Qualcomm Incorporated

12 Sigma Technologies

Yunqiang Chen

Xiaoyun Jiang

Dashan Gao

Xin Zhong

Shilpi Sahu

Feng Li

Min Li

Jiao Wang

Tianyi Zhao

Yuanpeng Wu

Shu Fei Fan

Nariaki Yamada

Hyung Cook Kim

Ke Qi

An apparatus for image processing includes one or more processors configured to receive first image data in a first color format that includes a plurality of color planes at a reduced resolution relative to a full resolution, generate second image data in an intermediate color format based on the first image data in the first color format, the intermediate color format includes a first color plane at an increased resolution and at least one of the plurality of color planes at the reduced resolution, store, in the one or more external memories, the second image data, perform image processing based on accessing the second image data, and generate third image data based on the image processing, the third image data is in a third color format that includes the plurality of color planes at a same resolution.

Intermediate color format for image processing

This disclosure is directed to a system and a method for providing enhanced real-time or near-real-time response to request for detached data analytics services. In one implementation, a system is disclosed for predicting a data analytics service that may be requested by a user based on real-time user interactive operations, and for pre-loading/pre-configuring a pipeline of data analytics components for performing the predicted data analytics service before an actual request is made. Additionally, at least some intermediate data may be calculated by the pre-configured pipeline and may be pre-cached in memory. Upon actual user request for the data analytics service, only data analytics that require additional input data concurrently provided with the request would need to be performed. In such a manner, user-perceived delay in completing the detached data analytics service is reduced.

Enhancement of real-time response to request for detached data analytics

This disclosure relates to digital image segmentation and region of interest identification. A computer implemented image segmentation method and system are particularly disclosed, including a predictive model trained based on a deep fully convolutional neural network. The model is trained using a loss function in at least one intermediate layer in addition to a loss function at the final stage of the full convolutional neural network. The predictive segmentation model trained in such a manner requires less training parameters and facilitates quicker and more accurate identification of relevant local and global features in the input image. In one implementation, the fully convolutional neural network is further supplemented with a conditional adversarial neural networks iteratively trained with the fully convolutional neural network as a discriminator measuring the quality of the predictive model generated by the fully convolutional neural network.

Enhanced convolutional neural network for image segmentation

In some cases, conventional digital zoom techniques can lead to poor quality images. Disclosed are systems and methods for improving the quality of images generated by digital zoom. For example, in some embodiments, a parallel structure is utilized where an image is passed through a sharpener and a 2D directional upscaler at the same time. Upscaling operations are then performed on the sharpened image. The upscaled sharpened image is added to the output of the 2D directional upscaler to produce an enhanced image.

Digital zoom methods and systems

Growing community of inventors

San Diego, CA, United States of America

Yunqiang Chen