CN-550000-BE252-00030000.pdf

EXHIBIT “A”

Project Title:

Phase IV: Real Time Monitoring and Prediction of Reduced Visibility Events on Florida’s

Highways

Principal Investigator: Christina Drake, PhD

Florida Polytechnic University

4700 Research Way, IST 2111

Lakeland, FL 33805 cdrake@floridapoly.edu

1-863-874-8554

DSR Contact: Jeanne Viviani

4700 Research Way, IST 2036

Lakeland, FL 33805 jviviani@floridapoly.edu

1-863-874-8534

Project Manager: Fred H. Heery, Sr., PE

Florida Department of Transportation

605 Suwannee Street, MS 90

Tallahassee, FL 32399-0450

Fred.Heery@dot.state.fl.us

1-850-410-5606

Scope of Services: Phase IV: Real Time Monitoring and Prediction of Reduced Visibility

Events on Florida’s Highways

Phase IV Executive Summary

The purpose of the Phase IV study “Real Time Monitoring and Prediction of Reduced

Visibility Events on Florida’s Highways” is to continue development and deployment of the multi-level fog monitoring stations, to utilize multi-spectral satellite imagery and multi-level sensor arrays for conducting further data analysis, to add test sites in Eastern Central, Western

Central and Southern Florida and for further refinement of the weather model to provide advanced warning of other weather road conditions which can cause traffic congestion.

On average, there are over 5,870,000 vehicle crashes each year. Twenty-three percent (23%) of these crashes — nearly 1,312,000 — are weather-related according to the National Highway

Traffic Safety Administration (NHTSA). In Florida, on January 29, 2012, along a stretch of I75 just south of Gainesville, 11 people perished and 20 were injured when smoke and fog combined, reducing visibility to nearly zero. The crash occurred four years after a similar tragedy on Interstate 4 in Polk County where a 70-vehicle pileup killed 4 people and injured 30.

The Real Time Monitoring and Prediction of Reduced Visibility Events on Florida’s

Highways’ project has validated that an array of low-cost meteorological sensors combined with site-adaptable software algorithms, weather modeling and GIS data, can detect, and predict the onset of fog, meeting or exceeding existing performance of traditional and much more expensive technologies. The addition of weather forecast, inversion, GIS and atmospheric parameters has put primary focus on future fog and visibility events (predictive) versus generalized information from traditional road weather systems or traffic events (reactive).

Additional test sites, further study and alternative validation methodologies using standard

Florida Department of Transportation (“Department”) cameras are being implemented to expand the coverage of fog monitoring test sites and refine both the fog and weather model. Improved detection and prediction of reduced visibility on Florida roadways can reduce crashes, improve traffic management, save money and most importantly save the lives of the more than 18 million residents who call Florida home.

Phase IV Project Objective(s)

The main objectives of this scope are as follows:

• To continue development and deployment of the multi-level fog monitoring stations;

• To utilize multi-spectral satellite imagery and multi-level sensor arrays for conducting further data analysis for weather events;

• To add test sites in Eastern Central, Western Central and Southern Florida and for further refinement of the weather model to provide advanced warning of other weather road conditions;

• To provide alternative validation methodologies using standard cameras to improve detection and prediction capabilities for the State of Florida.

Phase IV Task Summary

The following tasks under Florida Polytechnic University (“University”) are based on improving the findings under Phase III by providing a positive verification system to the weather model developed by subcontractor PraxSoft, Inc. This will be achieved using visible range cameras combined with image processing in order to characterize the changes in local “air conditions” indicative of imminent fog formation. This will be done in conjunction with PraxSoft’s efforts under subcontractor tasks as a way to improve the accuracy and prediction scope for fog formation.

Tasks under Florida Polytechnic University

Task 1: Program Management (December 2016 – September 2018) University will manage and coordinate tasks and deliverable submissions agreed upon in this scope.

Subtasks:

1.1 Quarterly Report #1 Cost $7,157.00

1.2 Quarterly Report #2 Cost $7,157.00

1.3 Quarterly Report #3 Cost $7,157.00

1.4 Quarterly Report #4 Cost $7,157.00

1.5 Quarterly Report #5 Cost $7,157.00

1.6 Quarterly Report #6 Cost $7,157.00

1.7 Draft Final and Final Report Cost $7,157.00

Deliverables: Quarterly project updates to status project and tasks. Draft final and final report of

University and PraxSoft’s tasks and final results and recommendations are included under this task.

