---
title: "Spatial Object Perception from an Image"
authors:
  - "Radu Horaud"
doi: ""
url: "https://ijcai.org/proceedings/1985/229"
pdf: "https://ijcai.org/proceedings/1985/0229.pdf"
venue: "Proceedings of the Ninth International Joint Conference on Artificial Intelligence"
year: 1985
pages: "1116-1118"
track: "Robotics"
keywords:
---

# Spatial Object Perception from an Image

Radu Horaud

*Proceedings of the Ninth International Joint Conference on Artificial Intelligence*, pages 1116-1118.

## Abstract

In this paper we address the problern of finding the spatial position and orientation of an object from a single image. It is assumed that the image formation process and an object model are known in advance. Sets of image lines are backprojected and constraints on their spatial int e rpretations are derived. A search space is then constructed where each node represents a space feature wi th a model assignment. Next, a hypothes i ze-and - test recognition strategy is used to select a solution, that is to determine six degrees of freedom of a part from a set of featur e s. Finally we discuss the efficiency and the rel i abil i ty of the me t hod.