Seokho Chi

Automated Object Identification Using Optical Video Cameras on Construction Sites

Visual recording devices such as video cameras, CCTVs, or webcams have been broadly used to facilitate work progress or safety monitoring on construction sites. Without human intervention, however, both real-time reasoning about captured scenes and interpretation of recorded images are challenging tasks. This article presents an exploratory method for automated object identification using standard video cameras on construction sites. The proposed method supports real-time detection and classification of mobile heavy equipment and workers. The background subtraction algorithm extracts motion pixels from an image sequence, the pixels are then grouped into regions to represent moving objects, and finally the regions are identified as a certain object using classifiers. For evaluating the method, the formulated computer-aided process was implemented on actual construction sites, and promising results were obtained. This article is expected to contribute to future applications of automated monitoring systems of work zone safety or productivity.

Image-Based Safety Assessment: Automated Spatial Safety Risk Identification of Earthmoving and Surface Mining Activities

This paper presents an automated image-based safety assessment method for earthmoving and surface mining activities. The literature review revealed the possible causes of accidents on earthmoving operations, investigated the spatial risk factors of these types of accident, and identified spatial data needs for automated safety assessment based on current safety regulations. Image-based data collection devices and algorithms for safety assessment were then evaluated. Analysis methods and rules for monitoring safety violations were also discussed. The experimental results showed that the safety assessment method collected spatial data using stereo vision cameras, applied object identification and tracking algorithms, and finally utilized identified and tracked object information for safety decision-making.

Development of Network-Level Project Screening Methods Supporting the 4-Year Pavement Management Plan in Texas

The Texas Department of Transportation (TxDOT) is concerned about the widening gap between pavement preservation needs and available funding. Thus, the TxDOT Austin District Pavement Engineer (DPE) has investigated methods to strategically allocate available pavement funding to potential projects that improve the overall performance of the District and Texas highway systems. The primary objective of the study presented in this paper is to develop a network-level project screening and ranking method that supports the Austin District 4-year pavement management plan development. The study developed candidate project selection and ranking algorithms that evaluated pavement conditions of each project candidate using data contained in the Pavement Management Information system (PMIS) database and incorporated insights from Austin District pavement experts; and implemented the developed method and supporting algorithm. This process previously required weeks to complete, but now requires about 10 minutes including data preparation and running the analysis algorithm, which enables the Austin DPE to devote more time and resources to conducting field visits, performing project-level evaluation and testing candidate projects. The case study results showed that the proposed method assisted the DPE in evaluating and prioritizing projects and allocating funds to the right projects at the right time.

Trends of Fall Accidents in the U.S. Construction Industry

AbstractFall accidents constitute a crucial type of accident in the construction industry. This study investigates fall accidents that occurred in the United States between 1997 and 2012. Using the...

Development of a Safety Inspection Framework on Construction Sites Using Mobile Computing

AbstractSite safety inspection is an essential task to ensure that construction operations are carried out in a safe manner, in accordance with relevant health and safety policies and standards of a particular jurisdiction. It is also critical to the smooth execution, monitoring, and controlling of construction activities. The evidence gathered from construction experts as well as from previous studies suggests that the efficiency and effectiveness of current inspection processes are less than satisfactory. This paper reports an Australian research project that develops an innovative safety inspection approach to incorporate mobile computing technologies into safety inspection processes in order to facilitate more effective data collection, processing, and control practices. The paper also discusses the interview results of safety practitioners about the proposed inspection approach. The approach was implemented through the development and test of a prototype mobile inspection tool. The feasibility and us...

Adaptive Detector and Tracker on Construction Sites Using Functional Integration and Online Learning

AbstractTracking construction equipment is a major task when monitoring work in progress and performance on construction sites. Real-time location data of heavy equipment can be used not only to pr...

