ROS Resources: Documentation | Support | Discussion Forum | Index | Service Status | ros @ Robotics Stack Exchange

Attention: Answers.ros.org is deprecated as of August the 11th, 2023. Please visit robotics.stackexchange.com to ask a new question. This site will remain online in read-only mode during the transition and into the foreseeable future. Selected questions and answers have been migrated, and redirects have been put in place to direct users to the corresponding questions on Robotics Stack Exchange. Additional details are available here.

0

High Number of False Positives

asked 2019-08-21 05:35:56 -0500

nisa20
3 ●2 ●3 ●3

Hi,

I am a Portuguese Master Degree's student and I am currently developing my Master Thesis which Theme is "People Detection from Laser Range Data".

I have already developed my Detector and I have already got results from a bunch of bagfiles that I recorded with a MOnarCH robot, but now I need to compare them to see if my method is, at least, acceptable.

To that matter I am using your leg_detector however, for a Bagfile with only one static people in the scenario under analysis all the time, leg_detector sees at least 10.

This results are obtained by echoing the topic (people_tracker_measurements).

The following link is for you to download the bagfile that I have recorded if you want to check the results, mentioned above, by yourself.

Link for the bagfile: https://we.tl/t-cHJUWUfffW

Thanks in advance.

edit retag flag offensive close merge delete

1 Answer

Sort by » oldest newest most voted

0

answered 2019-09-05 11:06:13 -0500

flag of United States of America

10932 ●123 ●219 ●250 http://MetroRobots.com/

In my usage of the leg detector, I too found that it had a high number of false positives. My usual solution was to ignore laser points that matched the static map using map_laser

edit flag offensive delete link

Question Tools

2 followers

Stats

Asked: 2019-08-21 05:35:56 -0500

Seen: 286 times

Last updated: Sep 05 '19

Related questions

ROS Answers is licensed under Creative Commons Attribution 3.0 Content on this site is licensed under a Creative Commons Attribution Share Alike 3.0 license.

Powered by Askbot version 0.10.2