Fine-tuned Pre-trained Mask R-CNN Models for Surface Object Detection

TL;DR

This paper evaluates the effectiveness of fine-tuned Mask R-CNN models for detecting surface objects on roads, focusing on archaeological stone surfaces, and explores modifications to improve detection accuracy.

Contribution

It introduces a modified confusion matrix to enhance true positive detection rates without affecting segmentation mask performance.

Findings

Significant reduction in false negatives and improved bounding box detection.

No notable change in segmentation mask accuracy.

Modified confusion matrix helps prioritize true positives.

Abstract

This study evaluates road surface object detection tasks using four Mask R-CNN models as a pre-study of surface deterioration detection of stone-made archaeological objects. The models were pre-trained and fine-tuned by COCO datasets and 15,188 segmented road surface annotation tags. The quality of the models were measured using Average Precisions and Average Recalls. Result indicates substantial number of counts of false negatives, i.e. left detection and unclassified detections. A modified confusion matrix model to avoid prioritizing IoU is tested and there are notable true positive increases in bounding box detection, but almost no changes in segmentation masks.