U.S. Department of Transportation
Federal Highway Administration
1200 New Jersey Avenue, SE
Washington, DC 20590
202-366-4000
Federal Highway Administration Research and Technology
Coordinating, Developing, and Delivering Highway Transportation Innovations
| Project Information | ||
| Project ID: | FHWA-PROJ-14-0012 | |
| Project Name: | DCode: A Comprehensive Automatic Coding System for Driver Behavior Analysis | |
| Project Status: | Active | |
| Start Date: | March 13, 2014 | |
| End Date: | March 12, 2016 | |
| Contact Information | ||
| Last Name: | Cobb | |
| First Name: | Lincoln | |
| Telephone: | 202-493-3313 | |
| E-mail: | lincoln.cobb@dot.gov | |
| Office: | Office of Safety Research and Development | |
| Program: | Exploratory Advanced Research | |
| Project detail | ||
| Project Description: | The goal of this project is to develop a comprehensive automatic coding system: DCode. The code will pay attention to the context of various driving situations by extracting features related to driver behavior as well as to features related to the environment both inside and outside of the vehicle. The overall algorithm will include a multitiered feature-extraction pipeline with a behavior-agnostic core layer and more behavior-specific upper layers that share features with the core layer. The core layer will track all directly observable features, such as head pose, facial features, upper body, and hand positions, as well as pedestrian and vehicle locations. The upper layers will use these features to identify various actions and gestures, as well as monitor the drivers state based on various machine-learning techniques. This architecture will make it straightforward to add new behavior detectors. The algorithms will be scalable, so they can be run on distributed processor architectures. | |
| Goals: |
(1) Extract features relevant to driving safety research easily and accurately in order to accelerate the use of the second Strategic Highway Research Program (SHRP2) Naturalistic Driving Study (NDS) data.
(2) Focus on the features that are "low-hanging fruit" to allow for the development of technologies quickly enough to be used as soon as the SHRP2 data are collected.
(3) Demonstrate accurate technologies for extracting specific behaviors, but promote approaches that can be generalized and applied to other behaviors.
(4) Demonstrate the effectiveness of the proposed technology and the degree of automation achieved using the SHRP2 24-car sample dataset.
(5) Build cooperation across the Government, academia, and the private sector to advance effective and cost-efficient methods and tools.
|
|
| More Information URL(s): | ||
| Product Type: | Research report Software | |
| Test Methodology: | An initial video preprocessing phase, followed by a three-tiered feature-extraction framework. | |
| Expected Benefits: | The proposed system will have the potential to significantly improve the speed and accuracy by which safety-related features can be coded from the massive amount of data collected by the second Strategic Highway Research Program (SHRP2) Naturalistic Driving Study (NDS), thereby expediting its use by safety researchers. | |
| Deliverables: | Name: DCode Product Type(s): Research report, Software Description: DCode is a comprehensive automatic coding system. The code will pay attention to the context of various driving situations by extracting features related to driver behavior as well as to features related to the environment both inside and outside of the vehicle | |
| Related URL(s): | http://wwwcf.fhwa.dot.gov/exit.cfm?link=http://onlinepubs.trb.org/onlinepubs/shrp2/2014SafetySymposium/5-NDS-Cobb.pdf |
|
| FHWA Topics: | Research/Technologies--Turner-Fairbank Highway Research Center (TFHRC) | |
| TRT Terms: | Behavior Coding systems Algorithms Research Safety Driving |
|
| FHWA Disciplines: | Safety |
|
| Subject Areas: | Data and Information Technology Research Transportation (General) Safety and Human Factors |
|
 |
||