Sustainable Road Management in Texas: Network-Level Flexible Pavement Structural Condition Analysis Using Data-Mining Techniques

The research team recognized the value of network-level Falling Weight Deflectometer (FWD) testing to evaluate the structural condition trends of flexible pavements. However, practical limitations due to the cost of testing, traffic control and safety concerns and the ability to test a large network may discourage some agencies from conducting the network-level FWD testing. For this reason, the surrogate measure of the Structural Condition Index (SCI) is suggested for use. The main purpose of the research presented in this paper is to investigate data mining strategies and to develop a prediction method of the structural condition trends for network-level applications which does not require FWD testing. The research team first evaluated the existing and historical pavement condition, distress, ride, traffic and other data attributes in the Texas Department of Transportation (TxDOT) Pavement Maintenance Information System (PMIS), applied data mining strategies to the data, discovered useful patterns and knowledge for SCI value prediction, and finally provided a reasonable measure of pavement structural condition which is correlated to the SCI. To evaluate the performance of the developed prediction approach, a case study was conducted using the SCI data calculated from the FWD data collected on flexible pavements over a 5-year period (2005 – 09) from 354 PMIS sections representing 37 pavement sections on the Texas highway system. The preliminary study results showed that the proposed approach can be used as a supportive pavement structural index in the event when FWD deflection data is not available and help pavement managers identify the timing and appropriate treatment level of preventive maintenance activities.

Development of an Automated Safety Assessment Framework for Construction Activities

This paper presents an ongoing research project concerning the development of an automated safety assessment framework for earthmoving and surface mining activities. This research seeks to determine data needs for safety assessment and investigates how to utilize collected data to promote more informed and efficient safety decision-making. The research first examined accidents and fatalities involved with earthmoving and surface mining activities—more specifically, those involving loading, hauling, and dumping operations,—investigated risk factors involved with the accidents, and finally identified data needs for safety assessment based on safety regulations and practices. An automated safety assessment method was then developed using the data needs that had been identified. This research is expected to contribute to the introduction of a fundamental framework for automated safety assessment and the systematic collection of safety-related data from construction activities. Implementation of the entire safety assessment process on actual construction sites remains a task for future research.

Sound Event Recognition-Based Classification Model for Automated Emergency Detection in Indoor Environment

Prompt emergency detection and response in indoor environments is a significant issue due to the difficulties in detecting indoor emergency events. However, current indoor monitoring tasks are mainly carried out by manual observations of occupants and such human-dependent methods generally have limitations in taking actions against emergency events. Many researchers have made much effort to develop automated indoor monitoring systems using wearable sensing device technologies and computer vision. While these methods have various advantages, there still remain challenges to be addressed for detecting indoor emergency events; for instance, wearable sensors need to be attached to a human body and occlusions make it hard to recognize the emergencies. To overcome those deficiencies, this paper proposes a sound event recognition (SER)-based indoor event classification (e.g., emergency and normal event) method with a convolutional neural network (CNN). The research consists of four main steps. First, the sound types of indoor events are determined as four emergency sounds (explosion, gunshot, glass break, and scream) and one normal sound (sleeping). Second, 692 sound data of identified events are collected from online sound data sharing services, and the preprocessing is performed. Third, SER model is developed through CNN algorithm with log-scaled mel-spectrogram features. Finally, model performance is evaluated using 5-fold cross validation. The experimental results showed that the sounds caused by indoor emergency events could be automatically recognized by the proposed method with F-score of 77.32%, which demonstrates its applicability for real emergency situations.

Sequential Pattern Analyses of Damages on Bridge Elements for Preventive Maintenance

For the safety and serviceability of aging bridges, it is important to understand how the current conditions of the bridges will deteriorate in the future as time goes by. The primary goal of this research is to analyze sequential patterns of damages on the bridge elements that are normally recorded through site inspections and managed by the bridge management system (BMS). To achieve the research goal, the research team first discovered a number of bridge clusters with distinguished characteristics by using a data clustering algorithm. Sequential pattern mining was then utilized to extract types and sequences of damages on bridge elements frequently seen in each cluster. The data used for the analyses was collected from BMS managed by the Korea Institute of Civil Engineering and Building Technology. This BMS includes the general, structural, traffic, and weather information of 6773 bridges (i.e., the total of 127 attributes) and contains 834,815 site inspection records of the bridge elements. A preliminary test was performed by using a dataset of 1542 Pre-Stressed Concrete I-shape type bridges for the validation purpose. The results of this study showed application potential to estimating future condition changes of the bridges based on the past inspection records for preventive bridge maintenance.