Meili Wang's research while affiliated with Northwest A & F University and other places

Publications (61)

Preprint
In-place gesture-based virtual locomotion techniques enable users to control their viewpoint and intuitively move in the 3D virtual environment. A key research problem is to accurately and quickly recognize in-place gestures, since they can trigger specific movements of virtual viewpoints and enhance user experience. However, to achieve real-time e...
Preprint
Full-text available
Transformer-based Self-supervised Representation Learning methods learn generic features from unlabeled datasets for providing useful network initialization parameters for downstream tasks. Recently, self-supervised learning based upon masking local surface patches for 3D point cloud data has been under-explored. In this paper, we propose masked Au...
Article
As the generation of realistic bas‐relief models from 2D images suffers from insufficient 3D depth information and severe under‐constraint, in this article, we propose a new framework for bas‐relief modeling based on 2D decorative images, which adopts conditional generative adversarial network to infer the normal information of the decorative bas‐r...
Article
Facial recognition technology and related research have matured over time, but research in the field of individual animal recognition is still very limited. Therefore, this article focuses on the identification of cashmere goats with similar characteristics. First, the single shot multibox detector network was used to process the dataset. Next, tra...
Article
In recent years, artificial intelligence has been widely used in such fields as agricultural informatization, precision agriculture and precision animal husbandry. Due to limited research on deep learning in real-time agricultural and pastoral situations, deep learning and computer vision have become very important topics in the agricultural field....
Article
Full-text available
In response to rapidly changing market and customer needs, product design and development (PDD) is evolving into a human-centred and data-driven design paradigm. The design environment gets more open often involving crowdsourcing and the design process becomes more complex, considering product family design along product whole lifecycle development...
Preprint
Full-text available
As a popular representation of 3D data, point cloud may contain noise and need to be filtered before use. Existing point cloud filtering methods either cannot preserve sharp features or result in uneven point distribution in the filtered output. To address this problem, this paper introduces a point cloud filtering method that considers both point...
Article
Existing position based point cloud filtering methods can hardly preserve sharp geometric features. In this paper, we rethink point cloud filtering from a non-learning non-local non-normal perspective, and propose a novel position based approach for feature-preserving point cloud filtering. Unlike normal based techniques, our method does not requir...
Preprint
Existing position based point cloud filtering methods can hardly preserve sharp geometric features. In this paper, we rethink point cloud filtering from a non-learning non-local non-normal perspective, and propose a novel position based approach for feature-preserving point cloud filtering. Unlike normal based techniques, our method does not requir...
Preprint
(see PDF here: https://arxiv.org/abs/2110.06632) Though a number of point cloud learning methods have been proposed to handle unordered points, most of them are supervised and require labels for training. By contrast, unsupervised learning of point cloud data has received much less attention to date. In this paper, we propose a simple yet effective...
Article
Malus micromalus Makino has great commercial and nutritional value. The regression and classification models were investigated by using near-infrared hyperspectral imaging (NIR-HSI) combined with chemometrics to improve the efficiency of non-destructive detection. The successive projections algorithm (SPA), interval random frog, and competitive ada...
Preprint
Walking in place for moving through virtual environments has attracted noticeable attention recently. Recent attempts focused on training a classifier to recognize certain patterns of gestures (e.g., standing, walking, etc) with the use of neural networks like CNN or LSTM. Nevertheless, they often consider very few types of gestures and/or induce l...
Article
It is significant to achieve automatic arrangement for bas-relief layout which can be noticeably more efficient than the time-consuming manual process. In fact, nearly none work has been reported in terms of bas-relief layout arrangement. In this paper, we propose a novel approach to tackle this problem. Specifically, we first identify the evaluati...
Article
Full-text available
The fast and accurate identification of apple leaf diseases is beneficial for disease control and management of apple orchards. An improved network for apple leaf disease classification and a lightweight model for mobile terminal usage was designed in this paper. First, we proposed SE-DEEP block to fuse the Squeeze-and-Excitation (SE) module with t...
