Filters








220,824 Hits in 8.2 sec

From Motion Observation to Qualitative Motion Representation [chapter]

Alexandra Musto, Klaus Stein, Andreas Eisenkolb, Thomas Röfer, Wilfried Brauer, Kerstin Schill
2000 Lecture Notes in Computer Science  
Abstraction is the key for the generation of qualitative representations from observed data.  ...  This paper deals with the conversion of motion data into qualitative representations, and it presents a new generalization algorithm that abstracts from irrelevant details of a course of motion.  ...  From Motion Observation to Qualitative Motion Representation. In: Freksa, Ch., Brauer, W., Habel, Ch., Wender, K. F. (Eds.): Spatial Cognition II. Lecture Notes in Artificial Intelligence 1849.  ... 
doi:10.1007/3-540-45460-8_9 fatcat:kxnlhm2c4zhptgpwmzxvydlaea

Acquisition of Qualitative Spatial Representation by Visual Observation

Takushi Sogo, Hiroshi Ishiguro, Toru Ishida
1999 International Joint Conference on Artificial Intelligence  
This paper proposes a method for reconstructing qualitative positions of multiple vision sensors from qualitative information observed by the vision sensors, i.e., motion directions of moving objects.  ...  The process iterates the following steps: (1) observing motion directions of moving objects from the vision sensors, (2) classifying the vision sensors into spatially classified pairs, (3) acquiring three  ...  Conclusion This paper has proposed a method for acquiring a qualitative spatial representation from qualitative motion information of moving objects.  ... 
dblp:conf/ijcai/SogoII99 fatcat:rpzum6tpvzfwrhddup4swgjtpi

Acquisition and propagation of spatial constraints based on qualitative information

T. Sogo, H. Ishiguro, T. Ishida
2001 IEEE Transactions on Pattern Analysis and Machine Intelligence  
This paper proposes a method for reconstructing qualitative positions of multiple vision sensors from qualitative information observed by the vision sensors, i.e., motion directions of moving objects.  ...  Compared with the previous methods, which reconstruct the environment structure from quantitative measurements and acquire qualitative representations by abstracting it, this paper focuses on how to acquire  ...  Qualitative Observation The qualitative spatial model is acquired by observing motion directions of moving objects from each point.  ... 
doi:10.1109/34.910879 fatcat:3f2m36sn5nh7xforsdkruuhseu

AAAI-90 Workshop on Qualitative Vision

William Lim, Philip Kahn, Daphna Weinshall, Andrew Blake
1991 The AI Magazine  
In particular, we would like to thank ADS for printing the workshop proceedings and making them available to the research community.  ...  Acknowledgments We would like to thank the reviewers for their time and guidance.  ...  Observer motion is estimated qualitatively by comparing against robust characteristics of a small set of prototype motion. The second method does not require the observer motion to be known.  ... 
doi:10.1609/aimag.v12i4.922 dblp:journals/aim/LimKWB91 fatcat:gssqvq6lbzdjrkfiirhxn6567i

Fuzzy Qualitative Human Motion Analysis

Chee Seng Chan, Honghai Liu
2009 IEEE transactions on fuzzy systems  
Second, a novel human motion representation, i.e., qualitative normalized template, is developed in terms of the fuzzy qualitative robot kinematics framework to effectively represent human motion.  ...  This paper proposes a fuzzy qualitative approach to vision-based human motion analysis with an emphasis on human motion recognition.  ...  Second, a novel human-motion representation, known as qualitative normalized template (QNT), is developed in terms of the fuzzy qualitative robot kinematics framework [19] to effectively represent human  ... 
doi:10.1109/tfuzz.2009.2016553 fatcat:cak5vdpouzcbtjrupshghx32ya

Perceptual Narratives of Space and Motion for Semantic Interpretation of Visual Data [chapter]

Jakob Suchan, Mehul Bhatt, Paulo E. Santos
2015 Lecture Notes in Computer Science  
The theory provides primitives for commonsense representation and reasoning with qualitative spatial relations, depth profiles, and spatio-temporal change; these may be combined with probabilistic methods  ...  We propose a commonsense theory of space and motion for the high-level semantic interpretation of dynamic scenes.  ...  QSTR -Qualitative Spatial and Temporal Reasoning Qualitative Spatial & Temporal Representation and Reasoning (QSTR) [28] abstracts from an exact numerical representation by describing the relations between  ... 
doi:10.1007/978-3-319-16181-5_24 fatcat:gcrh3sjjtzdavllpcscf4hnydm

A Novel Method for Acquiring Engineering-Oriented Operational Empirical Knowledge

Lijun Liu, Zuhua Jiang, Bo Song, Hongyuan Zhu, Xinyu Li
2016 Mathematical Problems in Engineering  
In this paper we propose a concept of engineering-oriented operational empirical knowledge (OEK) to describe this kind of knowledge and design a framework to acquire OEK from skilled technician's operations  ...  The framework integrates motion analysis, motion elicitation, and intent analysis.  ...  Acknowledgments The authors are most grateful to National Natural Science  ... 
doi:10.1155/2016/9754298 fatcat:yqs7msowpbaj3igfuwhb3m327y

H4D: Human 4D Modeling by Learning Neural Compositional Representation [article]

Boyan Jiang, Yinda Zhang, Xingkui Wei, Xiangyang Xue, Yanwei Fu
2022 arXiv   pre-print
Technically, we introduce novel GRU-based architectures to facilitate learning and improve the representation capability.  ...  This work presents a novel framework that can effectively learn a compact and compositional representation for dynamic human by exploiting the human body prior from the widely used SMPL parametric model  ...  Motion Completion Our representation can also fulfill fitting tasks in the auto-decoding fashion, in which the SMPL parameters and latent codes are optimized to produce output similar to the observation  ... 
arXiv:2203.01247v2 fatcat:rd62hdvrg5ccxdcc4s7bqpjkwa

