Dynamic visual understanding of the local environment for an indoor navigating robot

Tsai, Grace; Kuipers, Benjamin

doi:10.1109/iros.2012.6385735

Cited by 23 publications

(33 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It computes the differential of autocorrelation according to directions directly. A similar detector, named Kanade-Lucas-Tomasi (KLT) [42], was employed in [56] for efficient and continuous tracking. Compared to the Harris detector, KLT has an additional greedy corner selection criterion; thus, it is computationally more efficient.…”

Section: Corner-based Approachesmentioning

confidence: 99%

Extracting Semantic Information from Visual Data: A Survey

Liu

et al. 2016

Robotics

View full text Add to dashboard Cite

Abstract:The traditional environment maps built by mobile robots include both metric ones and topological ones. These maps are navigation-oriented and not adequate for service robots to interact with or serve human users who normally rely on the conceptual knowledge or semantic contents of the environment. Therefore, the construction of semantic maps becomes necessary for building an effective human-robot interface for service robots. This paper reviews recent research and development in the field of visual-based semantic mapping. The main focus is placed on how to extract semantic information from visual data in terms of feature extraction, object/place recognition and semantic representation methods.

show abstract

Section: Corner-based Approachesmentioning

confidence: 99%

Extracting Semantic Information from Visual Data: A Survey

Liu

et al. 2016

Robotics

View full text Add to dashboard Cite

show abstract

“…a video), Tsai, et al [11] generates a set of hypotheses from the first frame of the video, and uses a Bayesian filter to evaluate the hypotheses on-line based on their abilities to explain the 2D motions of a set of tracked features. Tsai and Kuipers [10] extended the real-time scene understanding method to generate children hypotheses on-line from existing hypotheses to describe the scene in more detail. These methods simply detect c 2013.…”

Section: Introductionmentioning

confidence: 99%

“…It may be distributed unchanged freely in print or electronic forms. ) We demonstrate our attention focusing method in an on-line generate-and-test framework for scene understanding [10]. The steps with solid gray blocks are adapted from [10], and the steps with dashed blue blocks show where we select and extract the informative features.…”

Section: Introductionmentioning

confidence: 99%

“…We demonstrate our attention focusing method in an on-line generate-and-test framework for scene understanding [10]. The steps with solid gray blocks are adapted from [10], and the steps with dashed blue blocks show where we select and extract the informative features. After generating children hypotheses (|{M} t−1 | ≥ |{M} t−1 |) , we select point features from the current set of tracked features that are informative to discriminate among the hypotheses {M} t−1 .…”

Section: Introductionmentioning

confidence: 99%

“…lines [2,5,7], points [10,11], and edges [7]) that are easily detectable for evaluating the hypotheses. In fact, some of the most informative features to discriminate the hypotheses may not be extracted if features are detected by fixed thresholds, because the most informative regions may not have high image contrasts for features to be detected.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Focusing Attention on Visual Features that Matter

Tsai

Kuipers²

2013

Procedings of the British Machine Vision Conference 2013

Self Cite

View full text Add to dashboard Cite

A common approach to scene understanding generates a set of structural hypotheses and evaluates these hypotheses using visual features that are easy to detect. However, these features may not necessarily be the most informative features to discriminate among the hypotheses. This paper demonstrates that by focusing attention on regions where the hypotheses differ in how they explain the visual features, we can then evaluate those hypotheses more efficiently. We define the informativeness of each feature based on the expected information gain that the feature provides to the current set of hypotheses, and demonstrate how these informative features can be selected efficiently. We evaluate our attention focusing method on a Bayesian filter-based approach to scene understanding. Our experimental results demonstrate that by focusing attention on the most informative point features, the Bayesian filter converges to a single hypothesis more efficiently, with no loss of accuracy.

show abstract

3D Spatial Layout Propagation in a Video Sequence

Rituerto

Manduchi

Murillo

et al. 2014

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Intelligent autonomous systems need detailed models of their environment to achieve sophisticated tasks. Vision sensors provide rich information and are broadly used to obtain these models, particularly, indoor scene understanding has been widely studied. A common initial step to solve this problem is the estimation of the 3D layout of the scene. This work addresses the problem of scene layout propagation along a video sequence. We use a Particle Filter framework to propagate the scene layout obtained using a state-of-the-art technique on the initial frame and propose how to generate, evaluate and sample new layout hypotheses on each frame. Our intuition is that we can obtain better layout estimation at each frame through propagation than running separately at each image. The experimental validation shows promising results for the presented approach.

show abstract

Dynamic visual understanding of the local environment for an indoor navigating robot

Cited by 23 publications

References 27 publications

Extracting Semantic Information from Visual Data: A Survey

Extracting Semantic Information from Visual Data: A Survey

Focusing Attention on Visual Features that Matter

3D Spatial Layout Propagation in a Video Sequence

Contact Info

Product

Resources

About