The Experts below are selected from a list of 66066 Experts worldwide ranked by ideXlab platform
Katsushi Ikeuchi - One of the best experts on this subject based on the ideXlab platform.
-
sensor modeling probabilistic Hypothesis Generation and robust localization for object recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995Co-Authors: Mark D Wheeler, Katsushi IkeuchiAbstract:In an effort to make object recognition efficient and accurate enough for real applications; we have developed three probabilistic techniques-sensor modeling, probabilistic Hypothesis Generation, and robust localization-which form the basis of a promising paradigm for object recognition. Our techniques effectively exploit prior knowledge to reduce the number of hypotheses that must be tested during recognition. Our recognition approach utilizes statistical constraints on the matches between image and model features. These statistical constraints are computed using a model of the entire sensing process-resulting in more realistic and tighter constraints on matches. The candidate hypotheses are pruned by probabilistic constraint satisfaction to select likely matches based on the image evidence and prior statistical constraints. The resulting hypotheses are ordered most-likely first for verification. Thus minimizing unnecessary verifications. The reliability of the verification decision is significantly increased by the use of a robust localization algorithm. >
-
sensor modeling probabilistic Hypothesis Generation and robust localization for object recognition
Proceedings of 1994 IEEE 2nd CAD-Based Vision Workshop, 1994Co-Authors: Mark D Wheeler, Katsushi IkeuchiAbstract:In an effort to make object recognition efficient and accurate enough for applications, the authors have developed three techniques; sensor modeling, probabilistic Hypothesis Generation, and robust localization-which form the basis of a probabilistic object recognition algorithm. To minimize recognition time, these techniques exploit prior knowledge to reduce the number of verifications (the most expensive and critical part of the algorithm) required during recognition. The approach utilizes statistical constraints generated by modeling the entire sensing process, resulting in more accurate constraints on matches. Hypotheses are pruned by a probabilistic algorithm which selects matches based on image evidence and prior statistical constraints. The reliability of the verification decision is increased by robust localization. The authors have implemented these techniques in a system for recognizing polyhedral objects in range images. The results demonstrate accurate recognition while greatly limiting the number of verifications performed. >
David Suter - One of the best experts on this subject based on the ideXlab platform.
-
efficient guided Hypothesis Generation for multi structure epipolar geometry estimation
Computer Vision and Image Understanding, 2017Co-Authors: Taotao Lai, Hanzi Wang, Yan Yan, Guobao Xiao, David SuterAbstract:A sampling method EGHG is proposed for multi-structure geometry estimation.EGHG combines the benefits of a global and a local sampling strategy.The global sampling strategy is designed to rapidly obtain promising solutions.The local sampling strategy is designed to efficiently achieve accurate solutions.Experimental results show the effectiveness of EGHG on public real image pairs. We propose an Efficient Guided Hypothesis Generation (EGHG) method for multi-structure epipolar geometry estimation. Based on the Markov Chain Monte Carlo process, EGHG combines two guided sampling strategies: a global sampling strategy and a local sampling strategy. The global sampling strategy, guided by using both spatial sampling probabilities and keypoint matching scores, rapidly obtains promising solutions. The spatial sampling probabilities are computed by using a normalized exponential loss function. The local sampling strategy, guided by using both Joint Feature Distributions (JFDs) and keypoint matching scores, efficiently achieves accurate solutions. In the local sampling strategy, EGHG updates a set of current best Hypothesis candidates on the fly, and then computes JFDs between the input data and these candidates. Experimental results on public real image pairs show that EGHG significantly outperforms several state-of-the-art sampling methods on multi-structure data.
-
Accelerated Hypothesis Generation for Multistructure Data via Preference Analysis
IEEE transactions on pattern analysis and machine intelligence, 2012Co-Authors: Tatjun Chin, David SuterAbstract:Random Hypothesis Generation is integral to many robust geometric model fitting techniques. Unfortunately, it is also computationally expensive, especially for higher order geometric models and heavily contaminated data. We propose a fundamentally new approach to accelerate Hypothesis sampling by guiding it with information derived from residual sorting. We show that residual sorting innately encodes the probability of two points having arisen from the same model, and is obtained without recourse to domain knowledge (e.g., keypoint matching scores) typically used in previous sampling enhancement methods. More crucially, our approach encourages sampling within coherent structures and thus can very rapidly generate all-inlier minimal subsets that maximize the robust criterion. Sampling within coherent structures also affords a natural ability to handle multistructure data, a condition that is usually detrimental to other methods. The result is a sampling scheme that offers substantial speed-ups on common computer vision tasks such as homography and fundamental matrix estimation. We show on many computer vision data, especially those with multiple structures, that ours is the only method capable of retrieving satisfactory results within realistic time budgets.
