Active object recognition

Wilkes, D.; Tsotsos, John K.

doi:10.1109/cvpr.1992.223215

Cited by 84 publications

(60 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The variables of interest then would be the distance to the target, r , and the angle of the camera optical axis, which can be represented using the polar angle ζ and azimuthal angle φ. In the context of active object recognition, Wilkes and Tsotsos (1992) showed a simple behavior-based control algorithm that, depending on the state of recognition, was able to successfully control these parameters. Dickinson et al (1994) showed the utility of aspect graph representations for encoding the appropriate active changes of sensor viewpoint for recognition.…”

Section: How Does An Agent Determine When and Where To Sense?mentioning

confidence: 99%

“…Agent pose Active selection of agent pose most appropriate for selecting a viewpoint most useful for current task (e.g., moving an agent to a close enough position for viewing a task-related object or event) Nilsson (1969) Sensor pose Active selection of the pose of a sensor most appropriate for the current task (includes convergent binocular camera systems) (e.g., pointing a camera at a target in with the best viewing angle for its recognition) Brown (1990) (general gaze control) Coombs and Brown (1990) (binocular vergence; use of nonvisual cues in stabilizing gaze) Wilkes and Tsotsos (1992) (viewpoint behaviors for recognition)…”

Section: Viewpoint Selectionmentioning

confidence: 99%

See 1 more Smart Citation

Revisiting active perception

2017

View full text Add to dashboard Cite

Despite the recent successes in robotics, artificial intelligence and computer vision, a complete artificial agent necessarily must include active perception. A multitude of ideas and methods for how to accomplish this have already appeared in the past, their broader utility perhaps impeded by insufficient computational power or costly hardware. The history of these ideas, perhaps selective due to our perspectives, is presented with the goal of organizing the past literature and highlighting the seminal contributions. We argue that those contributions are as relevant today as they were decades ago and, with the state of modern computational tools, are poised to find new life in the robotic perception systems of the next decade.

show abstract

Section: How Does An Agent Determine When and Where To Sense?mentioning

confidence: 99%

Section: Viewpoint Selectionmentioning

confidence: 99%

Revisiting active perception

2017

View full text Add to dashboard Cite

show abstract

“…see [13][14][15][16][17][18]. These recognition approaches differ on several factors such as the type of the objects and sensors they are applied to, the features used to represent the objects, the matching methods used to compare these features to the ones in the database, and the decision making strategy in case of active sensor placement.…”

Section: Literature Surveymentioning

confidence: 99%

Robust sequential view planning for object recognition using multiple cameras

Farshidi

Sirouspour

Kirubarajan

2009

Image and Vision Computing

View full text Add to dashboard Cite

In this thesis the problem of object recognition/pose estimation using active sensing is investigated. It is assumed that multiple cameras acquire images from different view angles of an object belonging to a set of a priori known objects. The eigenspace method is used to process the sensory observations and produce an abstract measurement vector. This step is necessary to avoid the manipulation of the original sensor data, i.e. large images, that can render the sensor modelling and matching process practically infeasible.The eigenspace representation is known to have shortcomings in dealing with structured noise such as occlusion. To overcome this problem, models of occlusions and sensor noise have been incorporated into the probabilistic model of sensor/object to increase robustness with respect to such uncertainties. The active recognition algorithm has also been modified to consider the possibility of occlusion, as well as variation in the occlusion levels due to camera movements.A recursive Bayesian state estimation problem is formulated to model the observation uncertainties through a probabilistic scheme. This enables us to identify the object and estimate its pose by fusing the information obtained from individual cameras. To this end, an extensive training step is performed, providing the system with the sensor model required for the Bayesian estimation. In order to enhance the quality A multi-camera active vision system has been developed in order to implement the ideas proposed in this thesis. Comparative Monte Carlo experiments conducted with the two-camera system demonstrate the effectiveness of the proposed methods in object classification/pose estimation in the presence of structured noise. Different concepts introduced in this work, i.e., the multi-camera data fusion, the occlusion modelling, and the active camera movement, all improve the recognition process significantly. Specifically, these approaches all increase the recognition rate, decrease the number of steps taken before recognition is completed, and enhance robustness with respect to partial occlusion considerably.iv

show abstract

“…However, the focus is not on how to find the best focal length. Most related to our work are publications from the area of active object recognition, where the best parameters of a camera (for example, position on a hemisphere around the object) is searched for, to reduce uncertainty in the recognition process [1,3,5,11,13,14].…”

Section: Introductionmentioning

confidence: 99%