Robotics StackExchange | Archived questions

High Number of False Positives

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 legdetector however, for a Bagfile with only one static people in the scenario under analysis all the time, legdetector sees at least 10.

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

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.

Asked by nisa20 on 2019-08-21 05:35:56 UTC

Comments

Answers

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

Asked by David Lu on 2019-09-05 11:06:13 UTC

Comments