Preprint
Full-text available
In the era of Industry 4.0, in response to rapidly changing market and customer needs, product design and development (PDD) is evolving into a human-centred and data-driven design paradigm. The design environment gets more open often involving crowdsourcing and the design process becomes more complex, considering product family design along product...
Article
For surgery simulation application, a high‐quality anatomical model is very important not only for rendering but also for physics simulation. CT and MRI reconstructed model has no surface parameterization attribute so texture‐based materials cannot be applied for rendering. Anatomical models on the digital market are efficient options but most can...
Article
Full-text available
The gut microbiota composition is influenced by the diet as well as the environment in both wild and domestic animals. We studied the effects of two feeding systems on the rumen and hindgut microbiome of semi-feral Tibetan goats kept at high altitude (∼4800 m) using 16S rRNA gene and metagenomic sequencing. Intensive drylot feeding resulted in sign...
Article
Full-text available
In this paper, we make two contributions. The first is to propose a new keyframe extraction algorithm, which reduces the keyframe redundancy and reduces the motion sequence reconstruction error. Secondly, a new motion sequence reconstruction method is proposed, which further reduces the error of motion sequence reconstruction. Specifically, we trea...
Conference Paper
Full-text available
Keyframes extraction, a fundamental problem in video processing and analysis, has remained a challenge to date. In this paper, we introduce a novel method to effectively extract keyframes of a video. It consists of four steps. At first, we generate initial clips for the classified frames, based on consistent content within a clip. Using empirical e...
Chapter
We present a novel method for extracting highlights from a badminton video. Firstly, we classify the different views of badminton videos for video segmentation through building classification model based on transfer learning, and achieve high-precision with real-time segmentation. Secondly, based on object detection by the object detecting model YO...
Article
Detail-and-geometry richness is essential to bas-relief modelling. However, existing image-based and model-based bas-relief modelling techniques commonly suffer from detail monotony or geometry loss. In this paper, we introduce a new bas-relief modelling framework for detail abundance with visual attention based mask generation and geometry preserv...
Preprint
Full-text available
Background: The gut microbiota composition is influenced by the diet as well as the environment in both wild and domestic animals. Although the rumen microbiome in herbivorous ruminants has been studied intensively, there is a lack of data regarding the simultaneous adaption of the rumen and hindgut metagenome as affected by different feeding syste...
Article
Full-text available
In order to realize anti-damage bud and automatic cutting of sugarcane in a single bud segment, a sugarcane cutting system based on machine vision is designed. The seed cutting system includes a mechanical part, electrical part, and visual processing part. The core of the system uses machine vision to identify the segments of sugarcane stalks. The...
Article
Full-text available
To investigate the feasibility of using near-infrared (NIR) spectral technology to detect the soluble solids content (SSC) of Malus micromalus Makino, rapid and non-destructive prediction models of SSC were studied using least-square support vector regression (LS-SVR), partial least squares regression (PLSR), and the error back propagation artifici...
Chapter
Full-text available
Sugarcane node identification is the key techniques for sugarcane cultivation mechanization. The accurate position of nodes that link two consecutive sections should be detected and transferred to microcontroller for cutting. However, current research fails to identify the sugarcane nodes for different kinds of sugarcanes and especially for those u...
Chapter
The rise of skeletal skinning technology has provided great convenience for animators. At the same time, it improves the efficiency of animation production. However, the deformation resulting from this technology suffers from some undesirable effects, which require manual improvement. In this paper, we propose an approach addressing the problem of...
Conference Paper
3D point cloud hole repairing is an important operation for generating a complete model. In this paper, we present a point cloud hole repairing method based on boundary rejection algorithm. This algorithm repairs the hole by pushing the boundary points into the hole region with the repulsive force from the adjacent points. Firstly, we select the bo...
Conference Paper
The efficiency in perception of 3D scenes is a significant problem. This paper presents a novel viewpoint evaluation method combining geometric and visual perception information. Firstly, we generalize the criteria of the best viewpoint selection from the references. Then, we introduce a dynamic inertia weight and Multi-start PSO algorithm into ori...
