scholarly journals Spectrum- and RGB-D-Based Image Fusion for the Prediction of Nitrogen Accumulation in Wheat

2020 ◽  
Vol 12 (24) ◽  
pp. 4040
Author(s):  
Ke Xu ◽  
Jingchao Zhang ◽  
Huaimin Li ◽  
Weixing Cao ◽  
Yan Zhu ◽  
...  
Keyword(s):  
Structural Information ◽  
Spectral Characteristics ◽  
Canopy Structure ◽  
Growth Period ◽  
Accurate Estimation ◽  
Depth Information ◽  
Nitrogen Accumulation ◽  
Hole Filling ◽  
Depth Images ◽  
Mean Square Errors

The accurate estimation of nitrogen accumulation is of great significance to nitrogen fertilizer management in wheat production. To overcome the shortcomings of spectral technology, which ignores the anisotropy of canopy structure when predicting the nitrogen accumulation in wheat, resulting in low accuracy and unstable prediction results, we propose a method for predicting wheat nitrogen accumulation based on the fusion of spectral and canopy structure features. After depth images are repaired using a hole-filling algorithm, RGB images and depth images are fused through IHS transformation, and textural features of the fused images are then extracted in order to express the three-dimensional structural information of the canopy. The fused images contain depth information of the canopy, which breaks through the limitation of extracting canopy structure features from a two-dimensional image. By comparing the experimental results of multiple regression analyses and BP neural networks, we found that the characteristics of the canopy structure effectively compensated for the model prediction of nitrogen accumulation based only on spectral characteristics. Our prediction model displayed better accuracy and stability, with prediction accuracy values (R2) based on BP neural network for the leaf layer nitrogen accumulation (LNA) and shoot nitrogen accumulation (SNA) during a full growth period of 0.74 and 0.73, respectively, and corresponding relative root mean square errors (RRMSEs) of 40.13% and 35.73%.

scholarly journals Recognition of Symbolic Gestures Using Depth Information

2018 ◽  
Vol 2018 ◽  
pp. 1-13 ◽  
Author(s):  
Hasan Mahmud ◽  
Md. Kamrul Hasan ◽  
Abdullah-Al-Tariq ◽  
Md. Hasanul Kabir ◽  
M. A. Mottalib
Keyword(s):  
Contextual Information ◽  
Depth Map ◽  
Recognition System ◽  
Support Vector ◽  
Svm Classifier ◽  
Depth Information ◽  
Scale Invariant ◽  
Binary Images ◽  
Depth Images ◽  
Symbolic Gestures

Symbolic gestures are the hand postures with some conventionalized meanings. They are static gestures that one can perform in a very complex environment containing variations in rotation and scale without using voice. The gestures may be produced in different illumination conditions or occluding background scenarios. Any hand gesture recognition system should find enough discriminative features, such as hand-finger contextual information. However, in existing approaches, depth information of hand fingers that represents finger shapes is utilized in limited capacity to extract discriminative features of fingers. Nevertheless, if we consider finger bending information (i.e., a finger that overlaps palm), extracted from depth map, and use them as local features, static gestures varying ever so slightly can become distinguishable. Our work here corroborated this idea and we have generated depth silhouettes with variation in contrast to achieve more discriminative keypoints. This approach, in turn, improved the recognition accuracy up to 96.84%. We have applied Scale-Invariant Feature Transform (SIFT) algorithm which takes the generated depth silhouettes as input and produces robust feature descriptors as output. These features (after converting into unified dimensional feature vectors) are fed into a multiclass Support Vector Machine (SVM) classifier to measure the accuracy. We have tested our results with a standard dataset containing 10 symbolic gesture representing 10 numeric symbols (0-9). After that we have verified and compared our results among depth images, binary images, and images consisting of the hand-finger edge information generated from the same dataset. Our results show higher accuracy while applying SIFT features on depth images. Recognizing numeric symbols accurately performed through hand gestures has a huge impact on different Human-Computer Interaction (HCI) applications including augmented reality, virtual reality, and other fields.

scholarly journals Fast battery capacity estimation using convolutional neural networks

2020 ◽  
pp. 014233122096642 ◽  
Author(s):  
Yihuan Li ◽  
Kang Li ◽  
Xuan Liu ◽  
Li Zhang
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Smart Grids ◽  
Estimation Method ◽  
Lithium Ion ◽  
Accurate Estimation ◽  
Capacity Estimation ◽  
Starting Point ◽  
Battery Capacity ◽  
Mean Square Errors

