Active recognition: Using uncertainty to reduce ambiguity (1996)

by F G Callari, F P Ferrie
Venue:in International Conference on Pattern Recognition
Add To MetaCart
Results 1 - 10 of 19

Active Recognition through Next View Planning: A Survey

by Sumantra Dutta Roy , Santanu Chaudhury , Subhashis Banerjee , 2002
"... 3-D object recognition involves using image-computable features to identify 3-D object. A single view of a 3-D object may not contain sufficient features to recognize it unambiguously. One needs to plan different views around the given object in order to recognize it. Such a task involves an active ..."
Abstract - Cited by 36 (2 self) - Add to MetaCart
3-D object recognition involves using image-computable features to identify 3-D object. A single view of a 3-D object may not contain sufficient features to recognize it unambiguously. One needs to plan different views around the given object in order to recognize it. Such a task involves an active sensor – one whose parameters (external and/or internal) can be changed in a purposive manner. In this paper, we review two important applications of an active sensor. We first survey important approaches to active 3-D object recognition. Next, we review existing approaches towards another important application of an active sensor namely, that of scene analysis and interpretation.

Entropy-based Gaze Planning

by Tal Arbel, Frank P. Ferrie - Image and Vision Computing , 1999
"... This paper describes an algorithm for recognizing known objects in an unstructured environment (e.g. landmarks) from measurements acquired with a single monochrome television camera mounted on a mobile observer. The approach is based on the concept of an entropy map, which is used to guide the mobi ..."
Abstract - Cited by 32 (0 self) - Add to MetaCart
This paper describes an algorithm for recognizing known objects in an unstructured environment (e.g. landmarks) from measurements acquired with a single monochrome television camera mounted on a mobile observer. The approach is based on the concept of an entropy map, which is used to guide the mobile observer along an optimal trajectory that minimizes the ambiguity of recognition as well as the amount of data that must be gathered. Recognition itself is based on the optical flow signatures that result from the camera motion - signatures that are inherently ambiguous due to the confounding of motion, structure and imaging parameters. We show how gaze planning partially alleviates this problem by generating trajectories that maximize discriminability. A sequential Bayes approach is used to handle the remaining ambiguity by accumulating evidence for different object hypotheses over time until a clear assertion can be made. Results from an experimental recognition system using a gantry-mounted television camera are presented to show the effectiveness of the algorithm on a large class of common objects. 1
(Show Context)

Feature space trajectory methods for active computer vision

by Michael A. Sipe, David Casasent - IEEE Transactions on Pattern Analysis and Machine Intelligence , 2002
"... Abstract—We advance new active object recognition algorithms that classify rigid objects and estimate their pose from intensity images. Our algorithms automatically detect if the class or pose of an object is ambiguous in a given image, reposition the sensor as needed, and incorporate data from mult ..."
Abstract - Cited by 16 (0 self) - Add to MetaCart
Abstract—We advance new active object recognition algorithms that classify rigid objects and estimate their pose from intensity images. Our algorithms automatically detect if the class or pose of an object is ambiguous in a given image, reposition the sensor as needed, and incorporate data from multiple object views in determining the final object class and pose estimate. A probabilistic feature space trajectory (FST) in a global eigenspace is used to represent 3D distorted views of an object and to estimate the class and pose of an input object. Confidence measures for the class and pose estimates, derived using the probabilistic FST object representation, determine when additional observations are required as well as where the sensor should be positioned to provide the most useful information. We demonstrate the ability to use FSTs constructed from images rendered from computer-aided design models to recognize real objects in real images and present test results for a set of metal machined parts. Index Terms—Active vision, classification, object recognition, pose estimation. 1
(Show Context)

