Video Desnowing and Deraining via Saliency and Dual Adaptive Spatiotemporal Filtering

Outdoor vision sensing systems often struggle with poor weather conditions, such as snow and rain, which poses a great challenge to existing video desnowing and deraining methods. In this paper, we propose a novel video desnowing and deraining model that utilizes the salience information of moving objects to address this problem. First, we remove the snow and rain from the video by low-rank tensor decomposition, which makes full use of the spatial location information and the correlation between the three channels of the color video. Second, because existing algorithms often regard sparse snowflakes and rain streaks as moving objects, this paper injects salience information into moving object detection, which reduces the false alarms and missed alarms of moving objects. At the same time, feature point matching is used to mine the redundant information of moving objects in continuous frames, and a dual adaptive minimum filtering algorithm in the spatiotemporal domain is proposed by us to remove snow and rain in front of moving objects. Both qualitative and quantitative experimental results show that the proposed algorithm is more competitive than other state-of-the-art snow and rain removal methods.

U-Net combined with multi-scale attention mechanism for liver segmentation in CT images

Background The liver is an important organ that undertakes the metabolic function of the human body. Liver cancer has become one of the cancers with the highest mortality. In clinic, it is an important work to extract the liver region accurately before the diagnosis and treatment of liver lesions. However, manual liver segmentation is a time-consuming and boring process. Not only that, but the segmentation results usually varies from person to person due to different work experience. In order to assist in clinical automatic liver segmentation, this paper proposes a U-shaped network with multi-scale attention mechanism for liver organ segmentation in CT images, which is called MSA-UNet. Our method makes a new design of U-Net encoder, decoder, skip connection, and context transition structure. These structures greatly enhance the feature extraction ability of encoder and the efficiency of decoder to recover spatial location information. We have designed many experiments on publicly available datasets to show the effectiveness of MSA-UNet. Compared with some other advanced segmentation methods, MSA-UNet finally achieved the best segmentation effect, reaching 98.00% dice similarity coefficient (DSC) and 96.08% intersection over union (IOU).

Identification of Apple Leaf Diseases by Improved Deep Convolutional Neural Networks With an Attention Mechanism

The accurate identification of apple leaf diseases is of great significance for controlling the spread of diseases and ensuring the healthy and stable development of the apple industry. In order to improve detection accuracy and efficiency, a deep learning model, which is called the Coordination Attention EfficientNet (CA-ENet), is proposed to identify different apple diseases. First, a coordinate attention block is integrated into the EfficientNet-B4 network, which embedded the spatial location information of the feature by channel attention to ensure that the model can learn both the channel and spatial location information of important features. Then, a depth-wise separable convolution is applied to the convolution module to reduce the number of parameters, and the h-swish activation function is introduced to achieve the fast and easy to quantify the process. Afterward, 5,170 images are collected in the field environment at the apple planting base of the Northwest A&F University, while 3,000 images are acquired from the PlantVillage public data set. Also, image augmentation techniques are used to generate an Apple Leaf Disease Identification Data set (ALDID), which contains 81,700 images. The experimental results show that the accuracy of the CA-ENet is 98.92% on the ALDID, and the average F1-score reaches .988, which is better than those of common models such as the ResNet-152, DenseNet-264, and ResNeXt-101. The generated test dataset is used to test the anti-interference ability of the model. The results show that the proposed method can achieve competitive performance on the apple disease identification task.

Intelligent recognition of underground pipeline From GPR image based on Hash algorithm

<p>Ground penetrating radar (GPR) is a high-resolution geophysical non-destructive detection method, which is widely used in near surface target detection, and has been successfully applied in urban construction and geotechnical engineering. In urban life, underground pipelines undertake important missions such as energy transmission and information transmission. As the basic data of smart city, the acquisition of spatial location information of underground pipelines depends on geophysical detection data such as GPR. The traditional recognition and interpretation of  GPR underground pipeline image mainly depends on and is seriously limited by the professional experience of the staff, which is very disadvantageous to the development of large-scale urban underground pipeline survey. To address this problem, according to the GPR reflection image characteristics of isolated targets such as underground pipelines, this paper proposes an intelligent recognition concept of isolated targets in GPR profile based on CBIR (Content-based image retrieval) According to Hash algorithm and improved vector K-means clustering analysis, the intelligent detection, automatic image sorting and recognition of underground pipeline target in GPR profile are realized. Finally, the pipeline material is judged by extracting the image brightness function of the middle trace in the recognition area. The application results of numerical simulation experiments and measured data show that this algorithm can effectively identify the hyperbolic characteristics of the pipeline in the GPR profile, and the identified area can accurately reflect the spatial location of the underground pipeline.</p>

