Journal ArticleDOI
Granular Flow Graph, Adaptive Rule Generation and Tracking
Reads0
Chats0
TLDR
A new method of adaptive rule generation in granular computing framework is described based on rough rule base and granular flow graph, and applied for video tracking, and it is shown that the neighborhood granulation provides a balanced tradeoff between speed and accuracy as compared to pixel level computation.Abstract:
A new method of adaptive rule generation in granular computing framework is described based on rough rule base and granular flow graph, and applied for video tracking. In the process, several new concepts and operations are introduced, and methodologies formulated with superior performance. The flow graph enables in defining an intelligent technique for rule base adaptation where its characteristics in mapping the relevance of attributes and rules in decision-making system are exploited. Two new features, namely, expected flow graph and mutual dependency between flow graphs are defined to make the flow graph applicable in the tasks of both training and validation. All these techniques are performed in neighborhood granular level. A way of forming spatio-temporal 3-D granules of arbitrary shape and size is introduced. The rough flow graph-based adaptive granular rule-based system, thus produced for unsupervised video tracking, is capable of handling the uncertainties and incompleteness in frames, able to overcome the incompleteness in information that arises without initial manual interactions and in providing superior performance and gaining in computation time. The cases of partial overlapping and detecting the unpredictable changes are handled efficiently. It is shown that the neighborhood granulation provides a balanced tradeoff between speed and accuracy as compared to pixel level computation. The quantitative indices used for evaluating the performance of tracking do not require any information on ground truth as in the other methods. Superiority of the algorithm to nonadaptive and other recent ones is demonstrated extensively.read more
Citations
More filters
Journal ArticleDOI
Granular computing for data analytics: a manifesto of human-centric computing
TL;DR: This study identifies the principles of Granular Computing, shows how information granules are constructed and subsequently used in describing relationships present among the data, and advocates that the level of abstraction can be flexibly adjusted through Granular computing.
Journal ArticleDOI
Deep learning in multi-object detection and tracking: state of the art
TL;DR: In this article, the authors provide a comprehensive overview of object detection and tracking using deep learning (DL) networks and compare the performance of different object detectors and trackers, including the recent development in granulated DL models.
Journal ArticleDOI
Attribute-Driven Granular Model for EMG-Based Pinch and Fingertip Force Grand Recognition
TL;DR: An attribute-driven granular model (AGrM) under a machine-learning scheme that achieved comparable pinch recognition accuracy but was of lowest computational cost and highest force grand prediction accuracy.
Journal ArticleDOI
Boosted K-nearest neighbor classifiers based on fuzzy granules
Wei Li,Yumin Chen,Yuping Song +2 more
TL;DR: Theoretical analysis and experimental results show that FGKNN and BFGKNN have better performance than that of the methods mentioned above if the appropriate parameters are given.
Journal ArticleDOI
Granulated deep learning and Z-numbers in motion detection and object recognition
TL;DR: The article deals with the problems of motion detection, object recognition, and scene description using deep learning in the framework of granular computing and Z-numbers and shows a balanced trade-off between speed and accuracy as compared to pixel level learning in tracking and recognition.
References
More filters
Journal ArticleDOI
Nonlinear Dynamic Model for Visual Object Tracking on Grassmann Manifolds With Partial Occlusion Handling
TL;DR: Experiments using the proposed tracker on videos captured by a single dynamic/static camera have shown robust tracking performance, particularly for scenarios when target objects contain significant nonplanar pose changes and long-term partial occlusions.
Journal ArticleDOI
Measures of Effective Video Tracking
TL;DR: This paper proposes three parameter-independent measures for evaluating multitarget video tracking that consider target-size variations, combine accuracy and cardinality errors, quantify long-term tracking accuracy at different accuracy levels, and evaluate ID changes relative to the duration of the track in which they occur.
Journal ArticleDOI
Title Natural computing: A problem solving paradigm with granular information processing
Sankar K. Pal,Saroj K. Meher +1 more
TL;DR: The present article provides an overview of the significance of natural computing with respect to the granulation-based information processing models, such as neural networks, fuzzy sets and rough sets, and their hybridization and emphasizes on the biological motivation, design principles, application areas, open research problems and challenging issues of these models.
Journal ArticleDOI
Learning A Superpixel-Driven Speed Function for Level Set Tracking
Xue Zhou,Xi Li,Weiming Hu +2 more
TL;DR: A level set tracking method based on a discriminative speed function, which produces a superpixel-driven force for effective level set evolution, and a simple but efficient weighted non-negative matrix factorization method that can online learn an object shape dictionary is developed.
Journal ArticleDOI
Efficient and Robust Learning for Sustainable and Reacquisition-Enabled Hand Tracking
TL;DR: This paper presents a robust machine learning approach based on enhanced particle filter trackers that performs favorably against state-of-the-art algorithms on numerous challenging video sequences of hand postures, and overcomes the largely unsolved problem of redetecting hands after they vanish and reappear into the frame.