---
title: "Separating Non-Stationary from Stationary Scene Components in a Sequence of Real World TV Images"
authors:
  - "Ramesh C. Jain"
  - "D. Militzer"
  - "Hans-Hellmut Nagel"
doi: ""
url: "https://ijcai.org/proceedings/1977/143"
pdf: "https://ijcai.org/proceedings/1977/0143.pdf"
venue: "Proceedings of the Fifth International Joint Conference on Artificial Intelligence"
year: 1977
pages: "612-617"
track: "Vision"
keywords:
---

# Separating Non-Stationary from Stationary Scene Components in a Sequence of Real World TV Images

Ramesh C. Jain, D. Militzer, Hans-Hellmut Nagel

*Proceedings of the Fifth International Joint Conference on Artificial Intelligence*, pages 612-617.

## Abstract

Results are presented for a new method to identify images of moving objects in a sequence of scene images, e.g. from a TV-camera observing a street intersection. The reported approach exploits the assumption that systematic greyvalue differencesbased on second order statistics - between consecutive frames are due to images of moving objects. No knowledge is assumed about size, shape, or tex-, ture for images of stationary or non-stationary scene components.