Learning Grouping Strategies for 2D and 3D Object Recognition*
نویسنده
چکیده
The Schema Learning System (SLS) automatically assembles task-specific object recognition programs from existing IU algorithms. SLS brings together two emerging technologies image understanding and machine learning to automatically build customized procedures for recognizing and extracting specific object classes in constrained contexts. This paper describes the representations and algorithms underlying SLS, and presents an example of SLS learning to recognize rooftops in aerial images of Ft. Hood. This task is the first of several tasks from the ARPA/ORD sponsored RADIUS project [6] that SLS is intended to learn without human interaction. In later experiments, SLS will be tasked to automatically construct 3D models of buildings and other objects of interest from overlapping aerial images.
منابع مشابه
Hand Gesture Recognition from RGB-D Data using 2D and 3D Convolutional Neural Networks: a comparative study
Despite considerable enhances in recognizing hand gestures from still images, there are still many challenges in the classification of hand gestures in videos. The latter comes with more challenges, including higher computational complexity and arduous task of representing temporal features. Hand movement dynamics, represented by temporal features, have to be extracted by analyzing the total fr...
متن کاملSeeing Glassware: from Edge Detection to Pose Estimation and Shape Recovery
Perception of transparent objects has been an open challenge in robotics despite advances in sensors and datadriven learning approaches. In this paper, we introduce a new approach that combines recent advances in learnt object detectors with perceptual grouping in 2D, and projective geometry of apparent contours in 3D. We train a state of the art structured edge detector on an annotated set of ...
متن کاملOutline-Based Part Segmentation Using Intermediate-Level Symmetries
A new part segmentation approach is presented which works on real images. These images contain 3D objects with textures and shadows on a complex background. The proposed approach relies on the outline of the object to guide the grouping of lines using symmetry and colinearity principles. This grouping of lines leads to simple shapes which can be modeled by 3D primitives such as geons or general...
متن کاملLearning Control Strategies for Object Recognition
This paper presents a system for learning object-speciic recognition strategies from training images and libraries of image understanding routines. The motivation for this work is that thirty years of computer vision research has produced hundreds of algorithms for visual subtasks ranging from edge detection to pose determination, but very few complete vision systems. The Schema Learning System...
متن کاملRelational Model Construction and 3D Object Recognition from Single 2D Monochromatic Image
This paper reports a method for automatically constructing a relational model of a rigid 3D object, to represent view-independent relations among its component parts, and of using such a model to recognise the object from single monochromatic images. The relational model is a graph associated with procedural constraints. It is constructed by a statistic analysis of images generated by projectin...
متن کامل