Digitalising Probation with Geospatial AI: Street-Level Human Perception in İstanbul’s Fatih District

Abstract

This paper explores the intersection of geospatial artificial intelligence (GeoAI), computer vision, and environmental criminology to enhance modern community supervision and probation monitoring frameworks. Focusing on streetscapes across the Fatih district of Istanbul, we examine how deep-learning-derived human perception indicators (such as safety, vibrancy, and visual disorder) inform spatial risk assessment and rehabilitative intervention pathways.

Yunus Serhat Bıçakçı

Assistant Professor

Assistant Professor specializing in GeoAI, Multimodal Vision-Language Models, and Spatial Data Science.