Lithium-ion batteries have been widely used in electric vehicles, smart grids and many other applications as energy storage devices, for which the aging assessment is crucial to guarantee their safe and reliable operation. The battery capacity is a popular indicator for assessing the battery aging, however, its accurate estimation is challenging due to a range of time-varying situation-dependent internal and external factors. Traditional simplified models and machine learning tools are difficult to capture these characteristics. As a class of deep neural networks, the convolutional neural network (CNN) is powerful to capture hidden information from a huge amount of input data, making it an ideal tool for battery capacity estimation. This paper proposes a CNN-based battery capacity estimation method, which can accurately estimate the battery capacity using limited available measurements, without resorting to other offline information. Further, the proposed method only requires partial charging segment of voltage, current and temperature curves, making it possible to achieve fast online health monitoring. The partial charging curves have a fixed length of 225 consecutive points and a flexible starting point, thereby short-term charging data of the battery charged from any initial state-of-charge can be used to produce accurate capacity estimation. To employ CNN for capacity estimation using partial charging curves is however not trivial, this paper presents a comprehensive approach covering time series-to-image transformation, data segmentation, and CNN configuration. The CNN-based method is applied to two battery degradation datasets and achieves root mean square errors (RMSEs) of less than 0.0279 Ah (2.54%) and 0.0217 Ah (2.93% ), respectively, outperforming existing machine learning methods.

scholarly journals CNN-Based Facial Expression Recognition from Annotated RGB-D Images for Human–Robot Interaction

2019 ◽  
Vol 16 (04) ◽  
pp. 1941002 ◽  
Author(s):  
Jing Li ◽  
Yang Mi ◽  
Gongfa Li ◽  
Zhaojie Ju
Keyword(s):  
Facial Expression ◽  
Facial Expression Recognition ◽  
Recognition Task ◽  
Recognition System ◽  
Human Robot Interaction ◽  
Microsoft Kinect ◽  
Depth Information ◽  
Expression Recognition ◽  
Stream Network ◽  
Depth Images

Facial expression recognition has been widely used in human computer interaction (HCI) systems. Over the years, researchers have proposed different feature descriptors, implemented different classification methods, and carried out a number of experiments on various datasets for automatic facial expression recognition. However, most of them used 2D static images or 2D video sequences for the recognition task. The main limitations of 2D-based analysis are problems associated with variations in pose and illumination, which reduce the recognition accuracy. Therefore, an alternative way is to incorporate depth information acquired by 3D sensor, because it is invariant in both pose and illumination. In this paper, we present a two-stream convolutional neural network (CNN)-based facial expression recognition system and test it on our own RGB-D facial expression dataset collected by Microsoft Kinect for XBOX in unspontaneous scenarios since Kinect is an inexpensive and portable device to capture both RGB and depth information. Our fully annotated dataset includes seven expressions (i.e., neutral, sadness, disgust, fear, happiness, anger, and surprise) for 15 subjects (9 males and 6 females) aged from 20 to 25. The two individual CNNs are identical in architecture but do not share parameters. To combine the detection results produced by these two CNNs, we propose the late fusion approach. The experimental results demonstrate that the proposed two-stream network using RGB-D images is superior to that of using only RGB images or depth images.

scholarly journals Nonparametric background modelling and segmentation to detect micro air vehicles using RGB-D sensor

2019 ◽  
Vol 11 ◽  
pp. 175682931882232
Author(s):  
Navid Dorudian ◽  
Stanislao Lauria ◽  
Stephen Swift
Keyword(s):  
Background Subtraction ◽  
High Speed ◽  
Micro Air Vehicles ◽  
Background Model ◽  
Depth Information ◽  
Subtraction Technique ◽  
Depth Images ◽  
Novel Approach ◽  
Model Update ◽  
Air Vehicles

