This work focuses on the development of objective measures of visual complexity for streetscapes and their application on online map services. In order to measure visual complexity of streetscapes, we have used the statistics of image features such as local contrast, local spatial frequency and CIELab color. We show how that these statistics are correlated with the human perception of visual complexity for streetscape environments. In this regard, other state-of-art measures are also analyzed. However, our proposed measures are more robust in the sense that they can be used for daytime and nighttime scenes. Finally, we apply these objective measures for producing city maps or visualizations which describe perceived information.
展开▼