Ninety (90) days prior to the end date of the task work order, the university will submit a draft final report to Fred Heery, Department Project Manager. The draft final and final reports must follow the Guidelines for University Presentation and Publication of Research available at http://www.dot.state.fl.us/research-center/Project_Mgt_Resources.shtm. The report must be well-written and edited for technical accuracy, grammar, clarity, organization, and format.

Deliverable: Upon Department approval of the draft final report, the University will submit the

Final Report on two (2) CDs. Both CDs shall contain the report in PDF and Microsoft Word formats. CDs should be labeled in a professional manner and include contract number, task work order number, project title, and date.

The final report is due by the end date of the task work order and should be mailed to the Florida

Department of Transportation, Traffic Engineering and Operations Office, 605 Suwannee Street, MS 90, Tallahassee, FL 32399-0450.

Total Task 1 Cost: $50,099.00 http://www.dot.state.fl.us/research-center/Project_Mgt_Resources.shtm

Task 2: Camera evaluation system for fog prediction (December 2016 – September 2018)

2.1 (Dec 2016 – September 2018) University will evaluate the earliest time period for positive recognition of fog formation prior to the onset of large visibility reduction using a Bosch Autodome 7000 HDs or a Bosch Autodome 800 HDs. These are similar to the Department cameras currently in use at one of the sites near Paynes

Prairie. At least one other commercially available CCD camera will also be used in parallel to the Bosch camera to unbias the results from any native software associated with the Bosch camera. This task will be achieved using camera image data and analysis based on changes in air characteristics. Two separate data analyses (target color shift and target haloing) will be performed to improve the confidence interval on the air characteristics determination.

Deliverables: Written report detailing results of camera image processing and analysis with parameters for identification of fog conditions under isolated conditions.

Total Subtask 2.1 Cost: $229,072.17

2.2 (January 2016 – September 2018) University will evaluate environmental and aging factors that would shift the performance of a camera verification system over time.

This information would be used to engineer against the likelihood of false positives during field use of the system.

Deliverable: Written report detailing results of testing and anticipated impact to system performance.

Total Subtask 2.2 Cost: $69,626.80

2.3 (May 2017 - September 2018) University will evaluate fog prediction performance at the Paynes Prairie site (in conjunction with PraxSoft sensor suite) using site infrastructure (with some modification) and the parameters determined from 2.1.

Deliverable: Written report detailing results of field tests and ability of cameras to increase prediction time for weather events.

Total Subtask 2.3 Cost: $49,435.03

Total Task 2 Cost: $348,134.00

Task 3: Statewide infrastructure viability (February 2017 - September 2018)

3.1 (February 2017 – September 2018) University will evaluate the viability of implementing prediction techniques used on the 2 cameras in this scope to other camera systems used within the state.

3.2 (May 2017 – September 2018) University will determine best use of existing infrastructure for extended image analysis capabilities within the multi-level fog monitoring stations.

Deliverables: Written report detailing results of capabilities of image analysis coupled to the weather model using available traffic camera infrastructure within the State of Florida.

Total Task 3 Cost: $57,106.00

Task 4: Increase prediction time in the weather model to provide advanced warning for the onset of fog and other possible weather conditions (December 2016 – September 2018)

4.1 (December 2016 – September 2018) University will determine most effective use of image analysis relative to earliest predictors of fog and to improve prediction confidence. A preliminary analysis of other weather conditions and use of the camera system for evaluation will be included. Final Fog Index recommendations are included as a portion of this task.

Deliverable: Written report detailing ability of enhanced prediction capabilities when image analysis is coupled to the prediction algorithm.

