Human pose estimation localizes body keypoints to accurately recognizing the postures of individuals given an image. This step is a crucial prerequisite to multiple tasks of computer vision which ...include human action recognition, human tracking, human-computer interaction, gaming, sign languages, and video surveillance. Therefore, we present this survey article to fill the knowledge gap and shed light on the researches of 2D human pose estimation. A brief introduction is followed by classifying it as a single or multi-person pose estimation based on the number of people needed to be tracked. Then gradually the approaches used in human pose estimation are described before listing some applications and also flaws facing in pose estimation. Following that, a center of attention is given on briefly discussing researches with a significant effect on human pose estimation and examine the novelty, motivation, architecture, the procedures (working principles) of each model together with its practical application and drawbacks, datasets implemented, as well as the evaluation metrics used to evaluate the model. This review is presented as a baseline for newcomers and guides researchers to discover new models by observing the procedure and architecture flaws of existing researches.
•Real time semantic segmentation for road scene understanding.•Follow two branch network strategy.•Utilize dilated spatial attention and channel attention.•Use supervision to ease the loss ...propagation.
Efficient and accurate semantic segmentation is particularly important in scene understanding for autonomous driving. Although Deep Convolutional Neural Networks(DCNNs) approaches have made a significant improvement for semantic segmentation. However, state-of-the-art models such as Deeplab and PSPNet have complex architectures and high computation complexity. Thus, it is inefficient for realtime applications. On the other hand, many works compromise the performance to obtain real-time inference speed which is critical for developing a light network model with high segmentation accuracy. In this paper, we present a computationally efficient network named DSANet, which follows a two-branch strategy to tackle the problem of real-time semantic segmentation in urban scenes. We first design a Semantic Encoding Branch, which employs channel split and shuffle to reduce the computation and maintain higher segmentation accuracy. Also, we propose a dual attention module consisting of dilated spatial attention and channel attention to make full use of the multi-level feature maps simultaneously, which helps predict the pixel-wise labels in each stage. Meanwhile, Spatial Encoding Network is used to enhance semantic information and preserve the spatial details. To better combine context information and spatial information, we introduce a Simple Feature Fusion Module. We evaluated our model with state-of-the-art semantic image semantic segmentation methods using two challenging datasets. The proposed method achieves an accuracy of 69.9% mean IoU and 71.3% mean IoU at speed of 75.3 fps and 34.08 fps on CamVid and Cityscapes test datasets respectively.
Food is essential for human life and has been the concern of many healthcare conventions. Nowadays new dietary assessment and nutrition analysis tools enable more opportunities to help people ...understand their daily eating habits, exploring nutrition patterns and maintain a healthy diet. In this paper, we develop a deep model based food recognition and dietary assessment system to study and analyze food items from daily meal images (e.g., captured by smartphone). Specifically, we propose a three-step algorithm to recognize multi-item (food) images by detecting candidate regions and using deep convolutional neural network (CNN) for object classification. The system first generates multiple region of proposals on input images by applying the Region Proposal Network (RPN) derived from Faster R-CNN model. It then indentifies each region of proposals by mapping them into feature maps, and classifies them into different food categories, as well as locating them in the original images. Finally, the system will analyze the nutritional ingredients based on the recognition results and generate a dietary assessment report by calculating the amount of calories, fat, carbohydrate and protein. In the evaluation, we conduct extensive experiments using two popular food image datasets - UEC-FOOD100 and UEC-FOOD256. We also generate a new type of dataset about food items based on FOOD101 with bounding. The model is evaluated through different evaluation metrics. The experimental results show that our system is able to recognize the food items accurately and generate the dietary assessment report efficiently, which will benefit the users with a clear insight of healthy dietary and guide their daily recipe to improve body health and wellness.
Multiple sclerosis is a severe brain and/or spinal cord disease. It may lead to a wide range of symptoms. Hence, the early diagnosis and treatment is quite important.
This study proposed a 14-layer ...convolutional neural network, combined with three advanced techniques: batch normalization, dropout, and stochastic pooling. The output of the stochastic pooling was obtained via sampling from a multinomial distribution formed from the activations of each pooling region. In addition, we used data augmentation method to enhance the training set. In total 10 runs were implemented with the hold-out randomly set for each run.
The results showed that our 14-layer CNN secured a sensitivity of 98.77 ± 0.35%, a specificity of 98.76 ± 0.58%, and an accuracy of 98.77 ± 0.39%.
Our results were compared with CNN using maximum pooling and average pooling. The comparison shows stochastic pooling gives better performance than other two pooling methods. Furthermore, we compared our proposed method with six state-of-the-art approaches, including five traditional artificial intelligence methods and one deep learning method. The comparison shows our method is superior to all other six state-of-the-art approaches.