Article
Full-text available
Human motion prediction is a challenging problem due to the complicated human body constraints and high-dimensional dynamics. Recent deep learning approaches adopt RNN, CNN or fully connected networks to learn the motion features which do not fully exploit the hierarchical structure of human anatomy. To address this problem, we propose a convolutio...
Article
Full-text available
Many art forms present visual content as a single image captured from a particular viewpoint. How to select a meaningful representative moment from an action performance is difficult, even for an experienced artist. Often, a well-picked image can tell a story properly. This is important for a range of narrative scenarios, such as journalists report...
Article
Full-text available
Sunken relief is an art form whereby the depicted shapes are sunk into a given flat plane with a shallow overall depth. In this paper, we propose an efficient sunken relief generation algorithm based on a single image by the technique of feature line enhancement. Our method starts from a single image. First, we smoothen the image with morphological...
Article
Full-text available
Raw point cloud data is often noisy, superfluous and with topological defects, such as holes. These issues cause inaccurate geometric representation in 3D reconstruction. As a result, surface reconstruction from point cloud data is a highly challenging problem. In this paper, we address the aforementioned issues by taking advantage of the embedded...
Article
Full-text available
Small and medium-sized enterprises face the challenges that they do not have enough employees and related resources to produce high-quality products with limited budget and time. The emergence of crowdsourcing provides an opportunity for them to improve their products by leveraging the wisdom of a large community of crowds, including their potentia...
Article
Full-text available
The improvement of resolution of digital elevation models (DEMs) and the increasing application of the Revised Universal Soil Loss Equation (RUSLE) over large areas have created problems for the efficiency of calculating the LS factor for large data sets. The pretreatment for flat areas, flow accumulation, and slope-length calculation have traditio...
Article
This paper proposes a novel method of optimizing locomotion controller for virtual characters, which is constructed with the deep neural network and learned with the assistance of existing motion data. The learning is accomplished with a progressive reward function by starting from a simple reward function and gradually imposing advanced requiremen...
Article
This paper presents a novel approach for bas‐relief generation and synthesis. In contrast to previous methods, we divide this problem into two parts: the selection of the best view and arrangement of the relief layout. Taking these into account, we incorporate the visual saliency and photographic composition rules into the bas‐relief generation. Ad...
Article
Full-text available
The segmentation of a point cloud is one of the key technologies for three-dimensional reconstruction, and the segmentation from three-dimensional views can facilitate reverse engineering. In this paper, we propose a self-adaptive segmentation algorithm, which can address challenges related to the region-growing algorithm, such as inconsistent or e...
Conference Paper
Sunken relief is an art form whereby the depicted shapes are sunk into a given flat plane with a shallow overall depth. In this paper, we propose a sunken relief generation algorithm based on a single image. Our method starts from a single image. First, we smoothen the image with morphological operations such as opening and closing operations and e...
Article
Full-text available
In light of the current problems including coarseness, visible cracks, difficult data organisation, and the expensive memory requirements of the current texture methods, this paper mainly focuses on efficient organisation, linearised memory compression and seamless texture mapping between scanned Citrus sinensis images and point cloud information....
Conference Paper
This paper aims to automate the process of generating a meaningful single still image from a temporal input of scene sequences. The success of our extraction relies on evaluating the optimal pose of characters selection, which should maximize the information conveyed. We define the information entropy of the still image candidates as the evaluation...
Conference Paper
The representation of detail is an essential part of animation. However, realistically and efficiently simulating details of folds and wrinkles in cloth has always been a huge challenge. Although the position-based dynamics method can simplify and generally depict details, grids are so fine that the simulation frame is far from satisfactory. The hi...
Conference Paper
In recent years, one of the most noticeable“” issues of current animation production is the challenge from the exponential growth of animation data known as an increasingly data-intensive process. There are obvious gaps between the animation production needs and research development, which call for novel design and new technology to tackle the emer...