Total Task 4 Cost: $44,751.00

Task 5: Integration of image analysis (December 2016 – December 2017)

5.1 Implement image analysis results into Web-based application

Determine the most effective use of image analysis with existing cameras and implement results into the Web-based application to verify presence of fog

5.2 Determine if image analysis with existing camera can increase prediction time in conjunction with the weather model

Determine if image analysis with existing cameras can increase prediction time in conjunction with the weather model to provide further advanced warning for the onset of fog (includes data analysis of events at 2 sites with camera coverage during the

2016-2017 fog season)

5.3 Determine if image analysis with existing cameras can provide verification or advanced warning for other possible weather conditions

Determine if image analysis with existing cameras can provide verification or advanced warning for other possible weather conditions (includes data analysis of events at 2 sites with camera coverage during the 2016-2017 fog season)

Deliverables: Written reports for subtasks 5.1 and 5.2. A comprehensive written report of camera and image processing integration in fog verification and prediction that includes all subtasks.

Total Task 5 Cost: $167,610.00

Task 6: Affordably expand coverage of areas susceptible to fog formation (December 2016 –

August 2016)

6.1 Select at least 2 additional “at-risk” sites in areas with differing land characteristics than previously-installed sites

6.2 Conduct radio path analysis of selected sites

6.3 FMS hardware and radio communications selection, production and in-house test

6.4 Camera and visibility sensor hardware selection, production and in-house test

6.5 Installation/deployment of five additional site locations

6.6 Field test of FMS, camera and visibility

Deliverables: Written reports for subtasks 6.1, 6.2, 6.3, 6.4 and 6.5. A comprehensive written report of new site locations that includes all subtasks.

Total Task 6 Cost: $ 340,226.00

Task 7: Adjust the model and prediction algorithm for use of results from image analysis

(December 2016 – December 2017)

7.1 Statistical analysis of 2016/17 season image processing test site data

7.2 Comparison of image processing statistical analysis to other means of validation (i.e.

visibility sensors, manual camera validation)

7.3 Implementation of Tasks 1.2 and 1.3 results with the weather model to gauge necessary effort for model refinement based on image analysis

7.4 Adjust and refine model based on image analysis for fog

7.5 Adjust and refine model based on image analysis for other weather conditions

7.6 Create and write formal plan for automation of image analysis

7.7 Collaborate with Department regarding final Fog Index recommendations with image analysis

Deliverables: Written reports for subtasks 7.1, 7.2, 7.3, 7.4, 7.5, and 7.6. A comprehensive written report of adjusted fog prediction algorithm that includes all subtasks.

Total Task 7 Cost: $153,547.00

Task 8: Fine-tune the model and prediction algorithm for other road weather conditions which reduce visibility (December 2016 – October 2017)

8.1 Statistical analysis of 2016/17 season reduced visibility events by storm type and storm attributes to improve detection and prediction

8.2 Correlate weather prediction for precipitation, heavy precipitation, mist and other reduced visibility events with localized measurements and conditions

8.3 Refine model based on forecast storm attributes versus measured conditions to provide improved, advanced warning of other reduced visibility weather conditions in a predictive manner

8.4 Refine model based on projected storm movement and trajectory

8.5 Collaborate with Department and University regarding final Fog Index recommendations for other road weather conditions

Deliverables: Written reports for subtasks 8.1, 8.2, 8.3, and 8.4. A comprehensive written report of adjusted reduced visibility detection and prediction algorithm for other road weather conditions that includes all subtasks.

Total Task 8 Cost: $ 110,740.00

Task 9: Enhance Web-based visualization of Fog Index and other weather road conditions and develop initial monitoring and alerting service (January 2017 – August 2017

9.1 Identify and evaluate different methods to display other road weather conditions

9.2 Integrate enhanced visualization technique into online portal

9.3 Provide preliminary set of enhancements in a BETA form for feedback and further refinement

9.4 Finalize and implement enhanced visualization methodology

9.5 Develop initial monitoring and alerting service to deliver fog index and other reduced visibility road weather condition warnings to select state agency personnel

9.6 Provide preliminary monitoring and alerting service in a BETA form for feedback and further refinement

Deliverables: Written reports for subtasks 9.1, 9.2, 9.3, 9.4, and 9.5. A comprehensive written report of online visualization portal and alerting service that includes all subtasks.

Total Task 9 Cost: $ 136,215.00

Task 10: Investigate the range of the validity for the combination of technologies being implemented in tasks 5 and 6 (January 2017 – June 2017)

10.1 Identify and evaluate methods to validate fog by geographic area

10.2 Reconfigure the weather model to look at more levels

10.3 Investigate coverage area of image processing, sensors and model area configuration

Deliverables: Written reports for subtasks 10.1 and 10.2. A comprehensive written report of most applicable coverage range that includes all subtasks.

