Trailer Angle Detection

The Seeker desires a system for automated detection of the angle between a trailer and its tow vehicle utilizing video from an on-board rearward facing camera. The system must be robust and operate accurately under a variety of weather and lighting conditions and must function on a mobile processor typically found in modern vehicles.

This is a Reduction-to-Practice Challenge that requires written documentation, output from the proposed system, and submission of source code and/or executable for validation upon request.

Maneuvering a trailer behind a car or truck can be a challenging task, particularly when backing around a corner or avoiding obstacles. Rear facing cameras can help a driver by providing a view of the trailer but offer incomplete or distorted information due to optical anomalies that occur based on camera placement and the viewing lens. Knowing the angle the trailer is making with the tow vehicle would be a great help but this is difficult for a driver to determine simply from the video feed. A system to automatically determine the trailer angle would be extremely useful and while such systems currently exist their performance in difficult weather or lighting conditions is inadequate for the Seeker’s needs. Therefore the Seeker requests systems that can accurately determine trailer angle in a variety of weather and lighting circumstances utilizing the video feed from a rear-facing camera. The system must be able to operate in real time on a microprocessor typically found in modern vehicles. Solvers will be provided a training set of videos with corresponding frame-by-frame ground truth trailer angle data for development of their system as well as a testing set of videos on which to demonstrate their system.

A submission to the Challenge should include the following:

1. A detailed description of the proposed Solution addressing specific Technical Requirements presented in the Detailed Description of the Challenge. This should also include a thorough description of the algorithm used in the Solution accompanied by a well-articulated rationale for the method employed.
2. Output from the proposed algorithm applied to the testing data set. Output must be in the form described in the Detailed Description of the Challenge.  Submissions will be ranked by the Seeker based on accuracy against the testing data set.
3. For the top ranked submissions, the Seeker may request source code and/or an executable with sufficient documentation to enable the Seeker to compile, execute the algorithm, and validate the method using additional validation data sets.

The Challenge award is contingent upon theoretical evaluation of the method/algorithm by the Seeker, and validation by the Seeker of the submitted reduction to practice Solution.

To receive an award, the Solver will have to transfer to the Seeker their exclusive Intellectual Property (IP) rights to the solution. 

Submissions to this Challenge must be received by 11:59 PM (US Eastern Time) on July 22, 2019

Late submissions will not be considered.