Abstract
Image demosaicking has been an essential and challenging problem among the most crucial steps of image processing behind image sensors. Due to the rapid development of intelligent processors based on deep learning, several demosaicking methods based on a convolutional neural network (CNN) have been proposed. However, it is difficult for their networks to run in real-time on edge computing devices with a large number of model parameters. This paper presents a compact demosaicking neural network based on the UNet++ structure. The network inserts densely connected layer blocks and adopts Gaussian smoothing layers instead of down-sampling operations before the backbone network. The densely connected blocks can extract mosaic image features efficiently by utilizing the correlation between feature maps. Furthermore, the block adopts depthwise separable convolutions to reduce the model parameters; the Gaussian smoothing layer can expand the receptive fields without down-sampling image size and discarding image information. The size constraints on the input and output images can also be relaxed, and the quality of demosaicked images is improved. Experiment results show that the proposed network can improve the running speed by 42% compared with the fastest CNN-based method and achieve comparable reconstruction quality as it on four mainstream datasets. Besides, when we carry out the inference processing on the demosaicked images on typical deep CNN networks, Mobilenet v1 and SSD, the accuracy can also achieve 85.83% (top 5) and 75.44% (mAP), which performs comparably to the existing methods. The proposed network has the highest computing efficiency and lowest parameter number through all methods, demonstrating that it is well suitable for applications on modern edge computing devices.
Highlights
In an ideal color digital camera system, there should be three image sensors that capture the red, green, and blue light component signals of photo images, respectively.that is complex and expensive
To speed up the convolutional neural network (CNN)-based image demosaicking process, this paper proposes a compact demosaicking neural network based on UNet++
We propose a compact, high-efficiency end-to-end demosaicking convolutional neural network for the current application needs on edge computing devices
Summary
In an ideal color digital camera system, there should be three image sensors that capture the red, green, and blue light component signals of photo images, respectively.that is complex and expensive. Most color digital cameras normally use an image sensor with a top color filter array (CFA) to capture the intensity of a single color component signal per pixel. It downsamples downsamples the the input input and extracts extracts image image features features through through three three densely densely connected connected image layer by layer and corresponding number number of times times convolutional layers. It is followed by up-sampling the corresponding bylayer layeruntil untilititarrives arrives allows image features at level each layer by at at thethe toptop andand getsgets out.out.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