Total Task 10 Cost: $91,567.00

Use of Graduate Student(s) and other Research Assistants

University will use 4 undergraduate students as research assistants to perform the work outlined above in University’s Tasks 2.0-4.0. The students will work on test set up, data collection, analysis and engineering application of the camera system and sensor suite.

Equipment

Rule 691.62.007, F.A.C states “For statewide financial reporting purposes, all tangible personal property with a value or cost of $1,000 or more and having a projected useful life of one year or more must be capitalized. Any hardback book with a value or cost of $25 or more and having a useful life of one year or more that is circulated to students or the general public, and any hardback book with a value or cost of $250 or more that is not circulated must be capitalized.”

In addition to the $1,000 threshold, the Department also has a list of Exception Class Property available at http://www.dot.state.fl.us/researchcenter/Project_Mgt_Resources.shtm

If equipment is to be purchased on a project the scope must include justification of specific requirements for the project and why the equipment should be purchased instead of leasing

(leasing of equipment is preferred). A description of the equipment to be purchased must be included with a copy of the quotes obtained.

Equipment will be purchased to support the testing and development of the camera based sensor system for fog prediction and analysis, as well as the multi-level weather stations. This includes both field tests and laboratory tests to define parameters and operating conditions. See

Equipment List and Cost in Exhibit C.

Expenses

Supplies (cameras, light sources, processors, parts for electronic housing, software and sensor weather proofing materials) will be purchased to support the testing and development of the camera based sensor system for fog prediction and analysis. This includes both field tests and laboratory tests to define parameters and operating conditions. See Supply List and Cost Table in Exhibit C.

Project Kickoff Teleconference

The principal investigator will schedule a kickoff teleconference that shall be held within the first

30 days of execution. The project manager, principal investigator, and research performance coordinator, and subcontractor lead shall attend. Other parties may be invited if appropriate. The purpose of the meeting is to review the tasks, deliverables, and deployment plan.

Project Closeout

The principal investigator will schedule a closeout teleconference that shall be held during the final 30 days of the task work order. The principal investigator, project manager, subcontract lead and research performance coordinator shall attend. Other parties may be invited, if appropriate. The purpose of the meeting is to review project performance, the deployment plan, and next steps.

Performance and Financial Consequences

Work not identified and included in this scope of service is not to be performed and will not be subject to compensation by the Department.

Payment shall be made only after receipt and approval of goods and services. Deliverable(s) must be received and accepted in writing prior to payment. If the Department determines that the performance of the University is unsatisfactory, the Department shall notify the University of the deficiency to be corrected, which correction shall be made within a time-frame to be specified by the Department. The University shall, within five days after notice from the

Department, provide the Department with a corrective action plan describing how the University will address all issues of contract non-performance, unacceptable performance, failure to meet the minimum performance levels, deliverable deficiencies, or contract non-compliance. If the corrective plan is unacceptable to the Department, the University shall be assessed a non-performance retainage equivalent to 10% of the total invoice amount. The retainage shall be applied to the invoice for the then-current billing period. The retainage shall be withheld until the University resolves the deficiency. If the deficiency is subsequently resolved, the University may bill the Department for the retained amount during the next billing period. If the University is unable to resolve the deficiency, the funds retained may be forfeited at the end of the task work order period.

Publication Provision

If at any time during a TWO the University desires to publish in any form any material developed under the TWO, the University must submit to the TWO Manager a written abstract and notification of intent to publish the material and receive the TWO Manager’s concurrence to publish. Such approval to publish shall not be unreasonably withheld. If the TWO Manager does not provide a written response within 30 days after receipt, the University may publish.

The publication must include the following language:

“The opinions, findings and conclusions expressed in this publication are those of the author(s) and not necessarily those of the Florida Department of Transportation or the

U.S. Department of Transportation.”

Phase IV List of Deliverables

University

Upon completion of specific milestones and tasks, the following deliverables shall be submitted to the project manager:

Task 1: Quarterly project updates to status project and tasks. Draft final and final report of

University tasks and final results and recommendations are included under this task.

