Search: id:"swepub:oai:DiVA.org:oru-91362" >
Learning Occupancy ...
Learning Occupancy Priors of Human Motion From Semantic Maps of Urban Environments
-
- Rudenko, Andrey, 1991- (author)
- Örebro universitet,Institutionen för naturvetenskap och teknik,Bosch Corporate Research, Renningen, Germany,Mobile Robotics and Olfaction Lab
-
- Palmieri, Luigi (author)
- Bosch Corporate Research, Renningen, Germany
-
- Doellinger, Johannes (author)
- Bosch Center for Artificial Intelligence, Renningen, Germany
-
show more...
-
- Lilienthal, Achim, 1970- (author)
- Örebro universitet,Institutionen för naturvetenskap och teknik,Mobile Robotics and Olfaction Lab
-
- Arras, Kai O. (author)
- Bosch Corporate Research, Renningen, Germany
-
show less...
-
(creator_code:org_t)
- IEEE, 2021
- 2021
- English.
-
In: IEEE Robotics and Automation Letters. - : IEEE. - 2377-3766. ; 6:2, s. 3248-3255
- Related links:
-
https://urn.kb.se/re...
-
show more...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- Understanding and anticipating human activity is an important capability for intelligent systems in mobile robotics, autonomous driving, and video surveillance. While learning from demonstrations with on-site collected trajectory data is a powerful approach to discover recurrent motion patterns, generalization to new environments, where sufficient motion data are not readily available, remains a challenge. In many cases, however, semantic information about the environment is a highly informative cue for the prediction of pedestrian motion or the estimation of collision risks. In this work, we infer occupancy priors of human motion using only semantic environment information as input. To this end, we apply and discuss a traditional Inverse Optimal Control approach, and propose a novel approach based on Convolutional Neural Networks (CNN) to predict future occupancy maps. Our CNN method produces flexible context-aware occupancy estimations for semantically uniform map regions and generalizes well already with small amounts of training data. Evaluated on synthetic and real-world data, it shows superior results compared to several baselines, marking a qualitative step-up in semantic environment assessment.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
Keyword
- Deep learning for visual perception
- human detection and tracking
- human motion analysis
- human motion prediction
- semantic scene understanding
Publication and Content Type
- ref (subject category)
- art (subject category)
Find in a library
To the university's database