Roland has been granted a patent for a computer program that enables image processing for person detection in frame images. The program includes steps for storing a person region, acquiring frame images from a moving image, setting a detection region based on the stored person region, and detecting the person within the detection region. The patent also includes expanded regions of the person’s whole body based on their role in vocal or instrumental performance. GlobalData’s report on Roland gives a 360-degree view of the company including its patenting strategy. Buy the report here.

Smarter leaders trust GlobalData

Report-cover

Premium Insights Roland Corp - Company Profile

Buy the Report

Premium Insights

The gold standard of business intelligence.

Find out more

According to GlobalData’s company profile on Roland, spatial audio processing was a key innovation area identified from patents. Roland's grant share as of September 2023 was 24%. Grant share is based on the ratio of number of grants to total number of patents.

Image processing program for detecting a person in a frame image

Source: United States Patent and Trademark Office (USPTO). Credit: Roland Corp

A recently granted patent (Publication Number: US11776309B2) describes an image processing program that enables a computer to execute image processing tasks. The program includes several steps to detect and analyze a person in a frame image.

The first claim of the patent describes a computer-readable medium that stores the image processing program. It includes steps such as storing a person region (a region that includes a detected person) and acquiring the frame image from a moving image. The program also sets a detection region based on expanded regions of the person's whole body. Finally, it detects the person within the set detection region.

The second claim builds upon the first claim by adding a person region acquisition step. This step acquires a person region based on the person detected in the previous step. The person region is then stored in the person storage step.

The third claim introduces a partial image acquisition step and a detection image generation step. These steps involve acquiring a partial image based on the person region stored in the person storage step and generating a detection image based on the acquired partial image. The person detection step then detects the person from the generated detection image.

The fourth claim reiterates the person detection step from the third claim, emphasizing that it detects the person from both the detection image and the detection region set in the previous steps.

The fifth claim is similar to the third claim, introducing the partial image acquisition and detection image generation steps. The person detection step remains the same.

The sixth claim reiterates the person detection step from the fifth claim, emphasizing that it detects the person from both the detection image and the detection region set in the previous steps.

The seventh claim introduces a range setting step, where a specific range including the person in the frame image is set. The person detection step then detects the person present in the specific range and the detection region set in the previous steps.

The eighth claim specifies that the specific range is set based on a specific body part of the person, such as their feet. The person detection step detects the person whose specific body part is present in the specific range and the detection region.

The ninth claim further specifies that the range setting step sets the feet of the person as the specific body part.

The tenth claim introduces the concept of a performer and sets the specific range as the stage on which the person performs in the frame image.

The eleventh claim introduces a non-specific range setting step, where a range not specified as a person region is set. The person detection step then detects the person from a region excluding the non-specific range and within the detection region.

The twelfth claim specifies that the non-specific range is a screen provided around the stage on which the performer performs.

The thirteenth claim introduces a region expansion table that stores expansion ratios corresponding to the vocal or instrument performed by the person. The expanded regions are the whole body regions expanded according to the expansion ratio in the table.

The patent also includes claims for an image processing apparatus and method that implement the steps described in the previous claims. These claims outline the components and steps involved in the apparatus and method, including the storage, acquisition, setting, and detection processes.

In summary, this granted patent describes an image processing program, apparatus, and method that enable the detection and analysis of a person in a frame image. The program includes steps for storing person regions, acquiring frame images, setting detection regions, and detecting the person within those regions. The apparatus and method implement these steps to achieve the desired image processing tasks.

To know more about GlobalData’s detailed insights on Roland, buy the report here.

Premium Insights

From

The gold standard of business intelligence.

Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.

GlobalData

GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.

GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.