Informed visual search: Combining attention and object recognition

Forssén, Per-Erik; Meger, David; Lai, K. Robert; Helmer, Scott; Little, James J.; Lowe, David

doi:10.1109/robot.2008.4543325

Cited by 54 publications

(35 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This system is especially suited for dealing with the robotic scenario, where the robot can acquire multiple shots, which are then matched with the image clusters; having highly populated clusters ensures a robust matching. The approach in [17] extends Curious George, by implementing an attention scheme that allows it to identify interesting regions that correspond to potential objects in the world. In both cases, the recognition scenario is different from ours, since multiple images of the same object are used as input of the classifier system, while we expect a single test image.…”

Section: Related Literaturementioning

confidence: 99%

“…In our work, we prefer to disregard the investigation of tags already associated to the images; instead, our aim is to produce textual tags which are semantically relevant for the key concepts that we are considering, and feeding an image search engine with those tags. A massive automatic retrieval of images for the training of object detectors is proposed in [15], where, similarly as in [14,17], simple image search by Google is used to populate the classes, but, differently from the the latter methods, no postprocessing is implemented. For this reason, we consider this process of data acquisition as competitor to our approach.…”

Section: Related Literaturementioning

confidence: 99%

See 1 more Smart Citation

Semantically-driven automatic creation of training sets for object recognition

Cheng

Setti

Zeni

et al. 2015

Computer Vision and Image Understanding

View full text Add to dashboard Cite

In the object recognition community, much effort has been spent on devising expressive object representations and powerful learning strategies for designing effective classifiers, capable of achieving high accuracy and generalization. In this scenario, the focus on the training sets has been historically weak; by and large, training sets have been generated with a substantial human intervention, requiring considerable time. In this paper, we present a strategy for automatic training set generation. The strategy uses semantic knowledge coming from WordNet, coupled with the statistical power provided by Google Ngram, to select a set of meaningful text strings related to the text class-label (e.g., "cat"), that are subsequently fed into the Google Images search engine, producing sets of images with high training value. Focusing on the classes of different object recognition benchmarks (PASCAL VOC 2012, Caltech-256, ImageNet, GRAZ and OxfordPet), our approach collects novel training images, compared to the ones obtained by exploiting Google Images with the simple text class-label. In particular, we show that the gathered images are better able to capture the different visual facets of a concept, thus encoding in a more successful manner the intra-class variance. As a consequence, training standard classifiers with this data produces performances not too distant from those obtained from the classical hand-crafted training sets. In addition, our datasets generalize well and are stable, that is, they provide similar performances on diverse test datasets. This process does not require manual intervention and is completed in a few hours.

show abstract

Section: Related Literaturementioning

confidence: 99%

Section: Related Literaturementioning

confidence: 99%

Semantically-driven automatic creation of training sets for object recognition

Cheng

Setti

Zeni

et al. 2015

Computer Vision and Image Understanding

View full text Add to dashboard Cite

show abstract

“…It mainly aims at fast and efficient object recognition of similar and ambiguous objects, but does not cope with multi-object scenarios and cluttered environments. Forssen et al [3] combine object recognition with an attention mechanism for obstacle avoidance to efficiently acquire scene information. This approach targets on rapidly identifying objects in cluttered environments, but neither models pose uncertainties nor takes into account object occlusions.…”

Section: Related Workmentioning

confidence: 99%

“…Equation (3) describes that reaching a future state q depends on the previous state q and on the applied action a t . The system dynamics underlie the state transition uncertainty ε t , meaning that each executed action influences the state distributions.…”

Section: A Inference Modelmentioning

confidence: 99%

Active perception and scene modeling by planning with probabilistic 6D object poses

Eidenberger

Scharinger

2010

2010 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-This paper presents an approach to probabilistic active perception planning for scene modeling in cluttered and realistic environments. When dealing with complex, multiobject scenes with arbitrary object positions, the estimation of 6D poses including their expected uncertainties is essential. The scene model keeps track of the probabilistic object hypotheses over several sequencing sensing actions to represent the real object constellation.To improve detection results and to tackle occlusion problems a method for active planning is proposed which reasons about model and state transition uncertainties in continuous and highdimensional domains. Information theoretic quality criteria are used for sequential decision making to evaluate probability distributions. The probabilistic planner is realized as a partially observable Markov decision process (POMDP).The active perception system for autonomous service robots is evaluated in experiments in a kitchen environment. In 80 test runs the efficiency and satisfactory behavior of the proposed methodology is shown in comparison to a random and a stepaside action selection strategy. The objects are selected from a large database consisting of 100 different household items.

show abstract

“…Hence, they avoid to model occlusions explicitly and rely on the robustness of the detector. In [9] object recognition is combined with an attention mechanism for occlusion avoidance to efficiently acquire scene information. This approach targets on rapidly identifying objects in cluttered environments, but does not model pose uncertainties.…”

Section: Related Workmentioning

confidence: 99%

Probabilistic occlusion estimation in cluttered environments for active perception planning

Eidenberger

Zoellner

Scharinger

2009

2009 IEEE/ASME International Conference on Advanced Intelligent Mechatronics

View full text Add to dashboard Cite

Abstract-This paper presents a probabilistic framework for scene modeling and active perception planning in complex environments. It tackles the problems of representing detection and transition uncertainties in multi-object scenes without knowledge of the total number of objects in the scenario. The correct association of observation data with scene information is essential for reasonable incorporation of sequencing measurements into the scene model. This work also deals with the probabilistic computation of object occlusions for probabilistic action planning in order to select the most profitable prospective viewpoint. Concepts from computer graphics and statistics are combined for the efficient and precise estimation of future observations.In an experimental setting this active perception system, integrated into an autonomous service robot, is evaluated in a kitchen scenario.

show abstract

Informed visual search: Combining attention and object recognition

Cited by 54 publications

References 21 publications

Semantically-driven automatic creation of training sets for object recognition

Semantically-driven automatic creation of training sets for object recognition

Active perception and scene modeling by planning with probabilistic 6D object poses

Probabilistic occlusion estimation in cluttered environments for active perception planning

Contact Info

Product

Resources

About