13.39 0.00 0.81 0.00 56.80 140.00 0.01 9.00 4.00 0.32
sda 0.00 3.69 0.00 0.65 0.00 2.60 8.00 8.27 1216.00 716.00 46.59
sda 0.00 2.72 0.00 3.09 0.00 24.68 16.00 15.81 2809.18 294.12 90.74
sda 0.00 0.00 0.00 1.00 0.00 4.80 9.60 32.69 4841.60 1000.00 100.00
sda 0.00 0.00 0.00 2.20 0.00 11.18 10.18 25.63 10185.82 454.55 99.80
sda 0.00 0.00 0.00 2.19 0.00 17.53 16.00 12.01 13870.91 454.55 99.60
sda 0.00 0.00 0.00 1.00 0.00 4.00 8.00 5.96 20111.20 1000.00 100.00
sda 0.00 0.20 0.00 1.00 0.00 4.78 9.60 0.45 13737.60 152.00 15.14
sda 0.00 0.40 0.00 0.40 0.00 3.20 16.00 0.00 0.00 0.00 0.00

svctm = service time in milliseconds (not including the time spent in queue.
await = service time including waiting in queue. it peaks at 20 seconds!

Little data is written, almost no data is read. Lots of time is spent in queue...
Why? Could it be that the USB pen is "asleep" and needs to be woken up?

====================================================================
***Wishlist***
*Once the face detector+gaze demo was working on this platform. Maybe it could be restored with little effort.

====================================================================
***IMPROVEMENTS SINCE PREVIOUS IMAGE***
*The demos work out of the box.
*The keyboard layout is Portuguese both for the real terminals and the X session.
*The browser doesn't write chache to the disk (freezing at almost every click)
*The sources lists have been updated, so more packages can be installed.
*Added the readme file

[[Category:Robots]]
[[Category:Vislab]]

DollarPedestrianDetectionCode

2014-02-06T16:00:07Z

Mtaiana:

Piotr Dollár et. al. collected the [http://www.vision.caltech.edu/Image_Datasets/CaltechPedestrians/ Caltech Pedestrian Detection Benchmark], a set of data and code to evaluate pedestrian detection algorithms. The data base consists of sequences of annotated images acquired by a camera mounted on a car. The authors provide the data, some code that allow others to test their detector on that data and the results of many state-of-the-art detectors, both in a synthetic form (ROC curves), as well as in the extensive form (the actual detection bounding boxes for each image). The authors also provide other data sets and results converted to match their format.

In order to have the system running you should download Piotr's Matlab Toolbox, the Evaluation/Labelling code and the data (image sequences, ground truth bounding boxes and detection results bounding boxes). You have link to these on the main page of the [http://www.vision.caltech.edu/Image_Datasets/CaltechPedestrians/ Caltech Pedestrian Detection Benchmark]. 
For the code to work you need to have Matlab with the Image Toolbox installed.

== Getting ready ==
You should unpack the Piotr's Matlab Toolbox somewhere and add it to the Matlab Path:
addpath(genpath('/home/matteo/PMT/')); savepath;

You should unpack the Evaluation/Labelling code in a directory that we will call $code (later, you should run Matlab from that directory).

All the files (image data bases, annotations, detection results) should be put in some standard subdirectories of '''$code/'''.
You have to have one subdirectory for each db, for instance, you need one for INRIA: '''$code/data-INRIA/'''. The names are standard, they're defined in some matlab file. 
Inside the particular db directory, you need to have:
# the video subdirectory, '''$code/data-INRIA/videos''', containing more subdirectories and the ".seq" files with the images
# the annotations subdirectory, '''$code/data-INRIA/annotations''', containing more subdirectories and the ground truth annotations
# the res subdirectory, '''$code/data-INRIA/res''', containing more subdirectories with the results of the detections obtained running various algorithms

Annotations are in the format: (x0, y0, deltaX, deltaY, confidence). The confidence value is used to plot the ROC curves.
There is one annotation file for each image.
I don't know if the top-left corner is (0,0) or (1,1).

