| actionRecord | Auxilliary Tool: A data structure that keeps track of a vector-valued action, and a time at which that action was taken |
| BlockTimer | Auxilliary Tool: A class for tracking the absolute runtime of several (possibly overlapping) blocks of code |
| BoxFeature | Auxilliary Tool: A linear feature that uses the "Integral
Image" trick to efficiently evaluate convolution kernels on an image, where the kernel can be expressed as a sum of boxes |
| BoxFeature2 | Auxilliary Tool: A linear feature that uses the "Integral
Image" trick to efficiently evaluate convolution kernels on an image, where the kernel can be expressed as a sum of boxes |
| ConvolutionalLogisticPolicy | Auxilliary Tool: A class for implementing convolutional logistic policies, which were first used in the IPOMDP domain in Butko and Movellan, 2008 (see Related Publications) |
| DetectionEvaluator | Auxilliary Tool: A tool for evaluating the performance of a whole-image-object-detector, such as a GentleBoostCascadedClassifier, for performance on an ImageDataSet |
| DetectionEvaluator2 | Auxilliary Tool: A tool for evaluating the performance of a whole-image-object-detector, such as a GentleBoostCascadedClassifier, for performance on an ImageDataSet |
| EvaluationMetrics | Auxilliary Tool: A data structure that collects statistics about the performance of a GentleBoostCascadedClassifier on some ImageDataSet |
| FastPatchList | Auxilliary Tool: A class that does the necessary book keeping for filtering an image quickly at many scales. FastPatchList is an implementation that sacrifices filtering accuracy for filtering speed |
| FastPatchList2 | Auxilliary Tool: A class that does the necessary book keeping for filtering an image quickly at many scales. FastPatchList is an implementation that sacrifices filtering accuracy for filtering speed |
| FastSalience | Machine Perception Primitive: An implementation of the "Fast Salience Using Natural-statistics" algorithm from Butko, et al., 2008. FastSUN is an efficient implementation of Zhang et al.'s SUN algorithm, which is documented in Zhang, et al., 2008 (see Related Publications) |
| Feature | Auxilliary Tool: A purely virtual class for providing the skeleton for specific features. This allows different features to be manipulated using a common set of tools |
| Feature2 | Auxilliary Tool: A purely virtual class for providing the skeleton for specific features. This allows different features to be manipulated using a common set of tools |
| FeaturePerformance | Auxilliary Tool: A data structure that keeps track of the a particular image feature setting, and performance of that feature |
| FeaturePerformance2 | Auxilliary Tool: A data structure that keeps track of the a particular image feature setting, and performance of that feature |
| FeatureRegressor | Auxilliary Tool: A data structure that learns a non-linear tuning curve for mapping feature outputs to image labels. This is the "weak learner" used by GentleBoost |
| FeatureRegressor2 | Auxilliary Tool: A data structure that learns a non-linear tuning curve for mapping feature outputs to image labels. This is the "weak learner" used by GentleBoost |
| GentleBoostCascadedClassifier | Machine Perception Primitive: An implementation of a GentleBoost cascaded classifier for full image object search |
| GentleBoostCascadedClassifier2 | Machine Perception Primitive: An implementation of a GentleBoost cascaded classifier for full image object search |
| GentleBoostClassifier | Machine Perception Primitive: An implementation of a GentleBoost classifier for image patch classification |
| GentleBoostClassifier2 | Machine Perception Primitive: An implementation of a GentleBoost classifier for image patch classification |
| HaarFeature | Auxilliary Tool: A linear feature that uses Haar Wavelets, which are a certain kind of box filter |
| HaarFeature2 | Auxilliary Tool: A linear feature that uses Haar Wavelets, which are a certain kind of box filter |
| ImageDataSet | Auxilliary Tool: A data structure for maintaining a list of image files and image labels to facilitate training and testing |
| ImageDataSet2 | Auxilliary Tool: A data structure for maintaining a list of image files and image labels to facilitate training and testing |
| ImageKalmanFilter | Auxilliary Tool: A Collection of Kalman Filters for estimating the appearance of an image |
| ImagePatch | Auxilliary Tool: A data structure that represents an image in an efficient memory layout, and manipulates that image in ways useful for efficient feature processing |
| ImagePatch2 | Auxilliary Tool: A data structure that represents an image in an efficient memory layout, and manipulates that image in ways useful for efficient feature processing |
| ImagePatchPyramid | Auxilliary Tool: The main data structure for the MIPOMDP algorithm. It is reponsible for generating the MIPOMDP observation vector. The ImagePatchPyramid (IPP) is described in detail in Butko & Movellan 2009 (see Related Publications) |
| InternalMotionModel | Machine Perception Primitive: An implementation of a model that allows a robot to learn about its own motion |
| likelihood | Auxilliary Tool: A data structure that keeps track of the likelihood value for a particular parameter setting, and the gradient of the value function with resepct to that parameter setting |
| MatrixKalmanFilter | Auxilliary Tool: A Kalman Filter for estimating the values of a matrix, which is like doing online linear regression from a probability theory perspective |
| MIPOMDP | Machine Perception Primitive: An implementation of the "Multinomial IPOMDP" algorithm from Butko and Movellan, 2009 (see Related Publications) |
| MultinomialObservationModel | Auxilliary Tool: Multionomial Observation Model, as described in Butko and Movellan, CVPR 2009 (see Related Publications). This data structure maintains the mapping between object detector output and the probability that the target object is located at every grid-cell |
| MultiObjectTrackingState | Auxilliary Tool: A class for trying to uniquely identify and track several objects simultaneously |
| ObjectDetector | Auxilliary Tool: A virtual class for providing the skeleton for specific object detectors |
| OpenCV2BoxFilter | Auxilliary Tool: A class for efficiently applying multiple box convolutions to the same image |
| OpenCVBoxFilter | Auxilliary Tool: A class for efficiently applying multiple box convolutions to the same image |
| OpenCVHaarDetector | Auxilliary Tool: A specific object detector that uses OpenCV's Haar Cascade Classifier to detect objects. The performance / behavior of the object detector is stored in an XML file, which is passed in in the constructor. The XML file provided in the data directory may be used for finding faces, or you can use OpenCV to train your own |
| OpenLoopPolicies | Auxilliary Tool: A static class for some open-loop fixation strategies, which can be used as points of comparison to more sophisticated search strategies |
| PatchDataset | Auxilliary Tool: A tool for managing the data used in training GentleBoost classifiers |
| PatchDataset2 | Auxilliary Tool: A tool for managing the data used in training GentleBoost classifiers |
| PatchList | Auxilliary Tool: A class that does the necessary book keeping for filtering an image quickly at many scales |
| PatchList2 | Auxilliary Tool: A class that does the necessary book keeping for filtering an image quickly at many scales |
| PerformanceMetrics | Auxilliary Tool: A data structure that keeps track of how a classifier (specifically a cascaded classifier) is performing. This is useful for evaluating candidate features to add |
| SearchResult | Auxilliary Tool: A data structure that keeps track of where objects were detected in the image, and how confident the classifier is in those detections |
| TrackingObject | Auxilliary Tool: A data structure for keeping simple statistics of objects, useful for trying to uniquely identify and track several objects simultaneously |