Genetic Algorithms for Ambiguous Labelling Problems

by Richard Myers, Edwin R. Hancock - Pattern Recognition , 1999
"... Consistent labelling problems frequently have more than one solution. Most work in the "eld has aimed at disambiguating early in the interpretation process, using only local evidence. This paper starts with a review of the literature on labelling problems and ambiguity. Based on this review ..."
Abstract - Cited by 9 (1 self) - Add to MetaCart
Consistent labelling problems frequently have more than one solution. Most work in the "eld has aimed at disambiguating early in the interpretation process, using only local evidence. This paper starts with a review of the literature on labelling problems and ambiguity. Based on this review, we propose a strategy for simultaneously extracting multiple related solutions to the consistent labelling problem. In a preliminary experimental study, we show that an appropriately modi"ed genetic algorithm is a robust tool for "nding multiple solutions to the consistent labelling problem. These solutions are related by common labellings of the most strongly constrained junctions. We have proposed three run-time measures of algorithm performance: the maximum "tness of the genetic algorithm's population, its Shannon entropy, and the total Hamming distance between its distinct members. The results to date indicate that when the Shannon entropy falls below a certain threshold, new solutions are unlikely to emerge and that most of the diversity in the population disappears within the "rst few generations. � 2000 Pattern Recognition Society. Published
(Show Context)

Recognizing Large Isolated 3-D Objects Through Next View Planning Using Inner Camera Invariants

by Sumantra Dutta Roy, Santanu Chaudhury, Subhashis Banerjee - IEEE Trans. on Systems, Man, and Cybernetics—Part B: Cybernetics , 2005
"... Abstract — Most model-based 3-D object recognition systems use information from a single view of an object. However, a single view may not contain sufficient features to recognize it unambiguously. Further, two objects may have all views in common with respect to a given feature set, and may be dist ..."
Abstract - Cited by 9 (1 self) - Add to MetaCart
Abstract — Most model-based 3-D object recognition systems use information from a single view of an object. However, a single view may not contain sufficient features to recognize it unambiguously. Further, two objects may have all views in common with respect to a given feature set, and may be distinguished only through a sequence of views. A further complication arises when in an image, we do not have a complete view of an object. This paper presents a new on-line scheme for the recognition and pose estimation of a large isolated 3-D object, which may not entirely fit in a camera’s field of view. We consider an uncalibrated projective camera, and consider the case when the internal parameters of the camera may be varied either unintentionally, or on purpose. The scheme uses a probabilistic reasoning framework for recognition and next view planning. We show results of successful recognition and pose estimation even in cases of a high degree of interpretation ambiguity associated with the initial view.

Active 3D Object Localization Using A Humanoid Robot

by Alexander Andreopoulos, Stephan Hasler, Heiko Wersing, Herbert Janssen, John K. Tsotsos, Edgar Körner - IEEE TRANSACTIONS ON ROBOTICS
"... We study the problem of actively searching for an object in a 3D environment under the constraint of a maximum search time, using a visually guided humanoid robot with twentysix degrees of freedom. The inherent intractability of the problem is discussed and a greedy strategy for selecting the best n ..."
Abstract - Cited by 5 (0 self) - Add to MetaCart
We study the problem of actively searching for an object in a 3D environment under the constraint of a maximum search time, using a visually guided humanoid robot with twentysix degrees of freedom. The inherent intractability of the problem is discussed and a greedy strategy for selecting the best next viewpoint is employed. We describe a target probability updating scheme approximating the optimal solution to the problem, providing an efficient solution to the selection of the best next viewpoint. We employ a hierarchical recognition architecture, inspired by human vision, that uses contextual cues for attending to the view-tuned units at the proper intrinsic scales and for active control of the robotic platform sensor’s coordinate frame, also giving us control of the extrinsic image scale and achieving the proper sequence of pathognomonic views of the scene. The recognition model makes no particular assumptions on shape properties like texture and is trained by showing the object by hand to the robot. Our results demonstrate the feasibility of using state of the art vision-based systems for efficient and reliable object localization in an indoor 3D environment.

Active Object Recognition Conditioned by Probabilistic Evidence and Entropy Maps

by Tal Arbel , 2000
"... Abstract This thesis introduces a novel method for sequentially accumulating evidence as it pertains to an active observer seeking to identify an object in a known environment. First, a probabilistic framework is developed, based on a generalized inverse theory, where assertions are represented by c ..."
Abstract - Cited by 2 (0 self) - Add to MetaCart
Abstract This thesis introduces a novel method for sequentially accumulating evidence as it pertains to an active observer seeking to identify an object in a known environment. First, a probabilistic framework is developed, based on a generalized inverse theory, where assertions are represented by conditional probability density functions. In order to resolve ambiguous assertions from single view measurements, a sequential recognition strategy is developed in which evidence is accumulated over successive viewpoints until a definitive assertion can be made. The main contribution of the thesis is a strategy for conditioning the inference and the measurement processes with feedback from prior information. The problem of interest is that of model-based recognition, where the task is to identify an unknown model from a database of known objects on the basis of parameter estimates. The robustness of the algorithm is illustrated through its application to two very different domains: (1) recognition of 3-D parametric models estimated directly from laser rangefinder data, (2) recognition of objects based on signatures extracted from optical flow images that they generate as they move with respect to a camera. The latter approach is completely novel and presents a major contribution to the field. Experimental results verify the strength of the approach at overcoming difficulties encountered in both contexts, as rapid convergence to the correct solution occurs in most cases.
(Show Context)

