Imaging device, image recording device, and imaging method for capturing a predetermined event
Provided are an imaging device, an image recording device, and an imaging method capable of recording an important moment. An imaging device includes an imaging unit and a changing unit. The imaging unit captures an image of the surroundings, and generates image data. The changing unit changes the frame rate of an image captured by the imaging unit in accordance with the degree of possibility that a predetermined event occurs, which is predicted based on the image data.
1. An imaging device, comprising:
circuitry configured to:
capture an image of surroundings to generate image data;
calculate, based on deep neural network (DNN) processing using a DNN, an accident prediction score indicating a degree of possibility that an accident, wherein the DNN is generated by machine learning based on image data of a plurality of images captured before occurrence of the accident and image data of a plurality of images based on a determination that no accident has occurred after the image is captured;
change a frame rate of the captured image based on the degree of possibility; and
change a luminance of the captured image based on the change in the frame rate and change in a gain of an amplifier that amplifies the luminance of the captured image.
2. The imaging device according to claim 1 , wherein the circuitry is further configured to increase the frame rate as the degree of possibility is increased.
3. The imaging device according to claim 1 , wherein the circuitry is further configured to increase a resolution of the captured image as the prediction score increases.
4. The imaging device according to claim 3 , wherein the circuitry is further configured to decrease the resolution and the frame rate as the prediction score decreases.
5. The imaging device according to claim 1 , wherein the circuitry is further configured to:
detect illuminance of the surroundings; and
determine a change range of the frame rate based on the detected illuminance.
6. The imaging device according to claim 1 , wherein the circuitry is further configured to increase the luminance of the captured image as the frame rate of the captured image is increased.
7. The imaging device according to claim 1 , wherein the circuitry is further configured to:
detect illuminance of the surroundings;
set, based on the detected illuminance, an upper limit of the frame rate of the captured image, wherein
the upper limit of the frame rate is decreased as the detected illuminance of the surroundings decreases; and
change the frame rate of the captured image based on the set upper limit.
8. An image recording device, comprising:
an imaging device including:
circuitry configured to:
capture an image of surroundings and generate image data;
calculate, based on deep neural network (DNN) processing using a DNN, an accident prediction score indicating a degree of possibility that an accident occurs, wherein the DNN is generated by machine learning based on image data of a plurality of images captured before occurrence of the accident and image data of a plurality of images based on a determination that no accident has occurred after the image is captured;
change a frame rate of the captured image based on the degree of possibility; and
change a luminance of the captured image based on the change in the frame rate and change in a gain of an amplifier that amplifies the luminance of the captured image; and
a memory configured to record the image captured by the imaging device.
9. An imaging method, comprising:
capturing an image of surroundings, and generating an image data;
calculating, based on deep neural network (DNN) processing using a DNN, an accident prediction score indicating a degree of possibility that an accident, wherein the DNN is generated by machine learning based on image data of a plurality of images captured before occurrence of the accident and image data of a plurality of images based on a determination that no accident has occurred after the image is captured;
changing a frame rate of the captured image based on the degree of possibility; and
changing a luminance of the captured image based on the change in the frame rate and change in a gain of an amplifier that amplifies the luminance of the captured image.