== Operations you want to do ==
=== Set the db you're working on ===
[pth,setIds,vidIds,skip,minHt] = dbInfo( 'inriatest' )
or simply:
dbInfo( 'inriatest' )

=== Show db images with annotations ===
vbbPlayer

=== Compute the ROC curves for the specified algorithms, on the current db ===
dbEval

=== Display images with GT annotations, the detections of a specific algorithm and their evaluation (true positive, false positive, etc.) ===
dbBrowser

You should set some parameters in dbBrowser.m, such as which algorithm's results you want to plot and if you want to resize the detected bounding boxes. I am not sure when you want to resize the bounding boxes, if it depends on the algorithm you are testing or on the data base you are using.
rPth=[pth '/res/HOG']; % directory containing results
thr=[]; % detection threshold
resize={100/128, 42/64, 0}; % controls resizing of detected bbs

This file writes plots in $code/results and data in $code/eval.

==How to evaluate the results of your algorithm==

You should repeat, for all the images in a given set:
# read one image
# run your classifier on it
# write the annotations in your results directory, e.g. '''$code/data-INRIA/res/myDetector/set01/V000/I00000.txt'''

Here's an example:
close all, clear;

%Add the directories where Maji code is stored to the path
addpath MajiCode/ped-demo-fast-8x8x1.1/
addpath MajiCode/libsvm-mat-2.84-1-fast.v3/

%Set parameters for Maji's code
% non max supression (similar to hog-detector)
nmax_param.sw = 0.1;
nmax_param.sh = 0.1;
nmax_param.ss = 1.3;
nmax_param.th = 0.0;

% detector is run at this scaleratio with a stride of 8x8
scaleratio = 2^(1/8);

% load precomputed models
load approx_models;
approx_model_hard = approx_models{2};
%two slightly different models (#training)

%Open the image sequence file (INRIA test set)
seqReader = seqIo( 'data-INRIA/videos/set01/V000.seq', 'reader'); %The pointer initially points to image -1, after the first sequReader.next() it points to image 1
outputDirectory = 'data-INRIA/res/MatteoMaji/set01/V000/'; %Set where to write the results
info = seqReader.getinfo();
nImages = info.numFrames;

%Run the detector on each image, store bounding boxes results (and images?)
for (imageNumber = 1 : nImages)
seqReader.next(); %Move pointer to the next image
[image, timeStamp] = seqReader.getframe(); %Get current image
[dr,ds] = run_detectorForDollar(image,approx_model_hard,scaleratio,nmax_param, outputDirectory, imageNumber-1); %Detect pedestrians (imageNumber is -1 because file numbers start from 0!)
end

Once you have you detections, you can evaluate them with '''dbEval.m''', I had to change some parameters like this:
dataNames={'InriaTest'}; %Evaluate algorithms on INRIA test

[...]

case 'InriaTest'
aIds=[7 15]; bnds=[]; %Evaluate only HIKSVM and my algorithm

[...]

case 15, alg=def('MatteoMaji',1,id); %Define the name and directory for my algorithm
%I'm not quite sure what the 1 means

After running '''dbEval.m''', you can run '''dbBrowser.m''' and compare your detection bounding boxes with the ground truth ones, inspect whether or not the evaluation software considers a detection as successful, etc.

You can change some parameters in '''dbEval.m''' so that it creates albums showing the mistakes a specific algorithm makes.
(Be careful to select only one algorithm to evaluate, otherwise you will create at least tens of albums!)

plotBb( res, rDir, 30, 'fp' ); %The third parameter tells the system how many pages of fals positives to save at most
plotBb( res, rDir, 0, 'tp' ); %If you want to save true positives
plotBb( res, rDir, 30, 'fn' ); %The third parameter tells the system how many pages of fals negatives to save at most

==Various==
=== Read one or more imags from a ".seq" file and write it to a regular file ===
Is = seqIo( 'data-INRIA/videos/set00/V000.seq', 'toImgs', '.', 1, 0, 2, 'png' )
input seq file command dest directory frames to skip first frame last frame format

=== Create seq file from a directory of images ===

seq utility: help seqIo>frImags

info.codec='jpg';
info.fps=5;
info.quality = 100;
info.width =640;
info.height =480;
seqIo('cam51.seq','frImgs', info,'sDir','/home/athira/Desktop/HDA/data_labelling/toolbox/cam51', 'f0',0,'f1',3660 )
fname command info varargin
Note: The code expects the extention of the image as '.jpg' and not '.jpeg'. So, in case if you want to use jpeg, alter the seqIo.m in line 335.(frmStr)

=== Adding a new dataset WIP ===
In order to add a new dataset to the system, you should first of all create one or more seq files.
So, create the root directory where this dataset will reside '''data-HDA''', plus the three subdirectories '''data-HDA/videos''', '''data-HDA/annotations''' and '''data-HDA/res'''.

