Current Issue : January - March Volume : 2021 Issue Number : 1 Articles : 5 Articles
Single image super-resolution (SISR) is a traditional image restoration problem. Given an image with low resolution (LR), the task\nof SISR is to find the homologous high-resolution (HR) image. As an ill-posed problem, there are works for SISR problem from\ndifferent points of view. Recently, deep learning has shown its amazing performance in different image processing tasks. There are\nworks for image super-resolution based on convolutional neural network (CNN). In this paper, we propose an adaptive residual\nchannel attention network for image super-resolution. We first analyze the limitation of residual connection structure and\npropose an adaptive design for suitable feature fusion. Besides the adaptive connection, channel attention is proposed to adjust the\nimportance distribution among different channels. A novel adaptive residual channel attention block (ARCB) is proposed in this\npaper with channel attention and adaptive connection. Then, a simple but effective upscale block design is proposed for different\nscales. We build our adaptive residual channel attention network (ARCN) with proposed ARCBs and upscale block. Experimental\nresults show that our network could not only achieve better PSNR/SSIM performances on several testing benchmarks but also\nrecover structural textures more effectively....
Anomaly event detection has been extensively researched in computer vision in recent years. Most conventional anomaly event\ndetection methods can only leverage the single-modal cues and not deal with the complementary information underlying other\nmodalities in videos. To address this issue, in this work, we propose a novel two-stream convolutional networks model for\nanomaly detection in surveillance videos. Specifically, the proposed model consists of RGB and Flow two-stream networks, in\nwhich the final anomaly event detection score is the fusion of those of two networks. Furthermore, we consider two fusion\nsituations, including the fusion of two streams with the same or different number of layers respectively. The design insight is to\nleverage the information underlying each stream and the complementary cues of RGB and Flow two-stream sufficiently. Two\ndatasets (UCF-Crime and ShanghaiTech) are used to validate the effectiveness of proposed solution....
Heterogeneous systems have gained popularity due to the rapid growth in data and the need for processing this big data to\nextract useful information. In recent years, many healthcare applications have been developed which use machine learning\nalgorithms to perform tasks such as image classification, object detection, image segmentation, and instance segmentation.\nThe increasing amount of big visual data requires images to be processed efficiently. It is common that we use heterogeneous\nsystems for such type of applications, as processing a huge number of images on a single PC may take months of computation.\nIn heterogeneous systems, data are distributed on different nodes in the system. However, heterogeneous systems\ndo not distribute images based on the computing capabilities of different types of processors in the node; therefore, a slow\nprocessor may take much longer to process an image compared to a faster processor....
With great developments of computing technologies and data mining methods, image annotation has attracted much attraction in\nsmart agriculture. However, the semantic gap between labels and images poses great challenges on image annotation in agriculture,\ndue to the label imbalance and difficulties in understanding obscure relationships of images and labels. In this paper, an image\nannotation method based on graph learning is proposed to accurately annotate images. Specifically, inspired by nearest\nneighbors, the semantic neighbor graph is introduced to generate preannotation, balancing unbalanced labels. Then, the\ncorrelations between labels and images are modeled by the random dot product graph, to deeply mine semantics. Finally, we\nperform experiments on two image sets. The experimental results show that our method is much better than the previous\nmethod, which verifies the effectiveness of our model and the proposed method....
This paper analyzes the problems in image encryption and decryption based\non chaos theory. This article introduces the application of the two-stage Logistic\nalgorithm in image encryption and decryption, then by information entropy\nanalysis it is concluded that the security of this algorithm is higher\ncompared with the original image; And a new image encryption and decryption\nalgorithm based on the combination of two-stage Logistic mapping and\nM sequence is proposed. This new algorithm is very sensitive to keys; the key\nspace is large and its security is higher than two-stage Logistic mapping of\nimage encryption and decryption technology....
Loading....