Fujitsu Corporation

Miho Kawano

Takahisa Suzuki

Ryuichi Matsukura

Kouichirou Amemiya

Kento Ikkaku

An information processing apparatus includes processors configured to execute inference processing using a GPU on frames of a moving image through each application for each of a plurality of applications, acquire a first degree of similarity between a target frame and a frame at a time of execution of previous inference processing, acquire a second degree of similarity between the target frame and an immediately preceding frame that is executed after the previous inference processing, set a constraint on execution of inference processing for the target frame having a throughput larger than a certain value when a number of frames accumulated in a queue that is used for waiting for the execution of the inference processing and accumulates frames exceeds a certain number, and determine whether to execute the inference processing for the target frame based on the first degree, the second degree, and whether the constraint presents.

Information processing apparatus, inference execution control method, and storage medium

An image processing control device includes: a memory; and a processor coupled to the memory and configured to: determine, on a basis of a processing rate of an image processing program to be deployed, a type of transfer data extracted from video at a time of transferring the video to be processed by the image processing program to be deployed to be a moving image or a still image; and select, on a basis of the type of the transfer data, a deployment destination information processing device to which the image processing program to be deployed is deployed from among a plurality of information processing devices.

Improving resource efficiency in an image processing system for processing a moving image or a still frame

A data collection device includes a memory and a processor coupled to the memory and the processor configured to acquire, for a plurality of data transmission requests, first predicted values of a delay from transmission of the respective data transmission requests to a start of reception of data and second predicted values of a throughput regarding the reception of the data, classify the plurality of data transmission requests into groups based on first dispersion of the first predicted values and second dispersion of the second predicted values, and determine transmission timings of the respective data transmission requests in a unit of the group.

Growing community of inventors

Hamamatsu, Japan

Miho Kawano