Best viewpoints for active vision classification and pose estimation

by Michael A. Sipe, David Casasent - Intelligent Robots and Computer Vision XVI: Algorithms, Techniques, Active Vision, and Materials Handling , 1997
"... We advance new active computer vision algorithms that classify objects and estimate their pose from intensity images. Our algorithms automatically re-position the sensor if the class or pose of an object is ambiguous in a given image and incorporate data from multiple object views in determining the ..."
Abstract - Cited by 2 (1 self) - Add to MetaCart
We advance new active computer vision algorithms that classify objects and estimate their pose from intensity images. Our algorithms automatically re-position the sensor if the class or pose of an object is ambiguous in a given image and incorporate data from multiple object views in determining the final object classification A feature space trajectory (FST) in a global eigenfeature space is used to represent 3-D distorted views of an object. Assuming that an observed feature vector consists of Gaussian noise added to a point on the FST, we derive a probability density function (PDF) for the observation conditioned on the class and pose of the object. Bayesian estimation and hypothesis testing theory are then used to derive approximations to the maximum a posteriori probability pose estimate and the minimum probability of error classifier. New confidence measures for the class and pose estimates, derived using Bayes theory, determine when additional observations are required as well as where the sensor should be positioned to provide the most useful information.

Recognition of 3-D Objects Having Ambiguous Views

by Manfred Prantl, Mark Burge, Axel Pinz, Conditional Rule Generation (crg , 1998
"... We present aneffi t method within an active vision framework for recognizing objects which are ambiguous from certain viewpoints. The approach uses an object representation that is structural and appearance based. At first a preliminary object classification is obtained using the CRG algorithm. I ..."
Abstract - Cited by 2 (2 self) - Add to MetaCart
We present aneffi t method within an active vision framework for recognizing objects which are ambiguous from certain viewpoints. The approach uses an object representation that is structural and appearance based. At first a preliminary object classification is obtained using the CRG algorithm. In case of ambiguous classification results, the system repositions its sensor and acquires additional data. Wegive an algorithm on this sensor planning task and also on howtointegrate the information gathered from various views. Keywords: object recognition, active vision, sensor planning 1

Active Object Recognition using Vocabulary Trees

by Natasha Govender, Jonathan Claassens, Philip Torr, Jonathan Warrell
"... For mobile robots to perform certain tasks in human environments, fast and accurate object classification is essential. Actively exploring objects by changing viewpoints promises an increase in the accuracy of object classification. This paper presents an efficient feature-based active vision system ..."
Abstract - Cited by 1 (1 self) - Add to MetaCart
For mobile robots to perform certain tasks in human environments, fast and accurate object classification is essential. Actively exploring objects by changing viewpoints promises an increase in the accuracy of object classification. This paper presents an efficient feature-based active vision system for the recognition and verification of objects that are occluded, appear in cluttered scenes and may be visually similar to other objects present. This system is designed using a selector-observer framework where the selector is responsible for the automatic selection of the next best viewpoint and a Bayesian ‘observer ’ updates the belief hypothesis and provides feedback. A new method for automatically selecting the ‘next best viewpoint ’ is presented using vocabulary trees. It is used to calculate a weighting for each feature based on its perceived uniqueness, allowing the system to select the viewpoint with the greatest number of ‘unique ’ features. The process is sped-up as new images are only captured at the ‘next best viewpoint’ and processed when the belief hypothesis of an object is below some pre-defined threshold. The system also provides a certainty measure for the objects identity. This system out performs randomly selecting a viewpoint as it processes far fewer viewpoints to recognise and verify objects in a scene. 1.
(Show Context)