Active object recognition: Looking for differences

被引：20

作者：

Callari, FG ^{[1
]}

Ferrie, FP ^{[1
]}

机构：

[1] McGill Univ, Ctr Intelligent Machines, Montreal, PQ H3X 2A7, Canada

来源：

INTERNATIONAL JOURNAL OF COMPUTER VISION | 2001年 / 43卷 / 03期

关键词：

active vision; control of perception; learning in computer vision;

D O I：

10.1023/A:1011135513777

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper introduces an information-based methodology for view selection that actively exploits prior knowledge about the objects to be found in a scene. The methodology is used to implement an active recognition strategy which effectively puts prior constraints from the object database into the gaze control (planning) loop. Theoretical results are presented and discussed along with promising experimental data.

引用

页码：189 / 204

页数：16

共 27 条

[1]

ALOIMONOS J, 1987, P 1 INT C COMP VIS L

[2] ACTIVE PERCEPTION [J].

BAJCSY, R .

PROCEEDINGS OF THE IEEE, 1988, 76 (08) :996-1005

[3]

Barr A. H., 1981, IEEE COMPUT GRAPH, V1, P1, DOI [10.1109/MCG.1981.1673788, DOI 10.1109/MCG.1981.1673788]

[4]

Bishop C. M., 1995, NEURAL NETWORKS PATT

[5]

BRIDLE JS, 1990, NATO ASI F, V68

[6]

Cover T. M., 2005, ELEM INF THEORY, DOI 10.1002/047174882X

[7]

DICKINSON S, 1994, P EUR C COMP VIS STO, pB3

[8]

Fedorov VV., 1972, THEORY OPTIMAL EXPT

[9]

Golub GH, 2013, Matrix Computations, V4

[10]

GROSS A, 1988, P INT C COMP VIS, P690

← 1 2 3 →