Computer Vision Speed Calculation Using Road Markings
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for determining driving metrics such as speed and acceleration rely on expensive and limited access to vehicles equipped with sensors like LIDAR and radar, and existing video datasets lack critical camera parameters, hindering research and real-time deployment in the autonomous vehicle industry.
Innovation Solution
A computing platform utilizing advanced computer vision methods to extract driving metrics from video footage without the need for LIDAR or radar, by detecting road markings and calculating speed and distance using camera parameters determined from ubiquitous pavement markings, enabling real-time and cost-effective metric generation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If video footage is used to determine driving metrics, then cost is reduced and accessibility is improved, but measurement precision deteriorates compared to sensor-based methods
Solution Approach 1:
The patent introduces road markings as an intermediary reference object that mediates between the camera and the vehicle. By detecting the temporal passage of known-length road markings through computer vision, the system creates an indirect measurement pathway that enables precise speed and distance calculations using only standard camera equipment, resolving the contradiction between low cost and high precision
Solution Approach 2:
The patent replaces mechanical sensor systems (LIDAR, radar) with an optical-computational system. Instead of using active sensing mechanisms that emit and detect electromagnetic waves, the system uses passive optical capture of road markings combined with computer vision algorithms to calculate driving metrics, achieving comparable precision at lower cost
2Measurement precision
If LIDAR and radar sensors are used, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent extracts the essential measurement function from complex sensor systems and isolates it to a simple temporal detection task. By focusing solely on detecting when road markings enter and exit the camera field of view, the system removes unnecessary sensor complexity while preserving the core speed measurement capability
Solution Approach 2:
The patent uses visual copying of road marking patterns that are already present in the environment. Instead of creating measurement signals through active sensors, the system captures and analyzes the visual pattern of existing road markings, using their known physical dimensions as a reference scale to derive speed and distance information
3Measurement precision
If advanced computer vision methods are implemented, then measurement capability is improved, but computational requirements and processing time increase
Solution Approach 1:
The patent extracts only the essential computational task from complex computer vision pipelines - specifically, detecting brightness transitions that indicate road marking boundaries. By focusing on this single, well-defined detection task rather than full scene understanding, the system achieves high measurement precision with minimal processing time
Solution Approach 2:
The patent exploits brightness (color) changes in the video feed as the primary detection signal. By monitoring when the brightness value exceeds a threshold to identify road marking boundaries, the system converts a potentially complex spatial recognition problem into a simple temporal brightness detection task, significantly reducing computational requirements
Data Source
AI summary
Aspects of the disclosure relate to dynamic driving metric output platforms that utilize improved computer vision methods to determine vehicle metrics from video footage. A computing platform may receive video footage from a vehicle camera. The computing platform may determine that a reference marker in the video footage has reached a beginning and an end of a road marker based on brightness transitions, and may insert time stamps into the video accordingly. Based on the time stamps, the computing platform may determine an amount of time during which the reference marker covered the road marking. Based on a known length of the road marking and the amount of time during which the reference marker covered the road marking, the computing platform may determine a vehicle speed. The computing platform may generate driving metric output information, based on the vehicle speed, which may be displayed by an accident analysis platform. Based on known dimensions of pavement markings the computing platform may obtain the parameters of the camera (e.g., focal length, camera height above ground plane and camera tilt angle) used to generate the video footage and use the camera parameters to determine the distance between the camera and any object in the video footage.