An RNN-Based IMM Filter Surrogate

被引：6

作者：

Becker, Stefan ^{[1
]}

Hug, Ronny ^{[1
]}

Huebner, Wolfgang ^{[1
]}

Arens, Michael ^{[1
]}

机构：

[1] Fraunhofer Inst Optron Syst Technol & Image Explo, Gutleuthausstr 1, D-76275 Ettlingen, Germany

来源：

IMAGE ANALYSIS | 2019年 / 11482卷

关键词：

Trajectory forecasting; Path prediction; IMM filter; Multiple model filter;

D O I：

10.1007/978-3-030-20205-7_32

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

The problem of varying dynamics of tracked objects, such as pedestrians, is traditionally tackled with approaches like the Interacting Multiple Model (IMM) filter using a Bayesian formulation. By following the current trend towards using deep neural networks, in this paper an RNN-based IMM filter surrogate is presented. Similar to an IMM filter solution, the presented RNN-based model assigns a probability value to a performed dynamic and, based on them, puts out a multi-modal distribution over future pedestrian trajectories. The evaluation is done on synthetic data, reflecting prototypical pedestrian maneuvers.

引用

页码：387 / 398

页数：12

共 27 条

[1] Abadi M., 2015, P 12 USENIX S OPERAT
[2] Social LSTM: Human Trajectory Prediction in Crowded Spaces
Alahi, Alexandre
Goel, Kratarth
Ramanathan, Vignesh
Robicquet, Alexandre
Li Fei-Fei
Savarese, Silvio
[J]. 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 961 - 971
[3] A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking
Arulampalam, MS
Maskell, S
Gordon, N
Clapp, T
[J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2002, 50 (02) : 174 - 188
[4] Bar -Shalom Y., 2004, Estimation with Applications to Tracking and Navigation: Theory Algorithms and Software
[5] RED: A Simple but Effective Baseline Predictor for the TrajNet Benchmark
Becker, Stefan
Hug, Ronny
Huebner, Wolfgang
Arens, Michael
[J]. COMPUTER VISION - ECCV 2018 WORKSHOPS, PT III, 2019, 11131 : 138 - 153
[6] State estimation for tracking in image space with a de- and re-coupled IMM filter
Becker, Stefan
Hubner, Wolfgang
Arens, Michael
[J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2018, 77 (15) : 20207 - 20226
[7] Detecting Abandoned Objects using Interacting Multiple Models
Becker, Stefan
Muench, David
Kieritz, Hilke
Huebner, Wolfgang
Arens, Michael
[J]. OPTICS AND PHOTONICS FOR COUNTERTERRORISM, CRIME FIGHTING, AND DEFENCE XI; AND OPTICAL MATERIALS AND BIOMATERIALS IN SECURITY AND DEFENCE SYSTEMS TECHNOLOGY XII, 2015, 9652
[8] THE INTERACTING MULTIPLE MODEL ALGORITHM FOR SYSTEMS WITH MARKOVIAN SWITCHING COEFFICIENTS
BLOM, HAP
BARSHALOM, Y
[J]. IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1988, 33 (08) : 780 - 783
[9] Chung Junyoung, 2015, Advances in Neural Information Processing Systems, P2980, DOI DOI 10.48550/ARXIV.1506.02216
[10] Deo N, 2018, IEEE INT VEH SYM, P1179, DOI 10.1109/IVS.2018.8500493

← 1 2 3 →