Automated responses to vehicle trunk entrapment

Patent metadata

Field	Value
Publication number	US-11590980-B2
Application number	US-202016882251-A
Country	US
Kind code	B2
Filing date	May 22, 2020
Priority date	May 22, 2020
Publication date	Feb 28, 2023
Grant date	Feb 28, 2023

Abstract

Described herein are systems, methods, and computer readable media for capturing sensor data relating to an enclosed compartment of a vehicle (e.g., a cargo area of the vehicle) via one or more vehicle sensors; analyzing the sensor data to determine whether it is indicative of a living being present in the enclosed compartment; performing an object detection analysis on at least a portion of the sensor data to determine a type of living being detected; and initiating one or more automated vehicle response measures based on the type of living being.

First claim

What is claimed is:

1. A computer-implemented method for detecting presence of a living being in an enclosed compartment of a vehicle, the method comprising:
capturing, via one or more sensors associated with the vehicle, sensor data relating to one or more sensed characteristics of the enclosed compartment of the vehicle, wherein the capturing comprises:
capturing, using a camera, one or more images within the enclosed compartment;
determining whether respective resolutions of the one or more images fail to satisfy a threshold resolution;
in response to determining that the respective resolutions of the one or more images fail to satisfy the threshold resolution, capturing any of:
heat signature data from one or more infrared (IR) sensors,
vibrational data from one or more vibration or inertial sensors, and
gas concentration data from one or more gas sensors;
determining that the sensor data is indicative of the presence of the living being in the enclosed compartment of the vehicle;
performing an object detection analysis on the one or more images included in the sensor data;
determining a type of the living being based at least in part on the object detection analysis;
determining a range of acceptable values of a health parameter related to the type of the living being;
capturing, via the one or more sensors, second sensor data including measured values of the health parameter;
determining whether the measured values of the health parameter are within the range of acceptable values;
performing additional monitoring of the enclosed compartment of the vehicle to capture additional sensor data including additional measured values of the health parameter further based at least in part on whether the measured values of the health parameter are within the range of acceptable values; and
initiating one or more automated vehicle response measures based at least in part on the type of the living being.

2. The computer-implemented method of claim 1 , wherein determining the type of the living being comprises determining that the living being is a live animal based at least in part on the object detection analysis.

3. The computer-implemented method of claim 2 , further comprising applying a trained machine learning model to the image data to determine a type of the live animal.

4. The computer-implemented method of claim 3 , wherein the sensor data is first sensor data,
wherein initiating the one or more automated vehicle response measures comprises initiating the one or more automated vehicle response measures further based at least in part on whether the measured values of the health parameter are within the range of acceptable values.

5. The computer-implemented method of claim 4 , wherein determining whether the measured values of the health parameter are within the range of acceptable values comprises determining that each of a threshold number of the measured values of the health parameter is within the range of acceptable values for at least a threshold period of time.

6. The computer-implemented method of claim 4 , wherein determining whether the measured values of the health parameter are within the range of acceptable values comprises determining that at least a threshold number of the measured values of the health parameter are outside of the range of acceptable values for at least a threshold period of time.

7. The computer-implemented method of claim 6 , wherein initiating the one or more automated vehicle response measures comprises at least one of: i) sending an emergency alert message to one or more emergency service providers, ii) presenting a visual or audible alert to an occupant of the vehicle, or iii) automatically releasing a locking mechanism of the enclosed compartment when the vehicle is not moving.

8. The computer-implemented method of claim 1 , wherein the sensor data is first sensor data, and wherein determining the type of the living being based at least in part on the object detection analysis comprises determining that the living being is a human, the method further comprising:
determining, based at least in part on the first sensor data, one or more physical characteristics of the human;
determining the range of the acceptable values for the health parameter based at least in part on the one or more physical characteristics of the human;
capturing, via the one or more sensors, second sensor data including measured values of the health parameter;
comparing the measured values of the health parameter to the range of acceptable values for the health parameter to obtain a set of one or more comparison results;
capturing, via the one or more sensors, third sensor data indicative of one or more environmental characteristics of at least one of an interior or surrounding exterior area of the vehicle; and
analyzing the third sensor data to generate a set of one or more analysis results,
wherein initiating the one or more automated vehicle response measures comprises initiating the one or more automated vehicle response measures further based at least in part on the set of one or more comparison results and the set of one or more analysis results.

9. The computer-implemented method of claim 8 , wherein comparing the measured values of the health parameter to the range of acceptable values for the health parameter comprises determining that at least a threshold number of the measured values are within the range of acceptable values for at least a threshold period of time, wherein analyzing the third sensor data comprises determining that the third sensor data is indicative of a potentially dangerous condition present in at least one of the interior or the surrounding exterior area of the vehicle, and wherein initiating the one or more automated vehicle response measures comprises at least one of: i) performing additional monitoring of the enclosed compartment of the vehicle to capture first additional sensor data including additional measured values of the health parameter, ii) performing additional monitoring of at least one of the interior or the surrounding exterior area of the vehicle to capture second additional sensor data indicative of the one or more environmental characteristics, or iii) sending a silent alert to one or more emergency service providers.

10. A system for detecting presence of a living being in an enclosed compartment of a vehicle, the system comprising:
at least one processor; and
at least one memory storing computer-executable instructions, wherein the at least one processor is configured to access the at least one memory and execute the computer-executable instructions to:
capture, via one or more sensors associated with the vehicle, sensor data relating to one or more sensed characteristics of the enclosed compartment of the vehicle, wherein the capturing comprises:
capturing, using a camera, one or more images within the enclosed compartment;
determining whether respective resolutions of the one or more images fail to satisfy a threshold resolution;
in response to determining that the respective resolutions of the one or more images fail to satisfy the threshold resolution, capturing any of:
heat signature data from one or more infrared (IR) sensors,
vibrational data from one or more vibration or inertial sensors, and
gas concentration data from one or more gas sensors;
determine that the sensor data is indicative of the presence of the living being in the enclosed compartment of the vehicle;
perform an object detection analysis on the one or more images image data included in the sensor data;
determine a type of the living being based at least in part on the object detection analysis;
determine a range of acceptable values of a healt

Assignees

• Pony Ai Inc

Inventors

• Dingli Robert
• Diehl Peter G

Classifications

• G06V10/764

  using classification, e.g. of video objects · CPC title

• B60W2040/0881

  Seat occupation; Driver or passenger presence · CPC title

• B60W50/14

  Means for informing the driver, warning the driver or prompting a driver intervention · CPC title

• G06V20/59

  inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions · CPC title

• G06V20/64

  Three-dimensional [3D] objects · CPC title