Processing system, processing method, and processing program
A processing system is performed by using an edge device and a server device, wherein the edge device includes first processing circuitry configured to input divided data obtained by dividing processing data into a plurality of pieces to a corresponding first model among a plurality of first models, and cause inference in each of the first models to be executed, and output, to the server device, only the divided data for which it is determined that an inference result in the corresponding first model matches a predetermined condition among a plurality of pieces of the divided data, and the server device includes second processing circuitry configured to execute inference processing on the divided data output from the edge device by using a second model having a higher amount of computation than that of the first model.
1 . A processing system performed by using an edge device and a server device, wherein
the edge device includes:
first processing circuitry configured to:
input divided data obtained by dividing processing data into a plurality of pieces to a corresponding first model among a plurality of first models, and cause inference in each of the first models to be executed; and
output, to the server device, only the divided data for which it is determined that an inference result in the corresponding first model matches a predetermined condition among a plurality of pieces of the divided data, and
the server device includes
second processing circuitry configured to
execute inference processing on the divided data output from the edge device by using a second model having a higher amount of computation than that of the first model.
2 . The processing system according to claim 1 , wherein the first processing circuitry is further configured to:
input the divided data divided to the corresponding first model among the plurality of first models, and cause object detection in each of the first models to be executed, and
output, to the server device, the divided data determined in the corresponding first model that at least a predetermined object is included, among the plurality of pieces of the divided data.
3 . The processing system according to claim 2 , wherein the first processing circuitry is further configured to output, to the server device, the divided data that includes the predetermined object and in which a certainty factor, which is a degree of certainty that a result of the object detection by the first model is correct, is greater than or equal to a predetermined threshold, among the plurality of pieces of the divided data.
4 . The processing system according to claim 2 , wherein the first processing circuitry is further configured to:
perform object detection and moving object detection on the divided data, and
output, to the server device, the divided data that includes the predetermined object and in which moving object detection is made, among the plurality of pieces of the divided data.
5 . The processing system according to claim 2 , wherein
the second processing circuitry is further configured to integrate inference results for the respective pieces of the divided data and output an integrated inference result as an inference result for the processing data.
6 . The processing system according to claim 2 , wherein
the processing data is one image, and
the first processing circuitry is further configured to:
input each of a plurality of divided images obtained by dividing the one image to a corresponding first model among the plurality of first models, and cause subject recognition in each of the first models to be executed, and
output, to the server device, the divided images determined in the respective first models that at least a predetermined subject is included, among the plurality of divided images.
7 . The processing system according to claim 2 , wherein
the processing data is a plurality of images captured along a time series, and
the first processing circuitry is further configured to:
input each of the plurality of images to a corresponding first model among the plurality of first models, and cause subject recognition in each of the first models to be executed, and
output, to the server device, the images determined in the respective first models that at least a predetermined subject is included, among the plurality of images.
8 . The processing system according to claim 2 , wherein
the processing data is a plurality of images captured along a time series, and
the first processing circuitry is further configured to:
input each of the plurality of images to a corresponding first model among the plurality of first models, and cause subject recognition in each of the first models to be executed,
select an image recognized in the corresponding first model that at least a predetermined subject is included, among the plurality of images,
input each of a plurality of divided images obtained by dividing the image selected to a corresponding first model among the plurality of first models, and cause subject recognition in each of the first models to be executed, and
output, to the server device, the divided images determined in the respective first models that at least a predetermined subject is included, among the plurality of divided images.
9 . The processing system according to claim 2 , wherein
the first processing circuitry is further configured to respectively encode the pieces of the divided data determined to be output to the server device and output the encoded pieces of the divided data to the server device, and
the second processing circuitry is further configured to respectively decode the pieces of the divided data encoded.
10 . A processing method executed by a processing system performed by using an edge device and a server device,
the processing method comprising:
inputting divided data obtained by dividing processing data into a plurality of pieces to a corresponding first model among a plurality of first models, and causing inference in each of the first models to be executed;
outputting, to the server device, only the divided data for which it is determined that an inference result in the corresponding first model matches a predetermined condition among a plurality of pieces of the divided data; and
executing inference processing on the divided data output from the edge device by using a second model having a higher amount of computation than that of the first model.
11 . A non-transitory computer-readable recording medium storing therein a processing program that causes a computer to execute a process comprising:
inputting divided data obtained by dividing processing data into a plurality of pieces to a corresponding first model among a plurality of first models, and causing inference in each of the first models to be executed;
outputting only the divided data for which it is determined that an inference result in the corresponding first model matches a predetermined condition among a plurality of pieces of the divided data; and
executing inference processing on the divided data output from the edge device by using a second model having a higher amount of computation than that of the first model.