•Groundwater table rising reduced nitrate concentration, while falling aggravated it.•Bacterial biomarkers and functional genes were identified during N transformation.•Groundwater table fluctuation ...affected N transformation mainly in indirectly paths.
Groundwater table fluctuation alters the biochemical environment and nitrogen transformation, leading to periodic changes in groundwater nitrate concentration. A microcosm experiment of groundwater table fluctuation was designed to explore the underlying mechanism. The dissolved oxygen (DO), bacterial community, functional gene groups and associated nitrogen transformation were investigated based on field scenario. The results showed that groundwater rising reduced the average nitrate concentration, while falling aggravated it. Owing to the variations in groundwater table, the DO concentration underwent periodic changes. Furthermore, the abundance and diversity of soil bacteria were enriched and the structure of the microbial community was altered. Nitrogen transformation biomarkers such as Arthrobacter sp., Bacillus sp., Chloroflexi sp. and Acidobacteriota sp. as well as nitrogen transformation functional genes were identified. A structure equation model was established which demonstrated that groundwater table fluctuation altered DO and the dominant bacterial abundance, which in turn modified the functional gene groups and nitrogen transformation. This study broadens the understanding of how and to what extent groundwater table fluctuation affects nitrogen transformation and is vital for assessing and managing risks associated with groundwater nitrate contamination
Early fault detection and diagnosis can increase the stability, reliability and safety of manufacturing equipment. It can be used for protection against unforeseen emergencies in manufacturing ...system. Recently, fault diagnosis (FD) methods based on deep learning (DL) have become a research hotspot for their excellent performance. However, the training process of deep learning (DL) models is time-consuming because of their high computation complexity. Moreover, most of DL-based FD methods have an assumption the distribution of training datasets in the source domain is the same as that of test datasets in the target domain. However, it is impossible in typical real-world manufacturing applications. In order to cope with these two problems, this paper proposes a FD method based on convolutional neural network (CNN) and transfer learning (TL). Firstly, a CNN model based on LeNet-5 is designed to extract fault features from images which is converted from raw signal data by continuous wavelet transform (CWT), then the performance of the CNN model are improved by fine-tuning which is an effective way of TL. The proposed method is conducted on two well-known datasets and the experimental results show that the proposed method can significantly improve the accuracy and efficiency performance a lot compared with the standard CNN model.
Coronary artery disease remains a leading cause of mortality among individuals with cardiovascular conditions. The therapeutic use of bioresorbable vascular scaffolds (BVSs) through stent ...implantation is common, yet the effectiveness of current BVS segmentation techniques from Intravascular Optical Coherence Tomography (IVOCT) images is inadequate.Background and ObjectiveCoronary artery disease remains a leading cause of mortality among individuals with cardiovascular conditions. The therapeutic use of bioresorbable vascular scaffolds (BVSs) through stent implantation is common, yet the effectiveness of current BVS segmentation techniques from Intravascular Optical Coherence Tomography (IVOCT) images is inadequate.This paper introduces an enhanced segmentation approach using a novel Wavelet-based U-shape network to address these challenges. We developed a Wavelet-based U-shape network that incorporates an Attention Gate (AG) and an Atrous Multi-scale Field Module (AMFM), designed to enhance the segmentation accuracy by improving the differentiation between the stent struts and the surrounding tissue. A unique wavelet fusion module mitigates the semantic gaps between different feature map branches, facilitating more effective feature integration.MethodsThis paper introduces an enhanced segmentation approach using a novel Wavelet-based U-shape network to address these challenges. We developed a Wavelet-based U-shape network that incorporates an Attention Gate (AG) and an Atrous Multi-scale Field Module (AMFM), designed to enhance the segmentation accuracy by improving the differentiation between the stent struts and the surrounding tissue. A unique wavelet fusion module mitigates the semantic gaps between different feature map branches, facilitating more effective feature integration.Extensive experiments demonstrate that our model surpasses existing techniques in key metrics such as Dice coefficient, accuracy, sensitivity, and Intersection over Union (IoU), achieving scores of 85.10%, 99.77%, 86.93%, and 73.81%, respectively. The integration of AG, AMFM, and the fusion module played a crucial role in achieving these outcomes, indicating a significant enhancement in capturing detailed contextual information.ResultsExtensive experiments demonstrate that our model surpasses existing techniques in key metrics such as Dice coefficient, accuracy, sensitivity, and Intersection over Union (IoU), achieving scores of 85.10%, 99.77%, 86.93%, and 73.81%, respectively. The integration of AG, AMFM, and the fusion module played a crucial role in achieving these outcomes, indicating a significant enhancement in capturing detailed contextual information.The introduction of the Wavelet-based U-shape network marks a substantial improvement in the segmentation of BVSs in IVOCT images, suggesting potential benefits for clinical practices in coronary artery disease treatment. This approach may also be applicable to other intricate medical imaging segmentation tasks, indicating a broad scope for future research.ConclusionThe introduction of the Wavelet-based U-shape network marks a substantial improvement in the segmentation of BVSs in IVOCT images, suggesting potential benefits for clinical practices in coronary artery disease treatment. This approach may also be applicable to other intricate medical imaging segmentation tasks, indicating a broad scope for future research.