Insert the entry relative to this dataset into the dbInfo.m script:

case 'hda'
setIds=0; %ID's of sub datasets if there are some
subdir='HDA';
skip=1; %number of frames used for subsampling during evaluation
minHt=50; %minimum labeled pedestrian height in dataset, not sure if this is used in the code somewhere or if it's just descriptive
vidIds={0}; %video ID's inside each of the sub datasets

To create a seq file staring from a video, you can use the [http://users.isr.ist.utl.pt/~mtaiana/code/createSeqFile.m createSeqFile.m] script. For some reason, the seq files created this way are not playable directly with '''vbbPlayer.m''', but it can be labelled using '''vbbLabeler.m'''. You can download a short tutorial on how to use the labeller here: [http://users.isr.ist.utl.pt/~mtaiana/temp/LabellingDemo.mkv labelling demo].

The classes for the bounding boxes are '''person''' for a single person, '''person?''' for something the labeler is not sure whether it is a person or not, '''people''' for groups of people for which it is impossible to label each person correctly. There is a label for persons who are partly occluded, it's not so clear how it works.

=== Accessing the frames of a seq file ===

%Initialize the reader
seqReader = seqIo( 'cam60.seq', 'reader');
%Read one frame
seqReader.seek(269);
image = seqReader.getframe();
imshow(image);

=== Annotating the INRIA data set again ===
It seems impossible to do it with '''vbbLabeler.m': it complains about something, like the fact that the images are not all of the same size.
So we might do that using '''bblabeler.m''', which saves the annotations in a different format, but should be useful anyway.

bbLabeler( [{'person', 'people'}], '~/PhD/datasets/INRIAPerson/Train/pos/', 'inriaNewLabels');

=== Transform all the images of a data set into a new version of it ===
Use the "convert" function on the seq file, applying imgFun(I) to each frame I:
seqIo( fName, 'convert', tName, imgFun, varargin )

Chico head

2014-02-05T16:04:00Z

Mtaiana:

Darwin

2014-02-05T15:56:09Z

Mtaiana: /* Crude instructions for running a demo */

[[Image:Darwin-op.jpg|frame|right|caption|Components of the DARwIn-OP robot.]]

Robotis DARwIn-OP (Dynamic Anthropomorphic Robot with Intelligence – Open Platform) is a humanoid robot platform which weighs approximately 3 kg and is about 45 cm tall. Sponsored by the National Science Foundation (NSF) in the United States, DARwIn-OP is developed by RoMeLa at Virginia Tech in collaboration with Purdue University, University of Pennsylvania, and Robotis Co.

DARwIn-OP is an open platform where users are encouraged to modify it in both hardware and software, and various software implementations are possible (C++, Python, LabVIEW, MATLAB, etc.) The open source hardware is not only user serviceable thanks to its modular design, but also can be fabricated by the user. Publicly open CAD files for all of its parts, and instructions manuals for fabrication and assembly are available on-line for free. DARwIn-OP can also be purchased from Robotis as a product.

= Crude instructions for running a demo =
* Extract Darwin from the box
* Connect power cable
* Hold Darwin in standing position and press the power switch to turn it on. It activates the joints and assumes a "squatting position" while it turns on.
* Wait for many LEDs to turn on on the back of the robot. When the initialization finishes, it says something.
* Click the "mode" button, Darwin should say: "Soccer demo".
* Click the "play" button.
* Put a red object in front of the robot to play.
* To stop the robot, click on the "mode" button again.
* Then click a button on the front of the robot to shut down the internal system. It's a hidden button, the lower "hole" on the right side of the robot chest.
* Eventually, move the power switch on the back of the robot to the off position.

= See also =

* http://darwin-op.springnote.com/
* http://support.robotis.com/
* http://sourceforge.net/projects/darwinop/
* http://www.robotis-shop-en.com/shop/step1.php?number=914#good1

[[Category:Robots]]
[[Category:Vislab]]

Nao

2014-02-04T15:20:29Z

Mtaiana:

Chico head

2014-02-04T15:17:27Z

Mtaiana:

The data is hosted on a USB stick. The image for that data is on Blackhole:
smb://blackhole/database/ICUB/CHICO_BACKUP_image1.7-oc
The image can be dumped on a new USB stick with the "dd" command:
sudo dd bs=4096 if=CHICO_BACKUP_image1.7-oc.bin of=/dev/sdXXXXX
Specify the correct sd device istead of sdXXXXX (sdb, sdc or the like). Pay attention not to overwrite the wrong disk!
Before removing the USB stick, run sync to ensure that all data has been written:
rsync
People who know about the image are Ricardo Ferreira and Alex.

