Understanding Human-Computer Interactions in Map Revision

Abstract

Abstract. It is difficult to track, parse and model human-computer interactions during editing and revising of documents, but it is necessary if we are to develop automated technologies that will aid or replace humans. This paper introduces a system for accessing and recording a stream of events related to human actions in a real-time cartographic map revision system. The recorded events are parsed into a sequence of meaningful user actions and an action representation in XML format is generated. We also report results of experiments on predicting user actions such as view changes, edits, road tracking/production using hidden Markov models.

Road tracking in aerial images based on human–computer interaction and Bayesian filtering

“…The event sequence is fed into the parser and is segmented into complete actions. A complete description on the human-computer interface is reported in Zhou et al, 2004. Besides providing analysis of human performance, the interface provides the operator with tools for evaluating the performance of the road tracker. As introduced in later sections, confidence values are generated from the proposed Bayesian filters that allow the performance of the model to be compared directly to the user performance through the realtime tracker interface.…”

Spatial–temporal modeling of interactive image interpretation

“…This is still considered the preferred solution as it is robust, flexible, and gives the user control over the interpretation tasks (e.g., Everingham et al, 2003;Koike et al, 2001). Zhou et al (2005) proposed a general framework for human-guided image interpretation consisting of five components, a human-computer interface, a user model, a set of computational algorithms, a knowledge transfer scheme, and a performance evaluation scheme. Of these five components, the human-computer interface and the computational algorithms have been studied extensively, but research on the knowledge transfer scheme, more specifically on the learning of computational algorithms from humans, has been very limited.…”

Online Learning With Novelty Detection in Human-Guided Road Tracking

“…We have developed a semi-automatic road tracking system for the United States Geological Survey (USGS) map revision platform [32]. This platform is used to revise the USGS 7.5-minute quadrangle topographic maps [33].…”

“…Zhou et al [5] proposed a general framework for humanguided image interpretation, which consists of five components, a human-computer interface, a user model, computational algorithms, a knowledge transfer scheme, and a performance evaluation scheme. Among these five components, the interface and the computational algorithms have been studied extensively [6], [7], [8], [9].…”