Vision-assist devices and methods of calibrating image data of a vision-assist device
AssigneeToyota Motor Engineering & Manufacturing North America, Inc.
InventorNobuyuki Matsuno
Life of this patent
Estimating the term…
Abstract
Vision-assist devices and methods are disclosed. In one embodiment, a vision-assist device includes an image sensor for generating image data corresponding to a scene, a processor, and an inertia measuring unit. The inertia measuring unit is configured to measure forces acting on the image sensor and the orientation of the image sensor. The processor is configured to receive the image data from the image sensor and process the force and orientation of the image sensor so as to determine a tilt of the image sensor. The processor is further configured to process the image data based on at least the tilt of the at least one image sensor so as to generate a corrected image data, wherein the corrected image data does not include the tilt.
Claims18
A vision-assist device comprising:
- an image sensor for generating an image data corresponding to a scene;
- a processor;
- and
- an inertia measuring unit, the inertia measuring unit configured to detect a force acting on the at least one image sensor and an orientation of the at least one image sensor, wherein the processor is further configured to:
- receive the image data from the at least one image sensor;
- process the force and orientation of the at least one image sensor so as to determine a tilt of the image sensor;
- and
- process the image data from based on at least the tilt of the at least one image sensor so as to generate a corrected image data, wherein the corrected image data does not include the tilt,
- wherein the processor is further programmed to perform object recognition on the image data to determine a classification of a detected object that is present within the scene, determine a confidence value with respect to the classification of the detected object, wherein the confidence value is based on a confidence that the classification of the detected object matches an actual classification of the detected object, and generate an auditory signal based on the confidence value, and
- wherein the vision-assist device is configured to be worn by a user.
A method of calibrating a vision-assist device, the vision-assist device comprising an image sensor, a processor, and an inertia measuring unit, the method comprising the steps of:
- generating, using the image sensor, image data corresponding to a scene;
- receiving, by the processor, the image data from the at least one image sensor;
- detecting, using the inertia measurement unit, a force and orientation of the image sensor and generating at least one signal corresponding to the force and orientation of the image sensor;
- processing, using the processor, the force and orientation of the image sensor of the at least one signal to determine a tilt of image sensor;
- and
- processing, using the processor, the image data to remove the tilt from the image data so as to generate a corrected image data that does not include the tilt,
- wherein the processor is further programmed to perform object recognition on the image data to determine a classification of a detected object that is present within the scene, determine a confidence value with respect to the classification of the detected object, wherein the confidence value is based on a confidence that the classification of the detected object matches an actual classification of the detected object, and generate an auditory signal based on the confidence value, and
- wherein the vision-assist device is configured to be worn by a user.
Dependencies are inferred from the claim text.