Soft Prototyping Camera Designs for Car Detection Based on a Convolutional Neural Network
Soft Prototyping Camera Designs for Car Detection Based on a Convolutional Neural Network
复制标题
基于卷积神经网络的汽车检测软原型相机设计
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
B. Wandell
中科院分区：
文献类型：
--
作者：
Zhenyi Liu;Trisha Lian;J. Farrell;B. Wandell
成像系统越来越多地被用作卷积神经网络（CNN）的输入，用于目标检测；我们希望设计出针对这一目的进行优化的相机。制造不同的相机，然后为每个潜在的相机设计获取和标记必要的数据是不切实际的；在环境中创建相机的软件模拟（软原型）是唯一现实的方法。我们实现了软原型工具，可以定量模拟图像亮度和相机设计，以创建逼真的图像，并将其输入到卷积神经网络中用于汽车检测。我们使用这些方法来量化关键硬件组件（像素大小）、传感器控制（曝光算法）和图像处理（伽马和去马赛克算法）对汽车检测平均精度的影响。我们量化了(a)像素大小与在不同距离上检测汽车的能力之间的关系，(b)选择不良曝光时间的惩罚，以及(c) CNN对各种采集后处理算法执行汽车检测的能力。这些结果表明，汽车检测的最佳选择不受消费者摄影中用于图像质量的相同指标的约束。使用带有特定任务指标的软原型来评估CNN应用程序的相机设计比使用消费者摄影指标更好。
Imaging systems are increasingly used as input to convolutional neural networks (CNN) for object detection; we would like to design cameras that are optimized for this purpose. It is impractical to build different cameras and then acquire and label the necessary data for every potential camera design; creating software simulations of the camera in context (soft prototyping) is the only realistic approach. We implemented soft-prototyping tools that can quantitatively simulate image radiance and camera designs to create realistic images that are input to a convolutional neural network for car detection. We used these methods to quantify the effect that critical hardware components (pixel size), sensor control (exposure algorithms) and image processing (gamma and demosaicing algorithms) have upon average precision of car detection. We quantify (a) the relationship between pixel size and the ability to detect cars at different distances, (b) the penalty for choosing a poor exposure duration, and (c) the ability of the CNN to perform car detection for a variety of post-acquisition processing algorithms. These results show that the optimal choices for car detection are not constrained by the same metrics used for image quality in consumer photography. It is better to evaluate camera designs for CNN applications using soft prototyping with task-specific metrics rather than consumer photography metrics.