Image Chunking: Defining Spatial Building Blocks for Scene Analysis
Rapid judgments about the properties and spatial relations of objects are the crux of visually guided interaction with the world. Vision begins, however, with essentially pointwise representations of the scene, such as arrays of pixels or small edge fragments. For adequate time-performance in...
| Main Author: | |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/6854 |
| _version_ | 1811091034500759552 |
|---|---|
| author | Mahoney, James V. |
| author_facet | Mahoney, James V. |
| author_sort | Mahoney, James V. |
| collection | MIT |
| description | Rapid judgments about the properties and spatial relations of objects are the crux of visually guided interaction with the world. Vision begins, however, with essentially pointwise representations of the scene, such as arrays of pixels or small edge fragments. For adequate time-performance in recognition, manipulation, navigation, and reasoning, the processes that extract meaningful entities from the pointwise representations must exploit parallelism. This report develops a framework for the fast extraction of scene entities, based on a simple, local model of parallel computation.sAn image chunk is a subset of an image that can act as a unit in the course of spatial analysis. A parallel preprocessing stage constructs a variety of simple chunks uniformly over the visual array. On the basis of these chunks, subsequent serial processes locate relevant scene components and assemble detailed descriptions of them rapidly. This thesis defines image chunks that facilitate the most potentially time-consuming operations of spatial analysis---boundary tracing, area coloring, and the selection of locations at which to apply detailed analysis. Fast parallel processes for computing these chunks from images, and chunk-based formulations of indexing, tracing, and coloring, are presented. These processes have been simulated and evaluated on the lisp machine and the connection machine. |
| first_indexed | 2024-09-23T14:56:04Z |
| id | mit-1721.1/6854 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T14:56:04Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/68542019-04-12T08:32:34Z Image Chunking: Defining Spatial Building Blocks for Scene Analysis Mahoney, James V. machine vision chunking segmentation tracing blobsdetection image understanding visual routines region growing Rapid judgments about the properties and spatial relations of objects are the crux of visually guided interaction with the world. Vision begins, however, with essentially pointwise representations of the scene, such as arrays of pixels or small edge fragments. For adequate time-performance in recognition, manipulation, navigation, and reasoning, the processes that extract meaningful entities from the pointwise representations must exploit parallelism. This report develops a framework for the fast extraction of scene entities, based on a simple, local model of parallel computation.sAn image chunk is a subset of an image that can act as a unit in the course of spatial analysis. A parallel preprocessing stage constructs a variety of simple chunks uniformly over the visual array. On the basis of these chunks, subsequent serial processes locate relevant scene components and assemble detailed descriptions of them rapidly. This thesis defines image chunks that facilitate the most potentially time-consuming operations of spatial analysis---boundary tracing, area coloring, and the selection of locations at which to apply detailed analysis. Fast parallel processes for computing these chunks from images, and chunk-based formulations of indexing, tracing, and coloring, are presented. These processes have been simulated and evaluated on the lisp machine and the connection machine. 2004-10-20T20:02:38Z 2004-10-20T20:02:38Z 1987-08-01 AITR-980 http://hdl.handle.net/1721.1/6854 en_US AITR-980 188 p. 11497118 bytes 8961816 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | machine vision chunking segmentation tracing blobsdetection image understanding visual routines region growing Mahoney, James V. Image Chunking: Defining Spatial Building Blocks for Scene Analysis |
| title | Image Chunking: Defining Spatial Building Blocks for Scene Analysis |
| title_full | Image Chunking: Defining Spatial Building Blocks for Scene Analysis |
| title_fullStr | Image Chunking: Defining Spatial Building Blocks for Scene Analysis |
| title_full_unstemmed | Image Chunking: Defining Spatial Building Blocks for Scene Analysis |
| title_short | Image Chunking: Defining Spatial Building Blocks for Scene Analysis |
| title_sort | image chunking defining spatial building blocks for scene analysis |
| topic | machine vision chunking segmentation tracing blobsdetection image understanding visual routines region growing |
| url | http://hdl.handle.net/1721.1/6854 |
| work_keys_str_mv | AT mahoneyjamesv imagechunkingdefiningspatialbuildingblocksforsceneanalysis |