This paper proposed an improved image semantic segmentation method based on superpixels and conditional random fields (CRFs). The proposed method can take full advantage of the superpixel edge information and the constraint relationship among different pixels. First, we employ fully convolutional networks (FCN) to obtain pixel-level semantic features and utilize simple linear iterative clustering (SLIC) to generate superpixel-level region information, respectively. Then, the segmentation results of image boundaries are optimized by the fusion of the obtained pixel-level and superpixel-level results. Finally, we make full use of the color and position information of pixels to further improve the semantic segmentation accuracy using the pixel-level prediction capability of CRFs. In summary, this improved method has advantages both in terms of excellent feature extraction capability and good boundary adherence. Experimental results on both the PASCAL VOC 2012 dataset and the Cityscapes dataset show that the proposed method can achieve significant improvement of segmentation accuracy in comparison with the traditional FCN model.
Abstract:In order to simplify the hardware design and reduce the resource requirements, this paper proposes a novel implementation of a convolutional auto-encoder (CAE) in a field programmable gate array (FPGA). Instead of the traditional framework realized in a layer-by-layer way, we designed a new periodic layer-multiplexing framework for CAE. Only one layer is introduced and periodically reused to establish the network, which consumes fewer hardware resources. Moreover, by fixing the number of channels, this framework can be applicable to an image of arbitrary size. Furthermore, to effectively improve the speed of convolution calculation, the parallel convolution method is used based on shift registers. Experimental results show that the proposed CAE framework achieves good performance in image compression. It can be observed that our CAE framework has advantages in resources occupation, operation speed, and power consumption, indicating great potential for application in digital signal processing.
Remote sensing optical image cloud detection is one of the most important problems in remote sensing data processing. Aiming at the information loss caused by cloud cover, a cloud detection method based on convolution neural network (CNN) is presented in this paper. Firstly, a deep CNN network is used to extract the multi-level feature generation model of cloud from the training samples. Secondly, the adaptive simple linear iterative clustering (ASLIC) method is used to divide the detected images into superpixels. Finally, the probability of each superpixel belonging to the cloud region is predicted by the trained network model, thereby generating a cloud probability map. The typical region of GF-1/2 and ZY-3 were selected to carry out the cloud detection test, and compared with the traditional SLIC method. The experiment results show that the average accuracy of cloud detection is increased by more than 5 %, and it can detected thin-thick cloud and the whole cloud boundary well on different imaging platforms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.