Research on text summarization classification based on crowdfunding projects

In recent years, artificial intelligence technologies represented by deep learning and natural language processing have made huge breakthroughs and have begun to emerge in the field of crowdfunding project analysis. Natural language processing technology enables machines to understand and analyze the text of crowdfunding projects, and classify them based on the summary description of the project, which can help companies and individuals improve the project pass rate, so it has received widespread attention. However, most of the current researches are mostly applied to topic modeling of project texts. Few studies have proposed effective solutions for classification prediction based on abstracts of crowdfunding projects. Therefore, this paper proposes a sequence-enhanced capsule network model for this problem. Specifically, based on the work of the capsule network, we propose to connect BiGRU and CapsNet in order to achieve the effect of considering both the sequence semantic information and spatial location information of the text. We apply the proposed method to the kickstarter-NLP dataset, and the experimental results prove that our model has a good classification effect in this case.

The influence of spatial location on same-different judgments of facial identity and expression

The “spatial congruency bias” is a behavioral phenomenon where two objects presented sequentially are more likely to be judged as being the same object if they are presented in the same location (Golomb et al., 2014), suggesting that irrelevant spatial location information may be bound to object representations. Here, we examine whether the spatial congruency bias extends to higher-level object judgments of facial identity and expression. On each trial, two real-world faces were sequentially presented in variable screen locations, and subjects were asked to make same-different judgments on the facial expression (Experiments 1-2) or facial identity (Experiment 3) of the stimuli. We observed a robust spatial congruency bias for judgements of facial identity, yet a more fragile one for judgements of facial expression. Subjects were more likely to judge two faces as displaying the same expression if they were presented in the same location (compared to in different locations), but only when the faces shared the same identity. On the other hand, a spatial congruency bias was found when subjects made judgements on facial identity, even across faces displaying different facial expressions. These findings suggest a possible difference between the binding of facial identity and facial expression to spatial location.

Spatial Effects of Urban Agglomeration on Energy Efficiency: Evidence from China

The rapid expansion of large cities in China has substantially increased energy consumption. With ever stringent environmental policy in force, energy efficiency becomes an important issue. As the emergence of these urban agglomerations (UAs) is usually due to externality effects of spatially concentrated factors, this paper investigates how these factors can affect energy efficiency. Based on mono index, which is used to describe the spatial location information, we have constructed the spatial-structure index of UAs. Using panel data on ten major UAs in China from 2008 to 2017, we find that, in the whole sample, there is an inverse relationship between the spatial structure of UAs and energy efficiency: The higher the concentration degree of factors of UAs, the lower the energy efficiency. Across different regions, however, the relationship between spatial structure and energy efficiency is heterogeneous. The concentration degree of factors in the eastern and central regions of China is relatively high, and the spatial structure there does lead to a decrease in energy efficiency. By contrast, UAs in China’s western region are in a period of factor concentration, with spatial structure playing, in that region, a positive role in improving energy efficiency.

Robust visual tracking via samples ranking

In recent years, deep convolutional neural networks (CNNs) have achieved great success in visual tracking. To learn discriminative representations, most of existing methods utilize information of image region category, namely target or background, and/or of target motion among consecutive frames. Although these methods demonstrated to be effective, they ignore the importance of the ranking relationship among samples, which is able to distinguish one positive sample better than another positive one or not. This is especially crucial for visual tracking because there is only one best target candidate among all positive candidates, which tightly bounds the target. In this paper, we propose to take advantage of the ranking relationship among positive samples to learn more discriminative features so as to distinguish closely similar target candidates. In addition, we also propose to make use of the normalized spatial location information to distinguish spatially neighboring candidates. Extensive experiments on challenging image sequences demonstrate the effectiveness of the proposed algorithm against several state-of-the-art methods.