Article
This paper simulates the behaviour of collective transport where a group of ants transports an object in a cooperative fashion. Different from humans, the task coordination of collective transport, with ants, is not achieved by direct communication between group individuals, but through indirect information transmission via mechanical movements of...
Conference Paper
As a key technology, interactive animation has been widely used in Virtual Reality nowadays which is important for the success of various VR applications. However, despite many years history and the ability to produce stunning illusory and immersive effects for many VR applications, interactive animation generation remains one of the most labour-in...
Article
It is difficult to extend image-based relief generation to high-relief generation, as the images contain insufficient height information. To generate reliefs from three-dimensional (3D) models, it is necessary to extract the height fields from the model, but this can only generate bas-reliefs. To overcome this problem, an efficient method is propos...
Article
Although current 3D scanner technology can acquire textural images from a point model, visible seams in the image, inconvenient data acquisition and occupancy of a large space during use are points of concern for outdoor fruit models. In this paper, an SPSDW (simplification and perception based subdivision followed by down-sampling weighted average...
Article
With the development of virtual reality technology, surgery simulation has become an effective way to train the operation skills for surgeons. Soft tissue dissection, as one of the most frequently performed operations in surgery, is indispensable to an immersive and high-fidelity surgery simulator. Energized dissection tools are much more commonly...
Article
Full-text available
Semi-supervised clustering algorithms are increasingly employed for discovering hidden structure in data with partially labelled patterns. In order to make the clustering approach useful and acceptable to users, the information provided must be simple, natural and limited in number. To improve recognition capability, we apply an effective feature e...
Conference Paper
Wheat diseases are harmful to wheat production, but there are few segmentation algorithms that can effectively identify common diseases of wheat leaves. This paper proposes an automatic and efficient solution with K-means clustering. Firstly, the colour image is transformed to Lab colour space from RGB. Clustering is then done by taking the absolut...
Article
Full-text available
Relief is a special art form that differs from painting and other round sculpture, and is traditionally created by laborious hand carving. Existing methods for digital relief generation focus on direct geometric compression, which transforms a three-dimensional (3D) mesh into a detail-preserving surface with a shallow depth, indicating the presence...
Article
Full-text available
Sunken relief is a special art form of sculpture whereby the depicted shapes are sunk into a given surface. This is traditionally created by laboriously carving materials such as stone. Sunken reliefs often utilize the engraved lines or strokes to strengthen the impressions of a 3D presence and to highlight the features which otherwise are unreveal...
Article
Full-text available
Digital reliefs mimic the style of their real life counterparts, and hence offer an elegant depiction of a 3D shape. Despite an increasing amount of research on digital relief generation in computer graphics, little has been reported on the generation of abstract sculpture forms using pure engraved lines. In this paper, we present a method to creat...
Article
This paper reports the development of digital relief generation over recent years. Relief generation techniques are classified into three types, image-based techniques, direct modeling techniques, and those by transforming 3D shapes into reliefs. This work aims to assist artists and designers to develop an in-depth understanding of current state of...

Citations

... In addition, use of sensors also causes additional costs. Recently, livestock action recognition combines visual object detection with image classification, and has been the subject of increased interest in the fields of computer vision and smart agriculture [2], [3]. ...
... Among them, sparse optimization methods, such as [9], [21], [22], [23], are more effective in preserving geometric features (especially for sharp features), based on the prior that geometric features are sparse over underlying surfaces. Recently, using the self-similarity characteristics of underlying surfaces, low-rank and dictionary learning techniques [6], [8], [24], [25], [26] have received attention for providing structural repetition preservation of underlying surfaces. Although optimization-based methods have advantages in preserving some kinds of geometric features, geometric priors may downgrade their performance in preserving other kinds of geometric features. ...
