SAFE/T Tool for Analyzing Driver Video Data

Similar documents
2 Pelco Video Analytics

A Simple CCD Based Lane Tracking System

A Reliability Point and Kalman Filter-based Vehicle Tracking Technique

RIVA Megapixel cameras with integrated 3D Video Analytics - The next generation

Detection and Recognition of Mixed Traffic for Driver Assistance System

CCTV - Video Analytics for Traffic Management

Automated Optical Inspection is one of many manufacturing test methods common in the assembly of printed circuit boards. This list includes:

Automatic Maritime Surveillance with Visual Target Detection

3D Scanner using Line Laser. 1. Introduction. 2. Theory

Dinion XF the high-performance, smart surveillance camera. Dinion XF the flagship of the Dinion family

T-REDSPEED White paper

False alarm in outdoor environments

Colorado School of Mines Computer Vision Professor William Hoff

Big Data Requires Collaboration

Analytics. CathexisVision. CathexisVision Features. Video Management Solutions

A Prototype For Eye-Gaze Corrected

Solutions Lab. AXIS Barcode Reader Beta 0.3

VEHICLE LOCALISATION AND CLASSIFICATION IN URBAN CCTV STREAMS

AAA AUTOMOTIVE ENGINEERING

Real-time pedestrian detection in FIR and grayscale images

3D Vision An enabling Technology for Advanced Driver Assistance and Autonomous Offroad Driving

Scientific Issues in Motor Vehicle Cases

Video Analytics A New Standard

DOLBY SR-D DIGITAL. by JOHN F ALLEN

Example Chapter 08-Number 09: This example demonstrates some simple uses of common canned effects found in popular photo editors to stylize photos.

Neural Network based Vehicle Classification for Intelligent Traffic Control

Next level of Performance, p. 2 Next level of Reliability, p. 3 Next level of Efficiency, p. 4

Speed Performance Improvement of Vehicle Blob Tracking System

In: Proceedings of RECPAD th Portuguese Conference on Pattern Recognition June 27th- 28th, 2002 Aveiro, Portugal

From Product Management Telephone Nuremberg

White paper. H.264 video compression standard. New possibilities within video surveillance.

Answer: Fixed cameras would be recorded per F.7; PTZ cameras would be recorded per F.6.

Static Environment Recognition Using Omni-camera from a Moving Vehicle

An Iterative Image Registration Technique with an Application to Stereo Vision

The Advantages of Using a Fixed Stereo Vision sensor

FSI Machine Vision Training Programs

Cloud tracking with optical flow for short-term solar forecasting

Tracking performance evaluation on PETS 2015 Challenge datasets

APPLICATION NOTE. Basler racer Migration Guide. Mechanics. Flexible Mount Concept. Housing

MoveInspect HF HR. 3D measurement of dynamic processes MEASURE THE ADVANTAGE. MoveInspect TECHNOLOGY

COMPACT GUIDE. Camera-Integrated Motion Analysis

Automatic Traffic Estimation Using Image Processing

3D Vision An enabling Technology for Advanced Driver Assistance and Autonomous Offroad Driving

Video compression: Performance of available codec software

Video Encoding Best Practices

Vision-Based Blind Spot Detection Using Optical Flow

Object tracking in video scenes

WAKING up without the sound of an alarm clock is a

Practical Tour of Visual tracking. David Fleet and Allan Jepson January, 2006

MEZORY IP-CCTV QUICK PREVIEW

Intel Core i processor. 8 x 3.5-inch SATA 6Gb/s, SATA 3Gb/s hard drive. 1. The system is shipped without HDD.

Tracking and integrated navigation Konrad Schindler

Compositing a 3D character over video footage in Maya Jean-Marc Gauthier, Spring 2008

Video in Logger Pro. There are many ways to create and use video clips and still images in Logger Pro.

Scanners and How to Use Them

ESE498. Intruder Detection System

Quad Core Intel Xeon Processor E3. 12 x 3.5-inch SATA 6Gb/s, SATA 3Gb/s hard drive. 1. The system is shipped without HDD.

EB Automotive Driver Assistance EB Assist Solutions. Damian Barnett Director Automotive Software June 5, 2015

Bosch Video Management System Scheduled Recording Settings as of Bosch VMS 3.0. Technical Note

PROJECT MANAGEMENT PLAN TEMPLATE < PROJECT NAME >

HIGH QUALITY AUDIO RECORDING IN NOKIA LUMIA SMARTPHONES. 1 Nokia 2013 High quality audio recording in Nokia Lumia smartphones

Bosch Video Management System Scheduled Recording Settings as of Bosch VMS 3.0. Technical Note

Understanding Video Latency What is video latency and why do we care about it?

A PHOTOGRAMMETRIC APPRAOCH FOR AUTOMATIC TRAFFIC ASSESSMENT USING CONVENTIONAL CCTV CAMERA

Edge detection. (Trucco, Chapt 4 AND Jain et al., Chapt 5) -Edges are significant local changes of intensity in an image.

Automated Recording of Lectures using the Microsoft Kinect

Real time vehicle detection and tracking on multiple lanes

Limitations of Human Vision. What is computer vision? What is computer vision (cont d)?


White paper. Axis Video Analytics. Enhancing video surveillance efficiency

Service Pack Release Letter MIC Series 550 System Controller Table of Contents

TRACKING DRIVER EYE MOVEMENTS AT PERMISSIVE LEFT-TURNS

Q. Can an Exceptional3D monitor play back 2D content? A. Yes, Exceptional3D monitors can play back both 2D and specially formatted 3D content.

