Learning Object Location Predictors with Boosting and Grammar-Guided Feature Extraction

  title={Learning Object Location Predictors with Boosting and Grammar-Guided Feature Extraction},
  author={Damian Eads and Edward Rosten and David P. Helmbold},
We present BEAMER: a new spatially exploitative approach to learning object detectors which shows excellent results when applied to the task of detecting objects in greyscale aerial imagery in the presence of ambiguous and noisy data. There are four main contributions used to produce these results. First, we introduce a grammar-guided feature extraction system, enabling the exploration of a richer feature space while constraining the features to a useful subset. This is specified with a rule… 

Figures from this paper

Boosting in Location Space
This thesis introduces a new boosting algorithm (LocationBoost) that operates over an entire image at all times during training, directly predicts object locations, and minimizes a spatial loss function that is strongly motivated by object detection.
Approximate variable-length time series motif discovery using grammar inference
A novel approach, based on grammar induction, is proposed for approximate variable-length time series motif discovery, which offers the advantage of discovering hierarchical structure, regularity and grammar from the data.
Visualizing Variable-Length Time Series Motifs
It is demonstrated that grammar induction in time series can effectively identify repeated patterns without prior knowledge of their lengths, and a motif visualization system based on grammar induction is developed.
Finding approximate frequent patterns in streaming medical data
  • Jessica Lin, Yuan Li
  • Computer Science
    2010 IEEE 23rd International Symposium on Computer-Based Medical Systems (CBMS)
  • 2010
A novel approach based on grammar induction that allows the discovery of approximate, variable-length motifs in streaming data is proposed and the preliminary results show that the grammar-based approach is able to find some important motifS in some medical data, and suggest that using grammar- based algorithms for time series pattern discovery might be worth exploring.


A Boundary-Fragment-Model for Object Detection
The BFM detector is able to represent and detect object classes principally defined by their shape, rather than their appearance, and to achieve this with less supervision (such as the number of training images).
Learning to detect objects in images via a sparse, part-based representation
A learning-based approach to the problem of detecting objects in still, gray-scale images that makes use of a sparse, part-based representation is developed and a critical evaluation of the approach under the proposed standards is presented.
Rapid object detection using a boosted cascade of simple features
  • Paul A. Viola, Michael J. Jones
  • Computer Science
    Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001
  • 2001
A machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates and the introduction of a new image representation called the "integral image" which allows the features used by the detector to be computed very quickly.
A general framework for object detection
A general trainable framework for object detection in static images of cluttered scenes based on a wavelet representation of an object class derived from a statistical analysis of the class instances and a motion-based extension to enhance the performance of the detection algorithm over video sequences is presented.
An Exemplar Model for Learning Object Classes
An exemplar model that can learn and generate a region of interest around class instances in a training set, given only a set of images containing the visual class, which enables the detection of multiple instances of the object class in test images.
Object class recognition by unsupervised scale-invariant learning
The flexible nature of the model is demonstrated by excellent results over a range of datasets including geometrically constrained classes (e.g. faces, cars) and flexible objects (such as animals).
Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study
A large-scale evaluation of an approach that represents images as distributions of features extracted from a sparse set of keypoint locations and learns a Support Vector Machine classifier with kernels based on two effective measures for comparing distributions, the Earth Mover’s Distance and the χ2 distance.
Improvements of Object Detection Using Boosted Histograms
A method for object detection that combines AdaBoost learning with local histogram features that outperforms all methods reported in [5] for 7 out of 8 detection tasks and four object classes.
Multiple Object Class Detection with a Generative Model
The performance of the proposed multi-object class detection approach is competitive to state of the art approaches dedicated to a single object class recognition problem.
Grammar-guided Feature Extraction for Time Series Classification
A flexible, general-purpose technique for generating time series classifiers that incorporates the use of grammars to constrain the set of valid feature extraction programs and to provide a mechanism for incorporating domain expertise.