Systems, devices and methods for measuring the mass of objects in a vehicle
There are provided methods and systems for estimating the mass of occupants in a vehicle cabin comprising obtaining multiple images of the occupants, comprising a sequence of two dimensional (2D) images and three dimensional (3D) images of the vehicle cabin captured by an image sensor, applying a pose detection algorithm on each of the obtained sequences of 2D images to yield one or more skeleton representations of the occupants and combining the one or more 3D images of said sequence of 3D images with the skeleton representations of the occupants to yield skeleton models and analyze the skeleton models to extract one or more features of each of the occupants and further process the one or more extracted features of the skeleton models to estimate the mass of the occupants.
1. A method for estimating the mass of one or more occupants in a vehicle cabin of a vehicle, the method comprising:
providing a processor configured to:
obtain multiple images of said one or more occupants, wherein said multiple images comprising sequences of 2D (two dimensional) images and one or more 3D (three dimensional) images of the vehicle cabin captured by an image sensor;
apply a pose detection algorithm on each of the sequences of 2D images to yield one or more skeleton representations of said one or more occupants;
filter out one or more skeleton representations based on predefined filtering criteria to yield valid skeleton representations, wherein said predefined filtering criteria is based on measured confidence grades of one or more key points in said skeleton representations;
analyze the one or more 3D images to extract one or more depth values of said one or more occupants;
apply the one or more depth values accordingly on the one or more skeleton representations to yield scaled skeleton models of the one or more occupants, wherein each of said scaled skeleton models comprises information relating to the distance of the skeleton model from a viewpoint;
analyze the scaled skeleton models to extract one or more features of each of the one or more occupants; and
process the one or more features to estimate the mass or body mass classification of each said one or more occupants.
2. The method of claim 1 , wherein said predefined filtering criteria includes specific selection rules which define valid poses or orientations of the one or more occupants.
3. The method of claim 1 , wherein said confidence grades are based on a measured probability heat map of said one or more key points.
4. The method of claim 1 , wherein said processor is configured to generate one or more output signals comprising said estimated mass or body mass classification of each said one or more occupants.
5. The method of claim 4 , wherein said output signals correspond to an operation of one or more units of the vehicle.
6. A method for estimating the mass of one or more occupants in a vehicle cabin of a vehicle, the method comprising:
providing a processor configured to:
obtain multiple images of said one or more occupants, wherein said multiple images comprising sequences of 2D (two dimensional) images and one or more 3D (three dimensional) images of the vehicle cabin captured by an image sensor;
apply a pose detection algorithm on each of the sequences of 2D images to yield one or more skeleton representations of said one or more occupants;
filter out one or more skeleton representations based on predefined filtering criteria to yield valid skeleton representations, wherein said predefined filtering criteria is based on a high-density model;
analyze the one or more 3D images to extract one or more depth values of said one or more occupants;
apply the one or more depth values accordingly on the one or more skeleton representations to yield scaled skeleton models of the one or more occupants, wherein each of said scaled skeleton models comprises information relating to the distance of the skeleton model from a viewpoint;
analyze the scaled skeleton models to extract one or more features of each of the one or more occupants; and
process the one or more features to estimate the mass or body mass classification of each said one or more occupants.
7. A system for estimating the mass of one or more occupants in a vehicle cabin of a vehicle, the system comprising:
a sensing device comprising:
an illumination module comprising one or more illumination sources configured to illuminate said vehicle cabin;
at least one imaging sensor configured to capture sequences of 2D (two dimensional) images and one or more 3D (three dimensional) images of the vehicle cabin; and
at least one processor configured to:
apply a pose detection algorithm on each of the sequences of 2D images to yield one or more skeleton representations of said one or more occupants;
analyze the one or more 3D images to extract one or more depth values of said one or more occupants;
apply the one or more depth values accordingly on the one or more skeleton representations to yield one or more scaled skeleton models of the one or more occupants, wherein each of said scaled skeleton models comprises information relating to the distance of the skeleton model from a viewpoint;
analyze the one or more scaled skeleton models to extract one or more features of each of the one or more occupants; and
process the one or more features to estimate the mass of each said one or more occupants.
8. The system of claim 7 , wherein said processor is configured to filter out one or more scaled skeleton models based on predefined filtering criteria to yield valid scaled skeleton models.
9. The system of claim 8 , wherein said predefined filtering criteria includes specific selection rules which define valid poses or orientations of the one or more occupants.
10. The system of claim 8 , wherein said predefined filtering criteria is based on a high-density model.
11. The system of claim 7 , wherein said sensing device is selected from a group consisting of: a ToF sensing device and a stereoscopic sensing device.
12. The system of claim 7 , wherein said sensing device is a structured light pattern sensing device and the at least one illumination source is configured to project modulated light in a predefined structured light pattern on the vehicle cabin.
13. The system of claim 12 , wherein the predefined structured light pattern is constructed of a plurality of diffused light elements.
14. The system of claim 13 , wherein a shape of said diffused light elements is one or more of a: dot, line, stripe, and a combination thereof.
15. The system of claim 7 , wherein said processor is configured to generate one or more output signals comprising said estimated mass or body mass classification of each said one or more occupants.
16. The system of claim 15 , wherein said output signals correspond to an operation of one or more units of the vehicle.
17. The system of claim 16 , wherein the one or more units of the vehicle are selected from the group consisting of: an Airbag, an Electronic Stabilization Control (ESC) Unit, and a safety belt.