Task 2: (2.1) Written report detailing results of camera image processing and analysis with parameters for identification of fog conditions under isolated conditions.

(2.2) Written report detailing results of testing and anticipated impact to overall system performance.

(2.3) Written report detailing results of field tests and use of cameras.

Task 3: Written report detailing results of capabilities of image analysis coupled to the weather model using available traffic camera infrastructure within the state of Florida.

Task 4: Written report detailing ability of enhanced prediction capabilities when image analysis is coupled to the prediction algorithm

Task 5: Written reports for subtasks 5.1 and 5.2. A comprehensive written report of camera and image processing integration in fog verification and prediction that includes all subtasks.

Task 6: Written reports for subtasks 6.1, 6.2, 6.3, 6.4 and 6.5. A comprehensive written report of new site locations that includes all subtasks.

Task 7: Written reports for subtasks 7.1, 7.2, 7.3, 7.4, 7.5, and 7.6. A comprehensive written report of adjusted fog prediction algorithm that includes all subtasks.

Task 8: Written reports for subtasks 8.1, 8.2, 8.3, and 8.4. A comprehensive written report of adjusted reduced visibility detection and prediction algorithm for other road weather conditions that includes all subtasks.

Task 9: Written reports for subtasks 9.1, 9.2, 9.3, 9.4, and 9.5. A comprehensive written report of online visualization portal and alerting service that includes all subtasks.

Task 10: Written reports for subtasks 10.1 and 10.2. A comprehensive written report of most applicable coverage range that includes all subtasks.

Project Milestones

Table 3: Task Schedule

Task Description Start Date End Date

1 Program Management

Deliverables: Quarterly status reports (3/15/17; 6/15/17; 7/15/17;

9/15/17; 12/15/17; 3/15/18); Draft final report 90 days prior to end of TWO (6/30/18); Final Report (9/30/18)

12/15/2016 9/30/2018

2 Camera evaluation system for fog prediction

Deliverables: 2.1 Written report (9/30/18); 2.2 Written report

(9/30/2018); 2.3 Written report – these may be included as a sections in Final Report (9/30/18)

12/15/2016 9/30/2018

3 Statewide infrastructure viability

Deliverable: Written report – may be included as a section in Final

Report (9/30/18)

2/15/2017 9/30/2018

4 Increase prediction time in the weather model to provide advanced warning for the onset of fog and other possible weather conditions

Deliverable: Written report – may be included as a section of Final

Report (9/30/18)

12/15/2016 9/30/2018

5 Integration of image analysis

Deliverable: Written report (6/30/17)

12/15/2016 12/31/2017

6 Affordably expand coverage of areas susceptible to fog formation

Deliverable: Written report (7/31/17)

12/15/2016 08/31/2017

7 Adjust the model and prediction algorithm for use of results from image analysis

Deliverable: Written report (10/6/17)

12/15/2016 12/1/2017

8 Fine-tune the model and prediction algorithm for other road weather conditions which reduce visibility

Deliverable: Written report (5/31/17)

12/15/2016 10/31/2017

9 Enhance Web-based visualization of Fog Index and other weather road conditions and develop initial monitoring and alerting service

Deliverable: Written report (6/30/2017)

1/1/2017 08/31/2017

10 Investigate the range of the validity for the combination of technologies being implemented in tasks 1 and 2

Deliverable: Written report (6/30/2017)

1/1/2017 06/30/2017

Table 4: Deliverable Schedule

Task Deliverable Due Date

1.1 Quarterly Report 3/15/17

1.2 Quarterly Report 6/15/17

1.3 Quarterly Report 9/15/17

1.4 Quarterly Report 12/15/17

1.5 Quarterly Report 3/15/18

1.6 DRAFT Final Report 6/30/18

1.7 Final Report 9/30/18

2.1 Written Report (2.1) 9/30/18

2.2 Written Report (2.2) 9/30/18

2.3 Written Report (2.3) 9/30/18

3 Written Report 9/30/18

4 Written Report 9/30/18

5 Written Report 12/31/2017

6 Written Report 08/31/2017

7 Written Report 12/1/2017

8 Written Report 10/31/2017

9 Written Report 08/31/2017

10 Written Report 06/30/2017