Optical Filter Net: A Spectral-Aware RGB Camera Framework for Effective Green Pepper Segmentation
Optical Filter Net: A Spectral-Aware RGB Camera Framework for Effective Green Pepper Segmentation
复制标题
光学滤波器网络：用于有效青椒分割的光谱感知 RGB 相机框架
DOI：
10.1109/access.2021.3091305
复制
发表时间：
2021
期刊：
影响因子：
3.9
通讯作者：
Zhan Shu
中科院分区：
文献类型：
--
作者：
Yu Jun;Kurihara Toru;Zhan Shu
相似颜色物体的检测和识别是计算机视觉中一项具有挑战性的任务。自然环境中的绿色辣椒可以使用高光谱相机在光谱域中提供的丰富信息来发现，但是高光谱相机是昂贵的设备。因此，我们提出了一种新的框架，称为光学滤波器网络，它使设计的光学滤波器，提高性能的绿色辣椒分割的特定的红-绿色-蓝（RGB）相机系统。当安装有滤光器时，该系统可以有效地利用可见波长中的光谱信息来区分绿色辣椒和树叶，而不需要昂贵的高光谱相机。一个主要的发现是光学滤波器的透射曲线和无偏置的深度卷积核之间的相似性。因此，我们可以将滤光片的透射曲线视为深度神经网络的一层。整个结构可以以端到端的方式进行训练。为了符合光学滤波器的物理要求，我们进一步约束训练过程，以实现非负和平滑的透射曲线。在对我们的数据集进行的实验评估中，我们提出的光谱感知RGB相机系统优于没有光学滤波器的RGB相机系统。
Detecting and identifying objects of similar color is a challenging task in computer vision. Green peppers in a natural environment can be found using the abundant information provided by a hyperspectral camera in the spectral domain, but the hyperspectral camera is an expensive device. Therefore, we propose a novel framework called Optical Filter Net, which enables the design of an optical filter that improves the performance of green pepper segmentation by a specific red-green-blue (RGB) camera system. When installed with the optical filter, the system can efficiently utilize the spectral information in the visible wavelength to distinguish green pepper and foliage without requiring an expensive hyperspectral camera. A main finding is the similarity between the transmission curve of the optical filter and the depth-wise convolution kernel without bias. Accordingly, we can treat the transmission curve of the optical filter as one layer of a deep neural network. The whole structure can be trained in an end-to-end manner. To comply with the physical requirement of the optical filter, we further constrain the training process to achieve a non-negative and smooth transmission curve. In an experimental evaluation on our dataset, our proposed spectral-aware RGB camera system outperformed the RGB camera system without an optical filter.