Abstract
Raft-culture is a way of utilizing water for farming aquatic product. Automatic raft-culture monitoring by remote sensing technique is an important way to control the crop’s growth and implement effective management. This paper presents an automatic pixel-wise raft labeling method based on fully convolutional network (FCN). As rafts are always tiny and neatly arranged in images, traditional FCN method fails to extract the clear boundary and other detailed information. Therefore, a homogeneous convolutional neural network (HCN) is designed, which only consists of convolutions and activations to retain all details. We further design a dual-scale structure (DS-HCN) to integrate higher-level contextual information for accomplishing sea–land segmentation and raft labeling at the same time in a uniform framework. A dataset with Gaofen-1 satellite images was collected to verify the effectiveness of our method. DS-HCN shows a satisfactory performance with a better interpretability and a more accurate labeling result.
Highlights
Raft-culture is a kind of aquaculture, where people use offshore waters to cultivate aquatic crops such as wakame, kelp and shellfish
We propose a new model called Homogeneous Convolutional Neural Network (HCN), which only consists of convolution and activation layers
The first experiment was used to evaluate the performance of the classical adaptive threshold method (AT) [1], a state-of-the-art semantic labeling method DeepLab [24], homogeneous convolutional neural network (HCN) and its dual-scale version dual-scale version of HCN (DS-HCN)
Summary
Raft-culture is a kind of aquaculture, where people use offshore waters to cultivate aquatic crops such as wakame, kelp and shellfish. The rafts are usually made up of floats and ropes, fixed to the seabed and neatly arranged on the water. With the fast development of optical remote sensing techniques, people nowadays are able to observe the states of rafts and control the growth of crops by remote sensing images. To obtain the accurate distribution and the area of these rafts, people have to manually label the large scale of the remote sensing image pixel by pixel. Labeling one thousand square kilometers of sea area would take tens of hours of human work. Automatic raft-culture labeling by optical remote sensing is important for agricultural automation production and implementing effective management
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.