Neural network supported camera image or video processing pipeline

• Main Authors: HUMPHRIES MARTIN, GORDON KEVIN, D 'AMORE COLIN
• Format: Patent
• Language: Chinese; English
• Published: 03.02.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS; PICTORIAL COMMUNICATION, e.g. TELEVISION

Comprising a still life camera or a video camera comprises a first neural network arranged to process and provide neural network-based results for at least one of image capture settings, sensor processing, global post-processing, local post-processing, and combined post-processing. The second neural network is arranged to receive neural network results and further provide at least one of image capture settings, sensor processing, global post-processing, local post-processing, and combined post-processing, wherein at least one of the first and second neural networks generates data on a local processor supported by a still life camera or a video camera. 包括静物相机或视频相机的图像处理流水线包括第一神经网络，该第一神经网络被布置为处理和提供用于图像捕获设置、传感器处理、全局后处理、局部后处理和组合后处理中的至少一个的基于神经网络的结果。第二神经网络被布置为接收神经网络结果并进一步提供图像捕获设置、传感器处理、全局后处理、局部后处理和组合后处理中的至少一个，其中第一和第二神经网络中的至少一个在由静物相机或视频相机支持的本地处理器上生成数据。