Real-time Traffic Congestion Detection Based on Video Analysis

RealAccess Analytics Sample of Reports Arnaud Le Devehat May 2016

AVM Software Upgrade + New Hardware Release. Saturday 13 TH June 2015

Vision based Vehicle Tracking using a high angle camera

3D U ser I t er aces and Augmented Reality

ROBUST VEHICLE TRACKING IN VIDEO IMAGES BEING TAKEN FROM A HELICOPTER

VEHICLE TRACKING AND SPEED ESTIMATION SYSTEM CHAN CHIA YIK. Report submitted in partial fulfillment of the requirements

Development of the Fabry-Perot Spectrometer Application. Kathryn Browne Code 587

Feasibility of an Augmented Reality-Based Approach to Driving Simulation

White paper. Axis Video Analytics. Enhancing video surveillance efficiency

GETTING STARTED WITH LABVIEW POINT-BY-POINT VIS

S b at 1.6 Gigabit/Second Bandwidth Encourages Industrial Imaging and Instrumentation Applications Growth

The Limits of Human Vision

ZEISS T-SCAN Automated / COMET Automated 3D Digitizing - Laserscanning / Fringe Projection Automated solutions for efficient 3D data capture

EyeSoft Quick Setup Guide For latest software update / manual, please see Please see Manual for detailed instructions.

Implementation of Man-Hours Measurement System for Construction Work Crews by Image Processing Technology

Development of an automated Red Light Violation Detection System (RLVDS) for Indian vehicles

A Computer Vision System on a Chip: a case study from the automotive domain

Distributed Vision Processing in Smart Camera Networks

High speed 3D capture for Configuration Management DOE SBIR Phase II Paul Banks

Tutorial for Tracker and Supporting Software By David Chandler

TRIMBLE ATS TOTAL STATION ADVANCED TRACKING SYSTEMS FOR HIGH-PRECISION CONSTRUCTION APPLICATIONS

Automatic Labeling of Lane Markings for Autonomous Vehicles

CCTV Training Analog and IP solutions

VEHICLE TRACKING USING ACOUSTIC AND VIDEO SENSORS

Project Time Management

Testing Metrics. Introduction

Transcription:

SAFE/T Tool for Analyzing Driver Video Data Part 2: Software Development Carol Martell, Rob Foss UNC Highway Safety Research Center Ken Gish, Loren Staplin TransAnalytics

Objective Overall: Develop analytic methods for the SHRP2 driving behavior and crash risk study such as: crash surrogates exposure-based collision risk driver vehicle roadway environment Project: Develop software to automatically output driver's head direction Software for Automatic Feature Extraction/Tracking (SAFE/T)

Why is SAFE/T needed? 1) Driver video data permits analysis of driving behavior in context. 2) Processing all driver video data using current methods is not feasible. 3) Without efficient video processing tools, SHRP2 may differ from its predecessors only in the volume of unused driver video data.

SAFE/T Main Features Early Processing: Low-pass filter Histogram equalization Edge detection Feature Detection: Forward = Eyes+Nose+Mouth Side = Ear/Hairline Tracking Motion prediction Reacquiring track

Early Processing: Histogram Equalization Original Equalized

Early Processing: Edge Detection Original Laplace Canny

Manual Video Data Extraction Digitization (completed) Video from AAA Driver Distraction study Format: 640x480 @ 30fps Codec: Divx Quantity: 2 hours of video for 4 drivers Manual Coding (in progress at UNC) Observer Pro Main coding variables: Head direction Features visible (1 trip per person)

Tracking Challenges Obstructions Eyewear Hand/arm Shadows Full face Partial face Glare Sun Headlights

Physical Obstructions

Frame Obstruction: Side Glances

Frame Obstruction: Forward Glance Lost track side glance!

System Performance Questions Can SAFE/T reliably detect not forward? What are the system requirements for recording, processing, and data output? Is the system cost-beneficial?

Assessing Tracking Performance Threshold for not forward : False positives: p( not forward forward ) False negatives: p( forward not forward ) Decision matrix: FP worse? Sensitivity analysis: Development: before/after software modification Future Evaluations: Tracker #1 vs. Tracker #2. Dependence on resolution and frame rate

Is tracking accurate enough? Compared to... Current status? Operational requirements? Ideal world? Can tracking accuracy and reliability be improved for... Pre-recorded video? To-be-recorded video?

How can tracking be improved? Optics NIR Filters NIR Sources Electronics Camera dynamic range Electronic synchronization Depth processing using stereo camera setup Software

High Dynamic Range Camera

Background Subtraction & Face Detection Image 1: Ambient + NIR t Ambien Camera NIR NIR Filter Image 2: Ambient Only t Ambien Camera NIR Filter

Background Subtraction & Face Detection Ambient Only Ambient + NIR Minus NIR Only Equals AdaBoost Face Detection

Vector Keying Original Scene After Setting Vector Key Background defined mathematically Sharp, dynamic edges around foreground object

Feature Tracking OpenCV Library Background subtraction Feature tracking Motion prediction Other Video Processing Libraries

How can tracking be optimized? Shadow Sun Glare Shadow + Obstruction Shadows: reduce or eliminate with optics & electronics Glare: reduce with optics & electronics Obstructions: improve with independent feature tracking Pre-recording vs. post-recording

What types of safety analyses does SAFE/T permit? How often do drivers direct their head away from the forward roadway? What are the durations of these glances? Combinations of frequency & duration Dependence on roadway & environment

Summary of Potential Benefits System: Quality & quantity of driver behavior data Efficiency of video processing Safety: True baseline (in many contexts) Exposure-based crash risk Prioritize countermeasure efforts

Future Work Phase I Software Development: Develop SAFE/T Prototype Use AAA data to evaluate output Optimization: modification+evaluation cycles Phase II Field Experiment: Electronic and optical configuration Compare true state with tracking output Multiple resolutions/frame rates ROC analysis