Context-based vision system for place and object recognition

Torralba, Murphy Murphy, Freeman

2003 · 883 citations · 20 references

DOIFull text

Open access

Concepts

TL;DR

A vision system must recognize its location and main objects while navigating an environment. The paper proposes a context‑based vision system for place and object recognition. The system uses a low‑dimensional global image representation to identify familiar locations, categorize new environments, and supply contextual priors that simplify object recognition. The system recognizes over 60 locations and more than 20 object types, and has been integrated into a mobile platform that delivers real‑time feedback.

Abstract

While navigating in an environment, a vision system has to be able to recognize where it is and what the main objects in the scene are. We present a context-based vision system for place and object recognition. The goal is to identify familiar locations (e.g., office 610, conference room 941, main street), to categorize new environments (office, corridor, street) and to use that information to provide contextual priors for object recognition (e.g., tables are more likely in an office than a street). We present a low-dimensional global image representation that provides relevant information for place recognition and categorization, and show how such contextual information introduces strong priors that simplify object recognition. We have trained the system to recognize over 60 locations (indoors and outdoors) and to suggest the presence and locations of more than 20 different object types. The algorithm has been integrated into a mobile system that provides realtime feedback to the user.

References

20