-
accelerated Hypothesis Generation for multi structure robust fitting
European Conference on Computer Vision, 2010Co-Authors: Tatjun Chin, David SuterAbstract:Random Hypothesis Generation underpins many geometric model fitting techniques. Unfortunately it is also computationally expensive. We propose a fundamentally new approach to accelerate Hypothesis sampling by guiding it with information derived from residual sorting. We show that residual sorting innately encodes the probability of two points to have arisen from the same model and is obtained without recourse to domain knowledge (e.g. keypoint matching scores) typically used in previous sampling enhancement methods. More crucially our approach is naturally capable of handling data with multiple model instances and excels in applications (e.g. multi-homography fitting) which easily frustrate other techniques. Experiments show that our method provides superior efficiency on various geometric model estimation tasks. Implementation of our algorithm is available on the authors, homepage.
-
ECCV (5) - Accelerated Hypothesis Generation for multi-structure robust fitting
Computer Vision – ECCV 2010, 2010Co-Authors: Tatjun Chin, David SuterAbstract:Random Hypothesis Generation underpins many geometric model fitting techniques. Unfortunately it is also computationally expensive. We propose a fundamentally new approach to accelerate Hypothesis sampling by guiding it with information derived from residual sorting. We show that residual sorting innately encodes the probability of two points to have arisen from the same model and is obtained without recourse to domain knowledge (e.g. keypoint matching scores) typically used in previous sampling enhancement methods. More crucially our approach is naturally capable of handling data with multiple model instances and excels in applications (e.g. multi-homography fitting) which easily frustrate other techniques. Experiments show that our method provides superior efficiency on various geometric model estimation tasks. Implementation of our algorithm is available on the authors, homepage.
Mark D Wheeler - One of the best experts on this subject based on the ideXlab platform.
-
sensor modeling probabilistic Hypothesis Generation and robust localization for object recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995Co-Authors: Mark D Wheeler, Katsushi IkeuchiAbstract:In an effort to make object recognition efficient and accurate enough for real applications; we have developed three probabilistic techniques-sensor modeling, probabilistic Hypothesis Generation, and robust localization-which form the basis of a promising paradigm for object recognition. Our techniques effectively exploit prior knowledge to reduce the number of hypotheses that must be tested during recognition. Our recognition approach utilizes statistical constraints on the matches between image and model features. These statistical constraints are computed using a model of the entire sensing process-resulting in more realistic and tighter constraints on matches. The candidate hypotheses are pruned by probabilistic constraint satisfaction to select likely matches based on the image evidence and prior statistical constraints. The resulting hypotheses are ordered most-likely first for verification. Thus minimizing unnecessary verifications. The reliability of the verification decision is significantly increased by the use of a robust localization algorithm. >
-
sensor modeling probabilistic Hypothesis Generation and robust localization for object recognition
Proceedings of 1994 IEEE 2nd CAD-Based Vision Workshop, 1994Co-Authors: Mark D Wheeler, Katsushi IkeuchiAbstract:In an effort to make object recognition efficient and accurate enough for applications, the authors have developed three techniques; sensor modeling, probabilistic Hypothesis Generation, and robust localization-which form the basis of a probabilistic object recognition algorithm. To minimize recognition time, these techniques exploit prior knowledge to reduce the number of verifications (the most expensive and critical part of the algorithm) required during recognition. The approach utilizes statistical constraints generated by modeling the entire sensing process, resulting in more accurate constraints on matches. Hypotheses are pruned by a probabilistic algorithm which selects matches based on image evidence and prior statistical constraints. The reliability of the verification decision is increased by robust localization. The authors have implemented these techniques in a system for recognizing polyhedral objects in range images. The results demonstrate accurate recognition while greatly limiting the number of verifications performed. >
Hanzi Wang - One of the best experts on this subject based on the ideXlab platform.