Main Page

2014-02-04T15:15:50Z

Mtaiana: /* Research */ Added Chico head to the list of robots.

<big>'''Welcome to the MediaWiki space of the [http://www.isr.ist.utl.pt Institute for Systems and Robotics].'''</big>

== Opportunities ==

=== Current ===

=== Past ===

* [[BII 2009]]
* [[Dissertation/Project proposals]]
* [[BII 2008]]

== Research ==

* bureaucracy: [[Prospective PhD students]]
* [[Vislab | Computer and Robot Vision Lab (VisLab)]]
** robots: [[Chica]], [[Chico]], [[Chico head]], [[Darwin]], [[Nao]], [[Vizzy]]
** archive: [[VisLab logbook]], [[VisLab Videos]], [[VisLab Proceedings]], [[VisLab Meetings]]
** datasets: [[Multiple View Tracking]]
** demos: [[Affordance imitation]], '''[[iCub demos]]''', [[Cyberglove Remote Control]]
** hardware: [[Chico3 laptop machine configuration]], [[Cortex]], [[iCubBrain server configuration]], [[Kinect]], [[pc104]], [[vislab8]] (NVIDIA Tesla GPGPU), [[OptiTrack]]
** software: [[VisLab machines configuration]], [[VisLab network]], [[RobotCub coding basics]], '''[[RobotCub software]], '''[[Poeticon software]]
** misc: [[Acknowledgements for papers]]
* [[Intelligent Robots and Systems Group]]
** robots: [[RAPOSA robot|RAPOSA]], [[ISR Bioloid Humanoid|Bioloid]], [[ISR-CoBot]]
* [[Lisbon-K Chromosome Dataset]]
* [[International conferences deadlines]]
* [[Journals]]
* [[Computer Vision Journals RSS feeds]]
* European Projects: [[Recommendations for European Project Proposals]]
* [[Introduction to ROS]]
** [http://ftp.isr.ist.utl.pt/pub/roswiki/ Local mirror of ROS wiki]

== Teaching ==

* [[Robotics lab resources]]
* [[Autonomous Systems resources]]
* [[Discrete Event Dynamic Systems resources]]
* [[Artificial Intelligence and Decision Systems resources]]

== Events ==

=== Ongoing ===

=== Past ===

* [[Ocupação Científica de Jovens nas Férias 2013]]
* [[Summer course on ROS framework 2013]]
* [[Ocupação Científica de Jovens nas Férias 2012]]
* [[Ocupação Científica de Jovens nas Férias 2011]]
* [[Ocupação Científica de Jovens nas Férias 2010]]
* [http://vislab.isr.ist.utl.pt/RLSS09 RLSS09: Robot Learning Summer School]
* [[Ocupação Científica de Jovens nas Férias 2009]]
* [[Lisbon Workshop on New Challenges for Cooperative Robotics]]

== Computing ==

* [[ISR computing resources]]
* [[Macintosh resources]] (incl. useful tips)
* [[Python resources]]

== Misc ==

* [[Administrative checklist]] (internal use only) -- '''check here for all rules concerning purchases, conference trips, paper credits, etc.'''
* [http://library.isr.ist.utl.pt/isr/logo/ ISR logos]
* [[ISR_meeting_room]]
* [[List of restaurants]]
* [http://wiki.isr.ist.utl.pt Former ISR wiki pages]
* Use this [[SandBox]] for experimentation with MediaWiki

Chico head

2014-02-04T15:14:53Z

Mtaiana:

The data is hosted on a USB stick. The image for that data is on Blackhole:
smb://blackhole/database/ICUB/CHICO_BACKUP_image1.7-oc
The image can be dumped on a new USB stick with the "dd" command:
sudo dd bs=4096 if=CHICO_BACKUP_image1.7-oc.bin of=/dev/sdXXXXX
Specify the correct sd device istead of sdXXXXX (sdb, sdc or the like). Pay attention not to overwrite the wrong disk!

People who know about the image are Ricardo Ferreira and Alex.

Chico head

2014-02-04T15:14:02Z

Mtaiana: Created page with "The data is hosted on a USB stick. The image for that data is on Blackhole: smb://blackhole/database/ICUB/CHICO_BACKUP_image1.7-oc The image can be dumped on a new USB stick wi..."