Image processing method and image processing device

• Main Authors: LIANG ZHE, ZHANG YUXIANG, ZHUANG YONGWEN, CAO YUHUI
• Format: Patent
• Language: Chinese; English
• Published: 10.05.2017
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention provides an image processing method and image processing device. The method and the device are used to realize a neural network algorithm for image processing, through utilization of a field programmable gate array (FPGA). The image processing method comprises the steps of obtaining original image data collected by an image obtaining unit; carrying out first image processing on the original image data through a first image processing unit, thereby obtaining first image data; determining a detection result of a target from the first image data by the field programmable gate array based on the first image data; and generating coding image data corresponding to the target by the first image processing unit based on the first image data and the detection result of the target. 本公开提供了种利用现场可编程门阵列(FPGA)实现用于图像处理的神经网络算法的图像处理方法和图像处理设备。所述图像处理方法包括：获取由图像获取单元采集的原始图像数据；由第图像处理单元对所述原始图像数据执行第图像处理，以获取第图像数据；由现场可编程门阵列单元基于所述第图像数据，确定所述第图像数据中的目标的检测结果；以及由所述第图像处理单元基于所述第图像数据和所述目标的检测结果，生成对应于所述目标的编码图像数据。