-
A unified Hypothesis Generation framework for multi-structure model fitting
Neurocomputing, 2017Co-Authors: Taotao Lai, Hanzi Wang, Yan Yan, Liming ZhangAbstract:Generating promising hypotheses plays a critical role in the success of multi-structure model fitting methods. However, conventional multi-structure Hypothesis Generation strategies do not exploit the information derived from the results of model selection to guide the subsequent Hypothesis Generation process. This leads to the problem that these Hypothesis Generation strategies are often computationally expensive for generating promising hypotheses, especially for heavily contaminated multi-structure data. To address this problem, we first propose a guided sampling strategy to accelerate promising Hypothesis Generation process by using information derived from the results of model selection on the fly. Then we present a Unified Hypothesis Generation (UHG) framework, which effectively combines the conventional multi-structure Hypothesis Generation strategy with the proposed guided sampling strategy by using a Markov Chain Monte Carlo process based on a cooling schedule. Experimental results on public databases demonstrate that the proposed UHG achieves significant superiority over several state-of-the-art sampling methods in terms of accuracy and efficiency, especially on multi-structure data. HighlightsA unified sampling framework UHG is proposed for multi-structure model fitting.UHG combines the merits of a global search strategy and a local search strategy.The global search strategy is guided by the conventional sampling strategy.The local search strategy is guided by using the results of model selection.Experimental results show the effectiveness of UHG on public datasets.
-
efficient guided Hypothesis Generation for multi structure epipolar geometry estimation
Computer Vision and Image Understanding, 2017Co-Authors: Taotao Lai, Hanzi Wang, Yan Yan, Guobao Xiao, David SuterAbstract:A sampling method EGHG is proposed for multi-structure geometry estimation.EGHG combines the benefits of a global and a local sampling strategy.The global sampling strategy is designed to rapidly obtain promising solutions.The local sampling strategy is designed to efficiently achieve accurate solutions.Experimental results show the effectiveness of EGHG on public real image pairs. We propose an Efficient Guided Hypothesis Generation (EGHG) method for multi-structure epipolar geometry estimation. Based on the Markov Chain Monte Carlo process, EGHG combines two guided sampling strategies: a global sampling strategy and a local sampling strategy. The global sampling strategy, guided by using both spatial sampling probabilities and keypoint matching scores, rapidly obtains promising solutions. The spatial sampling probabilities are computed by using a normalized exponential loss function. The local sampling strategy, guided by using both Joint Feature Distributions (JFDs) and keypoint matching scores, efficiently achieves accurate solutions. In the local sampling strategy, EGHG updates a set of current best Hypothesis candidates on the fly, and then computes JFDs between the input data and these candidates. Experimental results on public real image pairs show that EGHG significantly outperforms several state-of-the-art sampling methods on multi-structure data.
-
Rapid Hypothesis Generation by combining residual sorting with local constraints
Multimedia Tools and Applications, 2016Co-Authors: Taotao Lai, Hanzi Wang, Yan Yan, Da-han Wang, Guobao XiaoAbstract:Efficient Hypothesis Generation plays an important role in robust model fitting. In this study, based on the combination of residual sorting and local constraints, we propose an efficient guided Hypothesis Generation method, called Rapid Hypothesis Generation (RHG). By exploiting the local constraints to guide the Hypothesis Generation process, RHG raises the probability of generating promising hypotheses and reduces the computational cost during hypotheses Generation. Experimental results on homography and fundamental matrix estimation show that RHG can effectively guide Hypothesis Generation process and rapidly generate promising hypotheses for heavily contaminated multi-structure data.
-
ICARCV - Combining preference analysis with local constraints for rapid Hypothesis Generation
2014 13th International Conference on Control Automation Robotics & Vision (ICARCV), 2014Co-Authors: Taotao Lai, Da-han Wang, Guobao Xiao, Hanzi WangAbstract:Hypothesis Generation is crucial to many robust model fitting methods. In this paper, we propose an effective Hypothesis Generation method by adopting conditional sampling with local constraints. We choose data to generate hypotheses according to sampling weights, which are computed according to ordered residual indices. To sample a minimal subset, we randomly choose a seed datum, compute sampling weights of all data with regard to the seed datum, search the neighborhood set of the seed datum by using the sampling weights, and then sample the remaining data of the minimal subset from the neighborhood set. It has two advantages to consider the neighboring information in guided sampling: It raises the probability of generating all-inlier minimal subsets and it reduces the computational loads in hypotheses Generation. The proposed method shows good performance in fundamental matrix estimation using real image pairs.
Jin-su Jeong - One of the best experts on this subject based on the ideXlab platform.
-
Changes in brain activation induced by the training of Hypothesis Generation skills: an fMRI study.
