Cover Image

Not for Sale



View/Hide Left Panel
Click for next page ( 43


The National Academies | 500 Fifth St. N.W. | Washington, D.C. 20001
Copyright © National Academy of Sciences. All rights reserved.
Terms of Use and Privacy Statement



Below are the first 10 and last 10 pages of uncorrected machine-read text (when available) of this chapter, followed by the top 30 algorithmically extracted key phrases from the chapter as a whole.
Intended to provide our own search engines and external engines with highly rich, chapter-representative searchable text on the opening pages of each chapter. Because it is UNCORRECTED material, please consider the following text as a useful but insufficient proxy for the authoritative book pages.

Do not use for reproduction, copying, pasting, or reading; exclusively for search engines.

OCR for page 42
C H A P T E R 5 General Guidelines for Video Data Analysis Because all the data sets discussed in this report used video Each data set to be analyzed for this project typically has cameras to record driver behavior, certain rules need to be two data types associated with it. When applicable, video files followed. All the naturalistic data sets identified in this proj- will exist in a certain format, such as MPEG2, Audio Video ect are protected by the VT IRB, a committee that approves, Interleaved (AVI), or MP4. Additionally, each video file will monitors, and reviews research involving humans with the be associated with a parametric data file, such as a comma- aim of protecting the rights and welfare of the study partici- separated values (CSV) file, SQL database, or binary data file. pants. These approvals have been granted to the team mem- This parametric data file contains information collected from bers. In video-based data sets, IRB protocols are restrictive the vehicle sensors, such as velocity, acceleration, time of day, regarding who may access the data because of the inherent and radar data. The contracting institution must have the personal information (e.g., faces of drivers or location of res- capability to access and manipulate the various data formats idences). Access is often limited to key personnel associated provided. with the original data collection project, making it difficult For researchers to determine congestion factors, several for an outside entity to gain access to an institution's data. tools are required to view and examine a video-based data set. It is straightforward for the VTTI team to access and use The institution performing the analysis must have access to in-house data, as well as outside data that have IRB approval, and expertise with the tools necessary to perform manipula- but special issues need to be addressed when conducting tion of parametric data. Commercially available tools, such as research using video data because human beings are involved. MatLab and SAS, are commonly used to transform data, In case any institute performs a similar task using raw video identify events of interest, and perform statistical analyses of data and other raw kinematic vehicle data, the following pro- large data sets. Once events of interest are identified (e.g., cedures are necessary. crashes and near crashes), the data reduction process begins. Assuming the IRB protocol permits access to a contractor, Data reduction is the process of manually viewing video the contractor must be capable of complying with IRB require- and parametric data to validate events and derive additional ments. At a minimum, IRB approval from the entity main- measures. This process requires an institution that has facili- taining the data set is required; approval from the contractor's ties and tools for viewing synchronized video and parametric IRB may also be necessary. In some instances, the original IRB data, as well as a tool that links parametric data to video data agreement will not permit sharing of any personally identi- and provides an interface for entering additional data into the fiable data. In these cases, the contractor must perform the data set. Because no tool designed specifically for this purpose analyses without the personally identifiable data (e.g., with- is commercially available, the contracting institution will out video). Once IRB approval is granted, the institution per- need to have the capability to develop a custom solution. forming analysis on video-based data sets must possess the Some research groups (e.g., VTTI) have developed software capability to work efficiently with data sets from outside packages for data reduction that could easily be modified to sources. The contracting institution must have a secure com- meet the needs of this project. puting facility dedicated to the storage, retrieval, processing, Finally, a team of data reductionists will need to be trained and analysis of data. Permissions must be established so that on proper treatment of video data involving human subjects the videos and any associated data files for the project may be and the software used to reduce and analyze data. Reduc- accessible only to researchers and other personnel involved in tionists should be educated on the goals of the project, the the project. nature of the events, and the protocol for coding variables in 42