eprintid: 12640
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/01/26/40
datestamp: 2023-11-10 03:27:12
lastmod: 2023-11-10 03:27:12
status_changed: 2023-11-10 01:49:10
type: conference_item
metadata_visibility: show
creators_name: Fujita, H.
creators_name: Itagaki, M.
creators_name: Ichikawa, K.
creators_name: Hooi, Y.K.
creators_name: Kawahara, K.
creators_name: Sarlan, A.
title: Fine-tuned Surface Object Detection Applying Pre-trained Mask R-CNN Models
ispublished: pub
keywords: Convolutional neural networks; Intelligent computing; Object recognition; Roads and streets, CNN models; False negatives; Four Mask; Metric calculation methods; Mutual interference; Object class; Road surfaces; Validation data, Object detection
note: cited By 1; Conference of 2020 International Conference on Computational Intelligence, ICCI 2020 ; Conference Date: 8 October 2020 Through 9 October 2020; Conference Code:164916
abstract: This study evaluates road surface object detection tasks using four Mask R-CNN models available on the Tensor-Flow Object Detection API. The models were pre-trained using COCO datasets and fine-tuned by 15,1SS segmented road surface annotation tags. Validation data set was used to obtain Average Precisions and Average Recalls. Result indicates a substantial false negatives or "left judgement"counts for linear cracks, joints, fillings, potholes, stains, shadows and patching with grid cracks classes. There were significant number of incorrectly predicted label instances. To improve the result, an alternative metric calculation method was tested. However, the results showed strong mutual interferences caused by misinterpretation of the scratches with other object classes. © 2020 IEEE.
date: 2020
publisher: Institute of Electrical and Electronics Engineers Inc.
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85097532534&doi=10.1109%2fICCI51257.2020.9247666&partnerID=40&md5=2758293eafa9dbd7d5a0e244112984ec
id_number: 10.1109/ICCI51257.2020.9247666
full_text_status: none
publication: 2020 International Conference on Computational Intelligence, ICCI 2020
pagerange: 17-22
refereed: TRUE
isbn: 9781728154473
citation:   Fujita, H. and Itagaki, M. and Ichikawa, K. and Hooi, Y.K. and Kawahara, K. and Sarlan, A.  (2020) Fine-tuned Surface Object Detection Applying Pre-trained Mask R-CNN Models.  In: UNSPECIFIED.