论文标题
DynamicISP：动态控制的图像信号处理器用于图像识别
DynamicISP: Dynamically Controlled Image Signal Processor for Image Recognition
论文作者
论文摘要
图像信号处理器（ISP）在图像识别任务以及捕获图像的感知质量中起着重要作用。在大多数情况下，专家们付出了很多努力来手动调整ISP的许多参数，但是参数是最佳的。在文献中，已经对两种类型的技术进行了积极研究：一种基于机器学习的参数调整技术和一种基于DNN的ISP技术。前者是轻量级的，但缺乏表现力。后者具有表达能力，但是在边缘设备上的计算成本太重了。为了解决这些问题，我们提出了“ DynamicISP”，该问题由多个经典的ISP函数组成，并根据上一个帧的识别结果动态控制每个帧的参数。我们显示我们的方法成功地控制了多个ISP函数的参数，并在单个和多类别对象检测任务中以低计算成本实现了最先进的精度。
Image Signal Processors (ISPs) play important roles in image recognition tasks as well as in the perceptual quality of captured images. In most cases, experts make a lot of effort to manually tune many parameters of ISPs, but the parameters are sub-optimal. In the literature, two types of techniques have been actively studied: a machine learning-based parameter tuning technique and a DNN-based ISP technique. The former is lightweight but lacks expressive power. The latter has expressive power, but the computational cost is too heavy on edge devices. To solve these problems, we propose "DynamicISP," which consists of multiple classical ISP functions and dynamically controls the parameters of each frame according to the recognition result of the previous frame. We show our method successfully controls the parameters of multiple ISP functions and achieves state-of-the-art accuracy with low computational cost in single and multi-category object detection tasks.
