A Paradigm Shift in Mouza Map Vectorization: A Human-Machine Collaboration Approach

TL;DR

This paper introduces a semi-automated, human-machine collaboration approach for vectorizing complex Mouza maps, significantly improving efficiency over manual methods through CNN-based preprocessing and smoothing algorithms.

Contribution

It presents a novel semi-automated methodology combining CNN models and smoothing algorithms for efficient Mouza map vectorization, reducing manual effort.

Findings

Outperforms existing digitization methods in accuracy and speed.

Requires human intervention for high precision.

Validated on multiple maps with positive user feedback.

Abstract

Efficient vectorization of hand-drawn cadastral maps, such as Mouza maps in Bangladesh, poses a significant challenge due to their complex structures. Current manual digitization methods are time-consuming and labor-intensive. Our study proposes a semi-automated approach to streamline the digitization process, saving both time and human resources. Our methodology focuses on separating the plot boundaries and plot identifiers and applying our digitization methodology to convert both of them into vectorized format. To accomplish full vectorization, Convolutional Neural Network (CNN) models are utilized for pre-processing and plot number detection along with our smoothing algorithms based on the diversity of vector maps. The CNN models are trained with our own labeled dataset, generated from the maps, and smoothing algorithms are introduced from the various observations of the map's vector formats. Further human intervention remains essential for precision. We have evaluated our methods on several maps and provided both quantitative and qualitative results with user study. The result demonstrates that our methodology outperforms the existing map digitization processes significantly.