Back to results
US 11,891,002 B1Granted
Determining comfort settings in vehicles using computer vision
AssigneeAmbarella International LP
InventorsShimon Pertsel, Patrick Martin
Life of this patent
Estimating the term…
Abstract
An apparatus includes a capture device and a processor. The capture device may be configured to generate a plurality of video frames corresponding to users of a vehicle. The processor may be configured to perform operations to detect objects in the video frames, detect users of the vehicle based on the objects detected in the video frames, determine a comfort profile for the users and select a reaction to adjust vehicle components according to the comfort profile of the detected users. The comfort profile may be determined in response to characteristics of the users. The characteristics of the users may be determined by performing the operations on each of the users.
Claims19
An apparatus comprising:
- an interface configured to receive pixel data;
- and
- a processor configured to (i) process said pixel data arranged as video frames, (ii) detect one or more users by performing computer vision operations on said video frames, (iii) determine whether each of said users identified in said video frames is a known user or an unknown user, (iv) determine a comfort profile corresponding to said users detected and (v) select a reaction to adjust an environment according to said comfort profile of said users detected, wherein
- (a) said comfort profile is determined in response to (i) individual settings when one of said users is said known user and (ii) body type settings based on characteristics of one of said users when said one of said users is said unknown user,
- (b) said characteristics of said users are determined by performing said computer vision operations on each of said users,
- (c) said individual settings comprise adjustments to said environment specific to a particular person identified in response to said computer vision operations configured to perform facial recognition,
- (d) said body type settings comprise adjustments to said environment selected based on stored adjustments selected from a match with statistical information of said users with similar body proportions, said stored adjustments are previously collected from numerous combinations of body types and preferences,
- (e) said computer vision operations are further configured to detect a change to body parts that affects said comfort profile of said known user, and
- (f) said reaction further comprises recommending a comfort profile change to said individual settings in response to said change to said body parts detected.
6 more elements
An apparatus comprising:
- an interface configured to receive pixel data;
- and
- a processor configured to (i) process said pixel data arranged as video frames, (ii) detect one or more users by performing computer vision operations on said video frames, (iii) determine whether each of said users identified in said video frames is a known user or an unknown user, (iv) determine a comfort profile corresponding to said users detected and (v) select a reaction to adjust an environment according to said comfort profile of said users detected, wherein
- (a) said comfort profile is determined in response to (i) individual settings when one of said users is said known user and (ii) body type settings based on characteristics of one of said users when said one of said users is said unknown user,
- (b) said characteristics of said users are determined by performing said computer vision operations on each of said users,
- (c) said individual settings comprise adjustments to said environment specific to a particular person identified in response to said computer vision operations configured to perform facial recognition,
- (d) said body type settings comprise adjustments to said environment selected based on stored adjustments selected from a match with statistical information of said users with similar body proportions, said stored adjustments are previously collected from numerous combinations of body types and preferences, and
- (e) said computer vision operations are further performed by applying a convolution operation defined by a feature detection window using matrix multiplication of a plurality of layers generated from said video frames.
5 more elements
Dependencies are inferred from the claim text.