Context and objectives
Human perception and interpretation is an indispensable component in many aspects of remote sensing image analysis. Human intervention is a requisite for visual image interpretation, where the interpreter actually performs the analysis. Even in computer-based digital image processing, human screening and interpretation is still needed at certain stages. Next to the remote sensing domain, human intervention plays an important role in other types of geodata processing such as GIS and cartography. Although it is crucial for adequately assessing automated systems’ performance, virtually no research has focussed on operator functioning.
The goal of the present project is to determine the human factors that influence operator functioning:
- To quantify operator performance in a variety, though limited number, of remote sensing practices using air- and spaceborne remote sensing imagery;
- To characterize operator performance and its determinants (both problem-specific and human factors);
- To identify possible interventions to enhance operator performance and formulate well-founded feedback guidelines regarding the problem definition and the operator efficiency for use in practical settings.
- A web tool was developed to (1) quantify operator performance, (2) characterize its external and human determinants, and (3) identify possible interventions to enhance operator efficiency for use in practical settings;
- Operator performance was far from perfect, typically reached 80% and varied considerably across operators;
- The amount of variability was dependent on the type of task;
- Across the interpretation tasks, we found that operator performance was mainly determined by individual human characteristics whereas external and technical factors influenced operator performance to a lesser extent. Men performed better than women at most interpretation tasks;
- With respect to external factors, more noisy and busy working environments negatively influenced operator performance;
- A marked performance drop over time was assessed, both for experts and novices.
|Project leader(s):||UGent - Remote Sensing / Spatial Analysis lab (REMOSA)|