Active recognition through next view planning: a survey

Roy, Sumantra Dutta; Chaudhury, Santanu; Banerjee, Subhashis

doi:10.1016/j.patcog.2003.01.002

Cited by 86 publications

(7 citation statements)

References 99 publications

(159 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many researchers have investigated active perception, which is an important skill for robots that interact with objects, humans, and environments. The most popular application of active perception in robotics is active vision, in which a robot controls its attention to obtain information (Roy et al, 2004;Chen et al, 2011;Valipour et al, 2017;Zaky et al, 2020). For instance, Roy et al (2005) proposed a 3D object recognition system using a single camera.…”

Section: Active Perception In Roboticsmentioning

confidence: 99%

“…In the field of robotics, the issue of attention control for obtaining information to update estimations is formulated as active perception. In many studies, the attention point of a robotic camera has been controlled or actions have been selected to perceive sensory signals (Sakaguchi, 1993;Roy et al, 2004;Chen et al, 2011). For instance, Taniguchi et al (2018) proposed an active perception strategy designed to determine the order of perception for multimodal signals (e.g., vision, audio, and tactile signals) in an object recognition task.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Active Inference Through Energy Minimization in Multimodal Affective Human–Robot Interaction

Horii

Nagai

2021

Front. Robot. AI

View full text Add to dashboard Cite

During communication, humans express their emotional states using various modalities (e.g., facial expressions and gestures), and they estimate the emotional states of others by paying attention to multimodal signals. To ensure that a communication robot with limited resources can pay attention to such multimodal signals, the main challenge involves selecting the most effective modalities among those expressed. In this study, we propose an active perception method that involves selecting the most informative modalities using a criterion based on energy minimization. This energy-based model can learn the probability of the network state using energy values, whereby a lower energy value represents a higher probability of the state. A multimodal deep belief network, which is an energy-based model, was employed to represent the relationships between the emotional states and multimodal sensory signals. Compared to other active perception methods, the proposed approach demonstrated improved accuracy using limited information in several contexts associated with affective human–robot interaction. We present the differences and advantages of our method compared to other methods through mathematical formulations using, for example, information gain as a criterion. Further, we evaluate performance of our method, as pertains to active inference, which is based on the free energy principle. Consequently, we establish that our method demonstrated superior performance in tasks associated with mutually correlated multimodal information.

show abstract

Section: Active Perception In Roboticsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Active Inference Through Energy Minimization in Multimodal Affective Human–Robot Interaction

Horii

Nagai

2021

Front. Robot. AI

View full text Add to dashboard Cite

show abstract

“…Historically, active vision, i.e., active visual perception, has been studied as an important engineering problem in computer vision. Dutta Roy et al ( 2004 ) presented a comprehensive survey of active three-dimensional object recognition. For example, Borotschnig et al ( 2000 ) proposed an active vision method in a parametric eigenspace to improve the visual classification results.…”

Section: Background and Related Workmentioning

confidence: 99%

“…In spite of the wide range of studies about active perception (e.g., Borotschnig et al, 2000 ; Dutta Roy et al, 2004 ; Eidenberger and Scharinger, 2010 ; Krainin et al, 2011 ; Ferreira et al, 2013 ) and multimodal categorization for robots (e.g., Nakamura et al, 2007 , 2011a ; Sinapov and Stoytchev, 2011 ; Celikkanat et al, 2014 ; Sinapov et al, 2014 ), active perception methods for a robot, i.e., action selection methods for perception for unsupervised multimodal categorization, have not been sufficiently explored (see section 2).…”

Section: Introductionmentioning

confidence: 99%

Multimodal Hierarchical Dirichlet Process-Based Active Perception by a Robot

2018

View full text Add to dashboard Cite

In this paper, we propose an active perception method for recognizing object categories based on the multimodal hierarchical Dirichlet process (MHDP). The MHDP enables a robot to form object categories using multimodal information, e.g., visual, auditory, and haptic information, which can be observed by performing actions on an object. However, performing many actions on a target object requires a long time. In a real-time scenario, i.e., when the time is limited, the robot has to determine the set of actions that is most effective for recognizing a target object. We propose an active perception for MHDP method that uses the information gain (IG) maximization criterion and lazy greedy algorithm. We show that the IG maximization criterion is optimal in the sense that the criterion is equivalent to a minimization of the expected Kullback–Leibler divergence between a final recognition state and the recognition state after the next set of actions. However, a straightforward calculation of IG is practically impossible. Therefore, we derive a Monte Carlo approximation method for IG by making use of a property of the MHDP. We also show that the IG has submodular and non-decreasing properties as a set function because of the structure of the graphical model of the MHDP. Therefore, the IG maximization problem is reduced to a submodular maximization problem. This means that greedy and lazy greedy algorithms are effective and have a theoretical justification for their performance. We conducted an experiment using an upper-torso humanoid robot and a second one using synthetic data. The experimental results show that the method enables the robot to select a set of actions that allow it to recognize target objects quickly and accurately. The numerical experiment using the synthetic data shows that the proposed method can work appropriately even when the number of actions is large and a set of target objects involves objects categorized into multiple classes. The results support our theoretical outcomes.

show abstract

“…Chen et al [6] propose a multi-objective optimisation based sensor-placement algorithm that incorporates coverage and adequate overlap in camera's field of views for seamlessly tracking in a camera network. Camera placement planning is also important for next-view planning for accurate three-dimensional (3D) reconstruction [7]. Roy et al [8] propose an online method for next-view planning and object recognition using probabilistic reasoning.…”

Section: Camera Placementmentioning

confidence: 99%

Video analytics revisited

Choudhary

Chaudhury

2016

IET Computer Vision

Self Cite

View full text Add to dashboard Cite

Video, rich in visual real‐time content, is however, difficult to interpret and analyse. Video collections necessarily have large data volume. Video analytics strives to automatically discover patterns and correlations present in the large volume of video data, which can help the end‐user to take informed and intelligent decisions as well as predict the future based on the patterns discovered across space and time. In this study, the authors discuss various issues and problems in video analytics, proposed solutions and present some of the important current applications of video analytics.

show abstract

Active recognition through next view planning: a survey

Cited by 86 publications

References 99 publications

Active Inference Through Energy Minimization in Multimodal Affective Human–Robot Interaction

Active Inference Through Energy Minimization in Multimodal Affective Human–Robot Interaction

Multimodal Hierarchical Dirichlet Process-Based Active Perception by a Robot

Video analytics revisited

Contact Info

Product

Resources

About