System, device, and method for vehicle post-crash support
Inventors
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12148229-B2
Publication Date
2024-11-19
Expiration Date
Abstract
System and methods are provided for providing first responders after a vehicle accident with useful information regarding the medical status and injuries of the vehicle's occupants. The system includes an in-cabin sensor comprising at least one or more of an image sensor, depth sensor and micro-vibration sensor for capturing sensory data of the vehicle cabin including pre-crash data, during-crash and post-crash. The system also includes at least one processor configured to analyze the sensory data.
Core Innovation
The invention relates to a vehicle cabin post-crash support system that provides medical information of at least one occupant in the cabin. The system includes an illuminator that projects light in a predefined light pattern on the vehicle cabin, and an image sensor that captures sensory data comprising a sequence of 2D images and 3D images, with at least one 2D image comprising reflections of the predefined light pattern from the occupants.
The system detects an imminent crash and analyzes sensory data captured prior to detection of imminent crash, during the crash, and following the crash to provide the medical information and assess medical status following the crash. A second aspect estimates the medical state of one or more occupants in a vehicle cabin following an accident by projecting the predefined light pattern and capturing sensory data prior to, during and following the crash.
An impact detection signal is received, sensory data captured prior to receiving the impact detection signal is stored, and computer vision or machine learning is applied to yield pre-crash assessment data identifying an occupant’s state prior to the crash. The system further receives sensory data captured during the crash and analyzes the sequences of 2D images and 3D images to yield during-crash assessment data comprising body trajectories of the one or more occupants.
Medical information following the crash is then provided based on the during-crash assessment data and the pre-crash assessment data. Speckle-pattern temporal changes are analyzed to support micro-vibration-related signals, and computer vision or machine learning is used to support occupant pose/body motion and visible wounds detection, with fusion of pre-crash, during-crash, and post-crash assessments.
Claims Coverage
The document provides two independent claims covering 2 inventive features. The claims center on projecting a predefined light pattern into a vehicle cabin, capturing sequences of 2D and 3D images with reflections of the predefined light pattern from occupants, and using crash-timed analysis to provide medical information and assess occupant medical status or estimate occupant medical state.
Imminent-crash detection using projected predefined light pattern and 2D/3D sensory image sequences for post-crash medical status assessment
A system for providing medical information of at least one occupant in a vehicle cabin with a sensing module that projects light in a predefined light pattern on the vehicle cabin and captures sensory data comprising a sequence of 2D images and 3D images where at least one 2D image includes reflections of the predefined light pattern from occupants, and a control module that receives the sensory data, detects an imminent crash with the sensory data captured prior to detection, during the crash, and following the crash, analyzes the sensory data using one or more analysis methods to provide medical information, and assesses a medical status following the crash.
Pre-crash state identification and during-crash body-trajectory estimation from projected predefined light pattern and captured 2D/3D sequences for post-crash medical information
A system for estimating the medical state of one or more occupants in a vehicle cabin following an accident, comprising an illuminator projecting light in a predefined light pattern on the vehicle cabin and at least one image sensor capturing sensory data prior to, during and following a crash comprising a sequence of 2D images and 3D images where at least one 2D image includes reflections of the predefined light pattern from the occupants; and a control module configured to receive captured sensory data, receive an impact detection signal, store received sensory data captured prior to receiving the impact detection signal, analyze the received sensory data using computer vision or machine learning to yield pre-crash assessment data identifying the occupant state prior to the crash, analyze sensory data captured during the crash to yield during-crash assessment data comprising body trajectories, and provide medical information following the crash based on the during-crash assessment data and pre-crash assessment data.
Across the independent claims, the coverage centers on projecting a predefined light pattern into a vehicle cabin, capturing sequences of 2D and 3D images with reflections of the predefined light pattern from occupants, and using crash-timed analysis to generate medical information and assess occupant medical status or estimate occupant medical state.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Not explicitly described in patent.
Interested in licensing this patent?