Introducing a case study on the acceleration of image processing programs using the OSCARTech compiler.
The "OSCARTech Compiler" supports automatic parallelization of a wide range of software programs. We will introduce a case of automatic parallelization applied to a fundamental image processing algorithm called "Optical Flow," which detects the magnitude of movement (motion vectors) of objects within an image. In this case, we attempted parallelization using block matching (a method where blocks are cut out from a still image at a certain moment, and the vicinity of the same coordinates in the next moment is searched to select and determine the most similar block). 【Case Study】 ■ Optical Flow: Detects the direction and magnitude (motion vectors) of movement of objects within an image. ■ Verification Environment: Raspberry Pi 2 (Cortex-A7, 4 Core, 900Mhz, OS: Raspbian OS) ■ Time taken to generate motion vectors: - 1 Core: 936ms / 1.0x - 2 Cores: 480ms / 1.9x - 3 Cores: 340ms / 2.7x *For more details, please refer to the PDF document or feel free to contact us.
Inquire About This Product
basic information
【Other Examples】 ■ Image Edge Extraction Using the program "Image Edge Extraction," which is employed as a preprocessing step in image recognition to detect the outlines of objects within an image, edges are determined at points of sign change in the second derivative values after noise reduction with a 5×5 Laplacian of Gaussian filter, where the first derivative values exceed a specified threshold. ■ Sequential Approximation Image Reconstruction This is one method of reconstructing the measured object using projection data obtained from X-ray CT imaging, and an attempt was made at "Sequential Approximation Image Reconstruction" using a two-dimensional sequential approximation algorithm. ■ 3D Cone Beam An attempt was made to parallelize the "3D Cone Beam Method," which reconstructs images from projection data of a three-dimensional cone beam (conical) using the Feldkamp method. *For more details, please refer to the PDF document or feel free to contact us.
Price range
Delivery Time
Applications/Examples of results
For more details, please refer to the PDF document or feel free to contact us.
catalog（3）
Download All Catalogs
![[Example] Automatic parallelization of image processing programs](https://image.mono.ipros.com/public/catalog/image/01/0b4/381852/IPROS76641663294814749238.jpeg?w=120&h=170)
Company information
Oscar Technology Co., Ltd. is a venture business established to commercialize technology related to the parallelization of software developed through research at Waseda University. The technology from Waseda University pertains to a compiler that automatically parallelizes the driving software of computers, and it is unique in the world, receiving high academic acclaim for its effectiveness. By utilizing this technology, it is possible to enhance the performance of almost all electronic devices that use computers without changing their hardware, while simultaneously reducing power consumption.
