Fast on-line kernel density estimation for active object localization

Rhodes, Anthony D.; Quinn, Max H.; Mitchell, Melanie

doi:10.1109/ijcnn.2017.7965889

Cited by 5 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many data analysis problems, reaching from population analysis to computer vision [6,28], require estimating continuous models from discrete samples. Formally, this is the density estimation problem, where, given a sample fx i g $ pðxÞ, we would like to estimate the probability density function (PDF) p(x).…”

Section: Introductionmentioning

confidence: 99%

Data-driven deep density estimation

Puchert

Hermosilla

Ritschel

et al. 2021

Neural Comput & Applic

View full text Add to dashboard Cite

Density estimation plays a crucial role in many data analysis tasks, as it infers a continuous probability density function (PDF) from discrete samples. Thus, it is used in tasks as diverse as analyzing population data, spatial locations in 2D sensor readings, or reconstructing scenes from 3D scans. In this paper, we introduce a learned, data-driven deep density estimation (DDE) to infer PDFs in an accurate and efficient manner, while being independent of domain dimensionality or sample size. Furthermore, we do not require access to the original PDF during estimation, neither in parametric form, nor as priors, or in the form of many samples. This is enabled by training an unstructured convolutional neural network on an infinite stream of synthetic PDFs, as unbound amounts of synthetic training data generalize better across a deck of natural PDFs than any natural finite training data will do. Thus, we hope that our publicly available DDE method will be beneficial in many areas of data analysis, where continuous models are to be estimated from discrete observations.

show abstract

Section: Introductionmentioning

confidence: 99%

Data-driven deep density estimation

Puchert

Hermosilla

Ritschel

et al. 2021

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…Following [30] and [33], in the current study we use a dataset consisting of single pedestrian instances from the Portland State Dog-Walking Images for our proof of concept and comparative experiments [45]. This dataset contains 460 high-resolution annotated photographs, taken in a variety of locations.…”

Section: Datasetmentioning

confidence: 99%

Gaussian Processes with Context-Supported Priors for Active Object Localization

Rhodes

Witte²,

Mitchell

et al. 2018

2018 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

We devise an algorithm using a Bayesian optimization framework in conjunction with contextual visual data for the efficient localization of objects in still images. Recent research has demonstrated substantial progress in object localization and related tasks for computer vision. However, many current state-of-the-art object localization procedures still suffer from inaccuracy and inefficiency, in addition to failing to provide a principled and interpretable system amenable to high-level vision tasks. We address these issues with the current research.Our method encompasses an active search procedure that uses contextual data to generate initial bounding-box proposals for a target object. We train a convolutional neural network to approximate an offset distance from the target object. Next, we use a Gaussian Process to model this offset response signal over the search space of the target. We then employ a Bayesian active search for accurate localization of the target.In experiments, we compare our approach to a state-of-theart bounding-box regression method for a challenging pedestrian localization task. Our method exhibits a substantial improvement over this baseline regression method.

show abstract

“…Following [17] and [20], in the current study we use a subset consisting of single pedestrian instances from the Portland State Dog-Walking Images for our proof of concept and comparative experiments [30]. This subset contains 460 high-resolution annotated photographs, taken in a variety of locations.…”

Section: Datasetmentioning

confidence: 99%

Bayesian optimization for refining object proposals

Rhodes

Witte

Jednyak

et al. 2017

2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA)

Self Cite

View full text Add to dashboard Cite

We develop a general-purpose algorithm using a Bayesian optimization framework for the efficient refinement of object proposals. While recent research has achieved substantial progress for object localization and related objectives in computer vision, current state-of-the-art object localization procedures are nevertheless encumbered by inefficiency and inaccuracy. We present a novel, computationally efficient method for refining inaccurate bounding-box proposals for a target object using Bayesian optimization. Offline, image features from a convolutional neural network are used to train a model to predict an object proposal's offset distance from a target object. Online, this model is used in a Bayesian active search to improve inaccurate object proposals. In experiments, we compare our approach to a state-of-theart bounding-box regression method for localization refinement of pedestrian object proposals. Our method exhibits a substantial improvement for the task of localization refinement over this baseline regression method.

show abstract

Fast on-line kernel density estimation for active object localization

Cited by 5 publications

References 25 publications

Data-driven deep density estimation

Data-driven deep density estimation

Gaussian Processes with Context-Supported Priors for Active Object Localization

Bayesian optimization for refining object proposals

Contact Info

Product

Resources

About