Reinforcement Learning inspired Deep Learned Compositional Model for Decision Making in Tracking

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F18%3A10244478" target="_blank" >RIV/61989100:27240/18:10244478 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/8718691" target="_blank" >https://ieeexplore.ieee.org/document/8718691</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICRCICN.2018.8718691" target="_blank" >10.1109/ICRCICN.2018.8718691</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Reinforcement Learning inspired Deep Learned Compositional Model for Decision Making in Tracking

Popis výsledku v původním jazyce

We formulate a tracker which performs incessant decision making in order to track objects where the objects may undergo different challenges such as partial occlusions, moving camera, cluttered background etc. In the process, the agent must make a decision on whether to keep track of the object when it is occluded or has moved out of the frame temporarily based on its prediction from the previous location or to reinitialize the tracker based on the belief that the target has been lost. Instead of the heuristic methods we depend on reward and penalty based training that helps the agent reach an optimal solution via this partially observable Markov decision making (POMDP). Furthermore, we employ deeply learned compositional model to estimate human pose in order to better handle occlusion without needing human inputs. By learning compositionality of human bodies via deep neural network the agent can make better decision on presence of human in a frame or lack thereof under occlusion. We adapt skeleton based part representation and do away with the large spatial state requirement. This especially helps in cases where orientation of the target in focus is unorthodox. Finally we demonstrate that the deep reinforcement learning based training coupled with pose estimation capabilities allows us to train and tag multiple large video datasets much quicker than previous works

Název v anglickém jazyce

Reinforcement Learning inspired Deep Learned Compositional Model for Decision Making in Tracking

Popis výsledku anglicky

We formulate a tracker which performs incessant decision making in order to track objects where the objects may undergo different challenges such as partial occlusions, moving camera, cluttered background etc. In the process, the agent must make a decision on whether to keep track of the object when it is occluded or has moved out of the frame temporarily based on its prediction from the previous location or to reinitialize the tracker based on the belief that the target has been lost. Instead of the heuristic methods we depend on reward and penalty based training that helps the agent reach an optimal solution via this partially observable Markov decision making (POMDP). Furthermore, we employ deeply learned compositional model to estimate human pose in order to better handle occlusion without needing human inputs. By learning compositionality of human bodies via deep neural network the agent can make better decision on presence of human in a frame or lack thereof under occlusion. We adapt skeleton based part representation and do away with the large spatial state requirement. This especially helps in cases where orientation of the target in focus is unorthodox. Finally we demonstrate that the deep reinforcement learning based training coupled with pose estimation capabilities allows us to train and tag multiple large video datasets much quicker than previous works

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2018

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings - 2018 4th IEEE International Conference on Research in Computational Intelligence and Communication Networks, ICRCICN 2018

ISBN

978-1-5386-7638-7

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

158-163

Název nakladatele

IEEE

Místo vydání

Vienna

Místo konání akce

Kolkata

Datum konání akce

22. 11. 2018

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000474789200030