Cognitive Interpretation of Everyday Activities: Toward Perceptual Narrative Based Visuo-Spatial Scene Interpretation [article]

Mehul Bhatt, Jakob Suchan, Carl Schultz
2013 arXiv   pre-print
Our proposed narrative model encompasses aspects such as space, events, actions, change, and interaction from the viewpoint of commonsense reasoning and learning in large-scale cognitive systems.  ...  structures, Motion, Perceptual reasoning, Shape, Video analysis General keywords: cognitive systems; human-computer interaction; spatial cognition and computation; commonsense reasoning; spatial and temporal  ...  of motion as qualitative spatial change [Galton, 2000] .  ... 
arXiv:1306.5308v1 fatcat:jxqphtmqrjaz3i77dvgeiklwoq

Optical Flow Regularization of Implicit Neural Representations for Video Frame Interpolation [article]

Weihao Zhuang, Tristan Hascoet, Ryoichi Takashima, Tetsuya Takiguchi
2022 arXiv   pre-print
We achieve state of the art VFI on limited motion ranges using only a target video and its optical flow, without learning the interpolation operator from additional training data.  ...  Recent works have shown the ability of Implicit Neural Representations (INR) to carry meaningful representations of signal derivatives.  ...  Plots from (a) to (d) show both the observed and interpolated frames PSNR while plot (e) only shows the interpolated frames PSNR. Figure 5 : 5 Figure 5: Small Motion Video Qualitative Analysis.  ... 
arXiv:2206.10886v1 fatcat:74a4s2rhknh2bnsyfofvbhtj2u

Cognitive Interpretation of Everyday Activities - Toward Perceptual Narrative Based Visuo-Spatial Scene Interpretation

Mehul Bhatt, Jakob Suchan, Carl Schultz, Marc Herbstritt
2013 Workshop on Computational Models of Narrative  
We position a narrative-centred computational model for high-level knowledge representation and reasoning in the context of a range of assistive technologies concerned with visuo-spatial perception and  ...  Our proposed narrative model encompasses aspects such as space, events, actions, change, and interaction from the viewpoint of commonsense reasoning and learning in large-scale cognitive systems.  ...  interpretation of motion as qualitative spatial change [9] .  ... 
doi:10.4230/oasics.cmn.2013.24 dblp:conf/cmn/BhattSS13 fatcat:yu76luhe4ravldyymglafnf2ry

Animating Arbitrary Objects via Deep Motion Transfer [article]

Aliaksandr Siarohin, Stéphane Lathuilière, Sergey Tulyakov, Elisa Ricci, Nicu Sebe
2019 arXiv   pre-print
keypoints, in order to better encode motion information and (iii) a Motion Transfer Network, which uses the motion heatmaps and appearance information extracted from the input image to synthesize the  ...  Our framework consists of three main modules: (i) a Keypoint Detector unsupervisely trained to extract object keypoints, (ii) a Dense Motion prediction network for generating dense heatmaps from sparse  ...  This consists in reconstructing the input video from a representation in which motion and content are decoupled.  ... 
arXiv:1812.08861v3 fatcat:ra7ulibqgrflzevkxvt3zcisii

Decomposing Motion and Content for Natural Video Sequence Prediction [article]

Ruben Villegas, Jimei Yang, Seunghoon Hong, Xunyu Lin, Honglak Lee
2018 arXiv   pre-print
Our model is end-to-end trainable over multiple time steps, and naturally learns to decompose motion and content without separate training.  ...  To effectively handle complex evolution of pixels in videos, we propose to decompose the motion and content, two key components generating dynamics in videos.  ...  ACKNOWLEDGEMENTS This work was supported in part by ONR N00014-13-1-0762, NSF CAREER IIS-1453651, gifts from the Bosch Research and Technology Center, and Sloan Research Fellowship.  ... 
arXiv:1706.08033v2 fatcat:pq3eirkmn5cehplol4zmtbhska

Representation Strategies in Two-handed Melodic Sound-Tracing

Tejaswinee Kelkar, Alexander Refsum Jensenius
2017 Proceedings of the 4th International Conference on Movement Computing - MOCO '17  
We observe these strategies and present their typology through qualitative analysis. en we numerically verify the consistency of these strategies by conducting tests of signi cance between labeled and  ...  is paper describes an experiment in which the subjects performed a sound-tracing task to vocal melodies. ey could move freely in the air with two hands, and their motion was captured using an infrared,  ...  QUALITATIVE OBSERVATIONS Based on a qualitative observation of the data, we propose six schemes of representation that encompass most of the variation in the hands' motion, as illustrated in Figure 2  ... 
doi:10.1145/3077981.3078050 dblp:conf/moco/KelkarJ17 fatcat:n3bm2vlzcvd5npfactr67zp6e4

Computer vision methods for robot tasks: Motion detection, depth estimation and tracking

E. Martínez-Martín
2012 AI Communications  
However, it is not easy to identify what is seen from the provided visual input. On this regard, inspired by humans, we have studied motion as a primary cue.  ...  Particularly, we present a computational solution for motion detection, object location and tracking from images captured by perspective and fisheye cameras.  ...  quantitative and a qualitative point of view, and the design of a new object representation leading to a reliable tracking process.  ... 
doi:10.3233/aic-2012-0520 fatcat:57rmryqemzg7fprb5s26i5lmdm
« Previous Showing results 1 — 15 out of 220,824 results