[robotics-worldwide] [news] New Large-Scale Stereo Video Dataset and Benchmark for Off-Road Person Detection

classic Classic list List threaded Threaded
1 message Options
Reply | Threaded
Open this post in threaded view
|

[robotics-worldwide] [news] New Large-Scale Stereo Video Dataset and Benchmark for Off-Road Person Detection

Zach Pezzementi
We are pleased to announce the availability of the National Robotics Engineering Center (NREC) Agricultural Person Detection Dataset for download here:
https://urldefense.proofpoint.com/v2/url?u=http-3A__www.nrec.ri.cmu.edu_solutions_agriculture_human-2Ddetection-2Dand-2Dtracking.html&d=DwIGaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=tfigQ9YSI_i7KV-KDfEv67SwlM8DXoXZoh0A3p-H0i0&s=Zz6cWsiiQtiAGHbAwrJoCIMjjdVf1ESybBOrDHshpxI&e=

It consists of labeled stereo video of people in orange and apple orchards taken from two perception platforms (a tractor and a pickup truck), along with vehicle position data from RTK GPS. We define a benchmark on part of the dataset that combines a total of 76k labeled person images and 19k sampled person-free images. The dataset highlights several key challenges of the domain, including varying environment, substantial occlusion by vegetation, people in motion and in nonstandard poses, and people seen from a variety of distances; metadata are included to allow targeted evaluation of each of these effects.

For details, please see our paper in the Journal of Field Robotics:

Pezzementi Z, Tabor T, Hu P, et al. Comparing apples and oranges: Off-road pedestrian detection on the National Robotics Engineering Center agricultural person-detection dataset. J Field Robotics. 2017;1–19. https://urldefense.proofpoint.com/v2/url?u=https-3A__doi.org_10.1002_rob.21760&d=DwIGaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=tfigQ9YSI_i7KV-KDfEv67SwlM8DXoXZoh0A3p-H0i0&s=JFQVgKrWmv4X1J2cPfS6HuURSoWS_2i-9oAq1iaIvCM&e=

or the arXiv version here: https://urldefense.proofpoint.com/v2/url?u=https-3A__arxiv.org_abs_1707.07169&d=DwIGaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=tfigQ9YSI_i7KV-KDfEv67SwlM8DXoXZoh0A3p-H0i0&s=9-VNi91Y86cLeNvKFIfwbcVfbbL67Ws_4eXe5ouqYG0&e=

Download info and the latest results on the associated benchmark can be found on the National Robotics Engineering Center project page here:
https://urldefense.proofpoint.com/v2/url?u=http-3A__www.nrec.ri.cmu.edu_solutions_agriculture_human-2Ddetection-2Dand-2Dtracking.html&d=DwIGaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=tfigQ9YSI_i7KV-KDfEv67SwlM8DXoXZoh0A3p-H0i0&s=Zz6cWsiiQtiAGHbAwrJoCIMjjdVf1ESybBOrDHshpxI&e=

--
Zachary Pezzementi
Senior Robotics Engineer

National Robotics Engineering Center
Carnegie Mellon University

Email: [hidden email]<mailto:[hidden email]>


_______________________________________________
robotics-worldwide mailing list
[hidden email]
http://duerer.usc.edu/mailman/listinfo.cgi/robotics-worldwide