Systems and methods for temperature measurement

1 . A system, comprising:

at least one storage device including a set of instructions; and

at least one processor in communication with the at least one storage device, wherein when executing the set of instructions, the at least one processor is directed to perform operations including:

obtaining an image of an object acquired by an imaging device;

determining, based on the image, an angle between the object and the imaging device, the angle being defined by a reference direction and a direction that the object is facing; and

determining, based on the image, a temperature of the object in response to determining that the angle satisfies a condition, including:

obtaining a second image of the object acquired by a second imaging device, the second image being a thermal image and including temperature information of the object;

determining a position of the object in the second image based on a position of the object in the image and a transform relationship between a first coordinate system of the imaging device and a second coordinate system of the second imaging device;

obtaining, based on the position of the object in the second image, the temperature information of the object; and

determining, based on the temperature information of the object, the temperature of the object.

2 . The system of claim 1 , wherein the determining, based on the image, an angle between the object and the imaging device includes:

determining, based on the image, the angle between the object and the imaging device using an angle detection model associated with a plurality of reference images of reference objects each of which is acquired by a reference imaging device and corresponds to a reference angle between a reference object and the reference imaging device.

3 . The system of claim 2 , wherein the angle detection model includes a trained machine learning model, and the trained machine learning model is acquired according to a training process including:

obtaining the plurality of reference images of reference objects;

labeling each of at least a portion of the plurality of reference images with the reference angle corresponding to the reference image; and

training a preliminary machine learning model using the plurality of reference images and the reference angles corresponding to the plurality of reference images.

4 . The system of claim 3 , wherein the determining, based on the image, an angle between the object and the imaging device includes:

inputting the image into the trained machine learning model;

extracting image features from the image using the trained machine learning model; and

determining the angle based on the image features from the image.

5 . The system of claim 2 , wherein the angle detection model includes a corresponding relationship between each of the plurality of reference images of reference objects and the reference angle between the reference object and the imaging device, and the determining, based on the image, an angle between the object and the imaging device using an angle detection model includes:

extracting angle features from the image;

extracting reference angle features from each of the plurality of reference images;

determining at least one of the plurality of reference images whose reference angle features match the angle features of the image; and

determining the angle between the object and the imaging device based on at least one reference angle corresponding to the at least one of the plurality of reference images.

6 . The system of claim 1 , wherein the obtaining, based on the position of the object in the second image, the temperature information of the object includes:

identifying a target region of the object from the second image based on the position of the object in the second image; and

determining temperature information of the target region.

7 . The system of claim 6 , wherein the target region includes at least one of a facial area or a forehead area.

8 . The system of claim 6 , wherein the determining, based on temperature information of the target region, the temperature of the object includes:

determining a bounding box enclosing the target region, the bounding box being defined by at least one of one or more geometric parameters and position parameters; and

determining the temperature of the object based on the temperature information of the target region enclosed by the bounding box.

9 . A system, comprising:

at least one storage device including a set of instructions; and

at least one processor in communication with the at least one storage device, wherein when executing the set of instructions, the at least one processor is directed to perform operations including:

obtaining an image of an object acquired by an imaging device;

determining whether the image satisfies a condition; and

determining, based on the image, a temperature of the object in response to determining that the image satisfies the condition, including:

obtaining a second image of the object acquired by a second imaging device, the second image being a thermal image and including temperature information of the object;

determining a position of the object in the second image based on a position of the object in the image and a transform relationship between a first coordinate system of the imaging device and a second coordinate system of the second imaging device;

obtaining, based on the position of the object in the second image, the temperature information of the object; and

determining, based on the temperature information of the object, the temperature of the object.

10 . A method, the method being implemented on a computing device having at least one storage device and at least one processor, the method comprising:

obtaining an image of an object acquired by an imaging device;

determining, based on the image, an angle between the object and the imaging device, the angle being defined by a reference direction and a direction that the object is facing; and

determining, based on the image, a temperature of the object in response to determining that the angle satisfies a condition.

11 . The method of claim 10 , wherein the determining, based on the image, an angle between the object and the imaging device includes:

determining, based on the image, the angle between the object and the imaging device using an angle detection model associated with a plurality of reference images of reference objects each of which is acquired by a reference imaging device and corresponds to a reference angle between a reference object and the reference imaging device.

12 . The method of claim 11 , wherein the angle detection model includes a trained machine learning model, and the trained machine learning model is acquired according to a training process including:

obtaining the plurality of reference images of reference objects;

labeling each of at least a portion of the plurality of reference images with the reference angle corresponding to the reference image; and

training a preliminary machine learning model using the plurality of reference images and the reference angles corresponding to the plurality of reference images.

13 . The method of claim 12 , wherein the determining, based on the image, an angle between the object and the imaging device includes:

inputting the image into the trained machine learning model;

extracting image features from the image using the trained machine learning model; and

determining the angle based on the image features from the image.

14 . The method of claim 11 , wherein the angle detection model includes a corresponding relationship between each of the plurality of reference images of reference objects and the reference angle between the reference object and the imaging device, and the determining, based on the image, an angle between the object and the imaging device using an angle detection model includes:

extracting angle features from the image;

extracting reference angle features from each of the plurality of reference images;

determining at least one of the plurality of reference images whose reference angle features match the angle features of the image; and

determining the angle between the object and the imaging device based on at least one reference angle corresponding to the at least one of the plurality of reference images.

15 . The method of claim 10 ,

identifying a target region of the object from a second image based on a position of the object in the second image; and determining temperature information of the target region.

16 . The method of claim 15 , wherein the target region includes at least one of a facial area or a forehead area.

17 . The method of claim 15 , wherein the determining, based on temperature information of the target region, the temperature of the object includes:

determining a bounding box enclosing the target region, the bounding box being defined by at least one of one or more geometric parameters and position parameters; and

determining the temperature of the object based on the temperature information of the target region enclosed by the bounding box.