Improving Real-Time Construction Equipment Detection by Learning to Correct False Positives

Shuai Tang, Peng Chen, Liang Yu, Mani Golparvar-Fard

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Detecting construction equipment such as trucks, excavators, and mobile cranes from surveillance cameras is a vital part to provide robust and stable construction safety monitoring. A robust and real-time detection system is the key to success. In this paper, we investigate YOLOv3, a real-time object detector, for detecting common vehicle, i.e., car, bus, and truck as a preliminary study to gain insight on improving construction equipment detection. We prefer YOLOv3 for its superior accelerated inference speed, moderate model size, and efficient performance. Our major findings include (1) pretrained general-purpose YOLOv3 equipment detection model is adequate but often misses equipment at the far-end side of camera view; (2) we choose traffic scenes resembles construction sites, our best YOLOv3 model reaches 65.8% mean average precision (mAP) on test set; (3) YOLOv3-based equipment detection model has difficulty to transfer to novel scenes. When trained on 4 scenes and tested on 3 other scenes, test mAP drops to 31%; (4) Systematic confusion with background results in many vehicle detection false positives. We considerably improve overall detection mAP by learning a graph convolutional network (GCN) model to predict if detections are false positives. This GCN model improves equipment detection mAP from 65.8% to 69.3%.

Original languageEnglish (US)
Title of host publicationConstruction Research Congress 2020
Subtitle of host publicationComputer Applications - Selected Papers from the Construction Research Congress 2020
EditorsPingbo Tang, David Grau, Mounir El Asmar
PublisherAmerican Society of Civil Engineers
Pages1300-1309
Number of pages10
ISBN (Electronic)9780784482865
StatePublished - 2020
EventConstruction Research Congress 2020: Computer Applications - Tempe, United States
Duration: Mar 8 2020Mar 10 2020

Publication series

NameConstruction Research Congress 2020: Computer Applications - Selected Papers from the Construction Research Congress 2020

Conference

ConferenceConstruction Research Congress 2020: Computer Applications
CountryUnited States
CityTempe
Period3/8/203/10/20

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Building and Construction

Fingerprint Dive into the research topics of 'Improving Real-Time Construction Equipment Detection by Learning to Correct False Positives'. Together they form a unique fingerprint.

Cite this