Pure high impact polystyrene (HIPS) is widely used, but it is flammable. During combustion, it produces black smoke, drips, and poses other hazards to human safety, making it necessary to study ...flame-retardant HIPS. In this study, nitrogen-phosphorus-silicon flame retardants were prepared by using melamine cyanurate (MC), aluminum hypophosphite (ALHP), and nano-silica (nano-SiO2) to improve the flame retardancy of HIPS. The flame retardancy and mechanism of HIPS composites were studied. The results showed that when the ratio of MC to ALHP was 1:4 and nano-SiO2 was 1.5 wt%, the limiting oxygen index (LOI) value of HIPS composite was 26.9%, and PHRR and THR were reduced to 254 kW/m2 and 85 MJ/m2, respectively. The smoke production decreased by 32%, and the carbon residue increased by 70%. ALHP and nano-SiO2 mainly play a flame retardant role in the condensed phase. MC mainly plays a flame retardant role in the gas phase, as well as the condensed phase.
Display omitted
•The filling amount was lower than single silicon flame retardant.•The efficiency was higher than single nitrogen flame retardant.•The carbonization effect was better than single phosphorus flame retardant.•MC, ALHP, and nano-SiO2 were compounded and added to HIPS for the first time.•The flame retardant composite is an environmentally friendly material.
Plant basic/helix-loop-helix (bHLH) transcription factors participate in a number of biological processes, such as growth, development and abiotic stress responses. The bHLH family has been ...identified in many plants, and several bHLH transcription factors have been functionally characterized in Arabidopsis. However, no systematic identification of bHLH family members has been reported in potato (Solanum tuberosum). Here, 124 StbHLH genes were identified and named according to their chromosomal locations. The intron numbers varied from zero to seven. Most StbHLH proteins had the highly conserved intron phase 0, which accounted for 86.2% of the introns. According to the Neighbor-joining phylogenetic tree, 259 bHLH proteins acquired from Arabidopsis and potato were divided into 15 groups. All of the StbHLH genes were randomly distributed on 12 chromosomes, and 20 tandem duplicated genes and four pairs of duplicated gene segments were detected in the StbHLH family. The gene ontology (GO) analysis revealed that StbHLH mainly function in protein and DNA binding. Through the RNA-seq and quantitative real time PCR (qRT-PCR) analyses, StbHLH were found to be expressed in various tissues and to respond to abiotic stresses, including salt, drought and heat. StbHLH1, 41 and 60 were highly expressed in flower tissues, and were predicted to be involved in flower development by GO annotation. StbHLH45 was highly expressed in salt, drought and heat stress, which suggested its important role in abiotic stress response. The results provide comprehensive information for further analyses of the molecular functions of the StbHLH gene family.
Traditional Chinese state sacrificial ritual represented a symbolic system of integrating religious belief, divine authority, and political legitimacy. The Northern Stronghold (Beizhen 北鎮, i.e., ...Mount Yiwulü 醫巫閭山) was equal in status to the other four strongholds, which, moreover, served as a strategic military fortress and represented the earth virtue in the early state sacrifice system. In the late imperial era of China, and during the Yuan (1279–1368) and Qing (1644–1911) dynasties in particular, the Northern Stronghold swiftly achieved prominence and eventually became an instrument used by minority ethnic groups, namely the Mongolians and Manchus, when elaborating upon the legitimacy of their political regimes. During the Yuan dynasty, the mountain spirits of the five strongholds (Wuzhen 五鎮) were formally invested as kings and, as a result, were accorded equivalent sacrifices in comparison to those given to the five sacred peaks (Wuyue 五嶽). Given that the Northern Stronghold was located near the northeast of Beijing, the Yuan government considered it the foundation of the state. Thereafter, the Northern Stronghold was regarded as the most important of the five stronghold mountains. In the Ming dynasty (1368–1644), the Northern Stronghold Temple (Beizhenmiao 北鎮廟) was reconstructed as both a military fortress and religious site, while its representation as a significant site for a foreign conquest dynasty diminished and its significance as a bastion of anti-insurgent suppression emerged. By the Qing dynasty, the Northern Stronghold was regarded as an integral component of the geographic origin of the Manchu people and thereby assumed once again a position of substantial political significance. Several Qing emperors visited the Northern Stronghold and left poems and prose written in graceful Chinese to present their high respect and their mastery of Chinese culture. The history of the Northern Stronghold demonstrates how the ethnic minority regimes successfully utilized the traditional Chinese state sacrificial ritual to serve their political purpose.