Data&Codes.rar

The codes and data for the paper titled “Modeling Multi-Saliency-Based Navigation Cues for Human Navigation in Urban Street Environments".DataIn the folder Code:-<i>StrucutalCalculation.py </i>is used for the calculation of 3D structual module.In the folder Data, there are:<i>*.jpg:</i> 30 panoramic images of road intersections.<i>*.xlsx:</i> results obtained from Questionnaire Set 1 and 2.Other related open-source tools:<br>How to locate reference inforamtion mentioned in the study:Census Statistics of Hong Kong: open the url, click Major Housing Estates, select Prosperous Garden. Reference data is described in demographic and ecomonic characteristics.Usage:-Visual saliency prediction:Step 1: Image Segmentation (Mask2Former)Step 2: Saliency Object Prediction (VST)Step3: Mask GenerationStep4: Image impaitingStep5: Saliency prediction (MDS-ViTNet), one can fine-tuned the model by using the eye-tracking data we provided.-Semantic saliency prediction:Step1: POI embeddingStep2: add weighting following *.xlsx provided.Step3: Average pooling.-Structural calculation:Step1: Hotspot identification.Step2: add weighting follwing the <i>StrucutalCalculation.py</i>.<br>regression, Kappa, and Cronbach could be easily performed by Python or R.