RNN_LSTM: RNN Tracker


Benchmark:

Short name:

RNN_LSTM

Detector:

Public

Description:

We present a novel approach to online multi-target tracking based on
recurrent neural networks (RNNs). Tracking multiple objects in
real-world scenes involves many challenges, including a) an a-priori
unknown and time-varying number of targets, b) a continuous state
estimation of all present targets, and c) a discrete combinatorial
problem of data association. Most previous methods involve complex
models that require tedious tuning of parameters. Here, we propose for
the first time, a full end-to-end learning approach for online
multi-target tracking based on deep learning. Existing deep learning
methods are not designed for the above challenges and cannot be
trivially applied to the task. Our solution addresses all of the above
points in a principled way. Experiments on both synthetic and real data
show competitive results obtained at 300 Hz on a standard CPU, and pave
the way towards future research in this direction.

Project page / code:

Reference:

A. Milan, S. Rezatofighi, A. Dick, I. Reid, K. Schindler. Online Multi-Target Tracking using Recurrent Neural Networks. In AAAI, 2017.

Processing:

Online

Last submitted:

March 15, 2016 (4 years ago)

Published:

March 15, 2016 at 08:24:33 CET

Submissions:

2

Open source:

Yes

Hardware:

3 GHz, 1 CPU

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
2D MOT 201519.017.171.040.0329.011,57836,7061,490

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
ADL-Rundle-1-2.220.669.96.08.04,2135,058241
ADL-Rundle-323.723.772.03.09.02,1935,407158
AVG-TownCentre13.46.968.88.093.01,2064,682299
ETH-Crossing21.116.175.50.015.0277577
ETH-Jelmoli34.816.673.38.013.03141,28059
ETH-Linthescher12.44.774.73.0157.01647,60949
KITTI-1626.327.268.50.02.029089667
KITTI-1917.711.568.34.016.01,3882,818191
PETS09-S2L238.318.671.64.06.01,0164,611320
TUD-Crossing57.234.671.74.02.08134843
Venice-112.722.771.70.08.06863,24056

Raw data:


RNN_LSTM