Brain and cognition, 2008Co-Authors: Yong-ju Kwon, Jun-ki Lee, Dong-hoon Shin, Jin-su JeongAbstract:The aim of the present study is to investigate the learning-related changes in brain activation induced by the training of Hypothesis Generation skills regarding biological phenomena. Eighteen undergraduate participants were scanned twice with functional magnetic resonance imaging (fMRI) before and after training over a period of 2 months. The experimental group underwent eight biological Hypothesis Generation training programs, but the control group was not given any during the 2-month period. The results showed that the left frontal gyri, the cingulate gyrus, and the cuneus were activated during Hypothesis Generation. In addition, the brain activation of the trained group increased in the left inferior and the superior frontal gyri, which are related to working memory load and higher-order inferential processes. However, the activation after training decreased in the occipito-parietal route, which is associated with the perception and the analysis processes of visual information. Furthermore, the results have suggested that the dorsolateral prefrontal cortex (DLPFC) region is the critical area in the training of Hypothesis Generation skills.
-
Increased information transmission during scientific Hypothesis Generation: mutual information analysis of multichannel EEG.
International journal of psychophysiology : official journal of the International Organization of Psychophysiology, 2006Co-Authors: Seung-hyun Jin, Jin-su Jeong, Yong-ju Kwon, Suk Won Kwon, Dong-hoon ShinAbstract:Hypothesis Generation has been regarded as one of the core reasoning processes in creative thinking and scientific discovery. To investigate changes in the amount of information transmission during scientific Hypothesis Generation, the averaged cross-mutual-information (A-CMI) of EEGs was estimated. Twenty-five 5th grade students were sampled in this study. EEG signals from 16 electrodes on each subject's scalp were recorded using a 32-channel EEG system. In order to generate hypotheses, the students were asked to observe 20 quail eggs that gave rise to questions such as: Why do different sizes and shapes of patterns appear on the surface of the eggs? After the observation, they were asked to generate a scientific Hypothesis—a tentative causal explanation for the evoked question. The results of experimentation indicated several distinct brain activities during Hypothesis Generation interacting between different local brain regions. In addition, it was observed that the amount of information transmission during Hypothesis Generation increased in a large part of the brain region encompassing the temporal, parietal, and occipital cortexes, which implies the use of declarative and procedural memory systems. Furthermore, this study suggested the possibility that neuropsychological approaches may be potential tools to investigate the neuronal activity of EEGs during Hypothesis Generation.
-
Differences in brain information transmission between gifted and normal children during scientific Hypothesis Generation.
Brain and cognition, 2006Co-Authors: Seung-hyun Jin, Jin-su Jeong, Yong-ju Kwon, Suk Won Kwon, Dong-hoon ShinAbstract:The purpose of the present study was to investigate differences in neural information transmission between gifted and normal children involved in scientific Hypothesis Generation. To investigate changes in the amount of information transmission, the children's averaged-cross mutual information (A-CMI) of EEGs was estimated during their Generation of scientific hypotheses. We recorded EEG from 25 gifted and 25 age-matched normal children using 16 electrodes on each subject's scalp. To generate hypotheses, the children were asked to observe 20 "quail eggs" that gave rise to questions. After observation, they were asked to generate a scientific Hypothesis--a tentative causal explanation for the questions evoked. The results of this study revealed several distinguishing brain activities between gifted and normal children during Hypothesis Generation. In contrast to normal children, gifted children showed increased A-CMI values between the left temporal and central, between the left temporal and parietal, and between the left central and parietal locations while generating a Hypothesis. These results suggested that gifted children more efficiently distribute the cognitive resources essential to cope with Hypothesis Generation.
-
Brain Activation During Scientific Hypothesis Generation in Biologists and Non-biologists
Advances in Cognitive Neurodynamics ICCN 2007, 1Co-Authors: Il-sun Lee, Jun-ki Lee, Jin-su Jeong, Yong-ju KwonAbstract:Functional magnetic resonance imaging was used to investigate neural substrates during scientific Hypothesis Generation, in particular, the differences between biologists and non-biologists. Eight biologists and eight non-biologists were scanned while they performed eight scientific Hypothesis Generation tasks. The results of this study revealed that activation of the left inferior and middle frontal gyri were driven by increased working memory load. The superior medial prefrontal cortex reflected higher-order inferential processes. The activation of the right hippocampus reflected the retrieval and encoding of information in long-term memory. The increased activity in the occipito-parietal route was due to perception and visuo-spatial working memory. Furthermore, the biologists’ exceptional abilities for Hypothesis Generation were correlated with the acceleration of memory retrieval and higher-order inferential processes.