Pedestrian Collision Mitigation Using Speed-Based Image Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current pedestrian detection and collision mitigation systems (PDCMS) lack effective methods to accurately detect pedestrians using image processing and activate mitigation functions based on vehicle speed and pedestrian motion information, leading to potential collisions.
Innovation Solution
An apparatus and method that utilize an image collecting unit to detect pedestrians and an electronic control unit to determine the risk of collision by combining vehicle and pedestrian state information, activating a PDCMS function with warnings and automatic braking to mitigate collisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If pedestrian detection and collision mitigation systems are activated, then pedestrian safety is improved, but false detections may cause unnecessary braking and traffic disruption
Solution Approach 1:
The patent introduces an electronic control unit as an intermediary that processes image data from the image collecting unit and integrates it with vehicle speed and pedestrian motion information. This intermediary layer filters and validates detection data before triggering PDCMS activation, reducing false detections while maintaining system reliability.
Solution Approach 2:
The system changes detection parameters dynamically based on vehicle speed and pedestrian motion characteristics. By adjusting detection sensitivity and activation thresholds according to real-time parameters, the system improves detection accuracy without requiring overly complex fixed-threshold systems.
2Measurement precision
If image processing is used for pedestrian detection, then detection accuracy is improved, but processing time and computational load increase
Solution Approach 1:
The system performs preliminary actions by continuously collecting images and pre-processing data even before a potential collision scenario is fully developed. The image collecting unit operates in advance, building a buffer of processed image data that can be quickly evaluated when a pedestrian detection event occurs, reducing real-time processing delays.
Solution Approach 2:
The system applies partial image processing by focusing computational resources on key regions of interest in the image data, particularly areas where pedestrians are detected or where vehicle-pedestrian collision risk is highest. This selective processing approach maintains detection precision while reducing overall computational load and processing time.
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
An apparatus for activating a pedestrian (600) detection and collision mitigation system (PDCMS) of a vehicle (700) includes: an engine management system (EMS) acquiring speed information of the vehicle (700) in real-time; an image collecting unit (300) recognizing a pedestrian (600) positioned within a driving lane of the vehicle (700) and detecting information of a relative speed or a distance between the pedestrian (600) and the vehicle (700), when a speed of the vehicle (700) is greater than or equal to a set speed; and an electronic control unit (ECU) activating a PDCMS function based on a mapping table using the speed information of the vehicle (700) and information of a motion or a distance of the pedestrian (600) with respect to the vehicle (700), and controlling a warning unit (500) to inform a driver of a collision of the pedestrian (600) with the vehicle (700). The PDCMS function includes activating an operation of an active hood, activating an operation of the warning unit (500), and activating an operation of a brake regardless of whether the driver operates the brake. The activation of the operation of the warning unit (500) and the activation of the operation of the brake comprise, in order:activating the operation of the warning unit (500), activating a partial braking of the vehicle (700), and activating a full braking of the vehicle (700).