... In small or cluttered rooms, users can only move safely in a small restricted area or stay in place, hence many studies have focused on in-place gestures for virtual locomotion such as walking in place (WIP) [18,39,44,49], jumping [22,46], body leaning [6], arm swinging [33], etc. These in-place gesture-based locomotion methods concentrate on recognizing specific pre-defined gesture patterns from motion sequence data collected by motion capture sensors (i.e., HMDs, trackers, etc.) with low latency and high accuracy, for controlling the direction and speed of virtual locomotion. ...
... The conceptualisation of the information model is based on standards such as ISO 10303 and IEC 62264. Another recent work [10] can contribute significantly to these efforts, through the elaborated product design lifecycle information model that they propose. More specifically, product traceability landscape can be heterogeneous, and thereby requires multiple technologies (QR Code, barcode, RFID) which make traceability integration very complex. ...
... To test this further, we evaluated the preservative effect of CMs on peaches by detecting freshness parameters including SSC and TA. The SSC of peach fruit was measured by a refractometer (Rudolph, New York, USA) as described by Gao et al. 32 Peach fruit (20 g) was mashed for 5 min at speed of 5000 rpm. The homogenate was filtered by gauze, and two drops were put on the central prism of the refractometer. ...
... The idea of ViT was introduced by [17]. We compare the proposed framework with various handcrafted feature extraction such as histogram of oriented gradient (HOG) [18], locally encoded transform feature histogram (LETRIST) [19], local binary pattern (LBP) [20], gray level co-occurrence matrix (GLCM) [21], non-redundant local binary pattern (NRLBP) [22], completed joint-scale local binary pattern (CJLBP) [23], local tetra pattern (LTrP) [24], and D-CNN models, such as AlexNet [25], ShuffleNet [26], ResNet-50 [27], SqueezeNet [28], MobileNet-v2 [29], Inceptionv3 [30], GoogleNet [31], EfficientNetb0 [32], Inception-ResNet-v2 [33], DarkNet-53 [34] and Xception [35]. We also compare the feature extractions' performance with several classifiers, such as support vector machine [36,37], decision tree, k-nearest neighbors, ensemble, Naive Bayes, multi-layer perceptron (MLP) [38,39], radial basis function (RBF) and group method of data handling (GMDH). ...
... W. Chen et al. 2021), and Diaspididae (J. W. Chen et al. 2021), livestock detection such as pig (Shudong et al. 2021) and cattle (Feng, Zhao and Wang 2021), and aquaculture (Prasetyo, Suciati and Fatichah 2021;Xuelong et al. 2021). Aside from directly applying the original YOLOv4 algorithm, in the reviewed studies researchers have also made various modifications to YOLOv4 for model performance improvement, such as integrating a non-local attention module or a convolutional block attention model (Jiang et al. 2021;Yang et al. 2021), combining with a background separation model (Bai et al. 2021), changing to a different backbone (Ying et al. 2021), channel or layer pruning (W. ...
... However, they are not flexible concerning the usage of the patient case and training scenarios. The cutting simulation can be further improved with realistic haptic feedback and recent techniques of physics-based simulations, e.g., finite element method (FEM) [287][288][289] and PBD [104,290,291]. The FEM has been used in soft-tissue modeling and interactions with high precision and deformation flexibility [292,293]. ...
... Shen et al. (2020) studied caprine microbiota using metagenomics to identify and characterize the ciliate fauna profile, identify the factors which influence rumen quality, and analyze the functional categories of genes in the degradation of different diets. Other omics (metabolomics, transcriptomics, and proteomics) have been equally employed in the studies with goats for different goals, including verifying the influence of diets on the microbiota, verifying the effects of food restriction on the microbiota, and evaluating the changes in protein expression (Mao et al. 2016;Abecia et al. 2018;Guo et al. 2019;Zhang et al. 2019;Wang et al. 2020;Parreira et al. 2020;Zhang et al. 2021). ...
... Miura et al. [12] first performed principal com-ponent analysis on the motion data and then simplified the principal component curves to extract key frames. Xu et al. [13] extended the binomial fitting to obtain the points on the motion curve where the slope changes dramatically in their vicinity. Then they took these points as inputs to obtain keyframes by density clustering. ...