University of Illinois Urbana-Champaign

Characterizing construction equipment activities in long video sequences of earthmoving operations via kinematic features

Bao, Ruxiao

Content Files
BAO-THESIS-2015.pdf

Permalink

https://hdl.handle.net/2142/89233

Description

Title
Characterizing construction equipment activities in long video sequences of earthmoving operations via kinematic features
Author(s)
Bao, Ruxiao
Issue Date
2015-12-08
Director of Research (if dissertation) or Advisor (if thesis)
Golparvar Fard, Mani
Department of Study
Civil & Environmental Engineering
Discipline
Civil Engineering
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
M.S.
Degree Level
Thesis
Date of Ingest
2016-03-02T21:07:03Z
Keyword(s)
  • Kinematic Features
  • Activity Recognition
  • Convolutional Neural Network
  • Construction Equipment
Abstract
This thesis presents a fast and scalable method for activity analysis of construction equipment involved in earthmoving operations from highly varying long-sequence videos obtained from fixed cameras. A common approach to characterize equipment activities consists of detecting and tracking the equipment within the video volume, recognizing interest points and describing them locally, followed by a bag-of-words representation for classifying activities. While successful results have been achieved in each aspect of detection, tracking, and activity recognition, the highly varying degree of intra-class variability in resources, occlusions and scene clutter, the difficulties in defining visually-distinct activities, together with long computational time have challenged scalability of current solutions. In this thesis, we present a new end-to-end automated method to recognize the equipment activities by simultaneously detecting and tracking features, and characterizing the spatial kinematics of features via a decision tree. The method is tested on an unprecedented dataset of 5hr-long real-world videos of interacting pairs of excavators and trucks. The Experimental results show that the method is capable of activity recognition with accuracy of 88.91% with a computational time less than 1- to-1 ratio for each video length. The benefits of the proposed method for root-cause assessment of performance deviations are discussed.
Graduation Semester
2015-12
Type of Resource
text
Permalink
http://hdl.handle.net/2142/89233
Copyright and License Information
Copyright 2015 Ruxiao Bao

Owning Collections

Dissertations and Theses - Civil and Environmental Engineering
Graduate Dissertations and Theses at Illinois PRIMARY
Graduate Theses and Dissertations at Illinois