A novel approach to detect micro air vehicles in GPS-denied environments using an external RGB-D sensor is presented. The nonparametric background subtraction technique incorporating several innovative mechanisms allows the detection of high-speed moving micro air vehicles by combining colour and depth information. The proposed method stores several colour and depth images as models and then compares each pixel from a frame with the stored models to classify the pixel as background or foreground. To adapt to scene changes, once a pixel is classified as background, the system updates the model by finding and substituting the closest pixel to the camera with the current pixel. The background model update presented uses different criteria from existing methods. Additionally, a blind update model is added to adapt to background sudden changes. The proposed architecture is compared with existing techniques using two different micro air vehicles and publicly available datasets. Results showing some improvements over existing methods are discussed.

scholarly journals Evaluation of FORMOSAT-2 and PlanetScope Imagery for Aboveground Oil Palm Biomass Estimation in a Mature Plantation in the Congo Basin

2020 ◽  
Vol 12 (18) ◽  
pp. 2926
Author(s):  
Pierre Migolet ◽  
Kalifa Goïta
Keyword(s):  
Remote Sensing ◽  
Oil Palm ◽  
Aboveground Biomass ◽  
Fourier Transforms ◽  
Canopy Structure ◽  
Principal Component ◽  
Congo Basin ◽  
Biomass Estimation ◽  
Mean Square Errors

The present study developed methods using remote sensing for estimation of total dry aboveground biomass (AGB) of oil palm in the Congo Basin. To achieve this, stem diameters at breast height (DBH, 1.3 m) and stem heights were measured in an oil palm plantation located in Gabon (Congo Basin, Central Africa). These measurements were used to determine AGB in situ. The remote sensing approach that was used to estimate AGB was textural ordination (FOTO) based upon Fourier transforms that were applied, respectively, to PlanetScope and FORMOSAT-2 satellite images taken from the area. The FOTO method is based on the combined use of two-dimensional (2D) Fast Fourier Transform (FFT) and Principal Component Analysis (PCA). In the context of the present study, it was used to characterize the variation in canopy structure and to estimate the aboveground biomass of mature oil palms. Two types of equations linking FOTO indices to in situ biomass were developed: multiple linear regressions (MLR); and multivariate adaptive spline regressions (MARS). All best models developed yielded significant results, regardless of whether they were derived from PlanetScope or from FORMOSAT-2 images. Coefficients of determination (R2) varied between 0.80 and 0.92 (p ≤ 0.0005); and relative root mean-square-errors (%RMSE) were less than 10.12% in all cases. The best model was obtained using MARS approach with FOTO indices from FORMOSAT-2 (%RMSE = 6.09%).

scholarly journals Hands on Wheel Classification Based on Depth Images and Neural Networks

2020 ◽  
Vol 308 ◽  
pp. 06003
Author(s):  
Jan-Christoph Schmitz ◽  
Stephan Tilgner ◽  
Kathrin Kalischewski ◽  
Daniel Wagner ◽  
Anton Kummert
Keyword(s):  
Embedded System ◽  
Class Imbalance ◽  
Computational Effort ◽  
Training Data ◽  
Steering Wheel ◽  
Depth Information ◽  
Further Training ◽  
Depth Images ◽  
Hands On ◽  
Roof Module

This paper describes a system to automatically observe if the driver has his hands on the wheel, which is important to know that he can intervene if necessary. To accomplish this an artificial neural network is used, which utilizes depth information captured by a camera in the roof module of the car. This means that the driver and the steering wheel are viewed from above. The created classification system is described. It is designed to require as little computational effort as possible, since the target application is on an embedded system in the car. A dataset is presented and the effect of a class imbalance that is incorporated in it is studied. Furthermore, it is examined which part, i.e. the depth or the intensity image, of the available data is important to achieve the best possible performance. Finally, by examining a learning curve, an experiment is made to find out whether the recording of further training data would be reasonable.

scholarly journals Artifact Handling Based on Depth Image for View Synthesis

2019 ◽  
Vol 9 (9) ◽  
pp. 1834 ◽  
Author(s):  
Xiaodong Chen ◽  
Haitao Liang ◽  
Huaiyuan Xu ◽  
Siyu Ren ◽  
Huaiyu Cai ◽  
...  
Keyword(s):  
Objective Evaluation ◽  
Depth Image ◽  
Reference Image ◽  
Depth Information ◽  
Virtual Image ◽  
Hole Filling ◽  
Virtual View ◽  
Depth Image Based Rendering ◽  
Handling Method

The depth image based rendering (DIBR) is a popular technology for 3D video and free viewpoint video (FVV) synthesis, by which numerous virtual views can be generated from a single reference view and its depth image. However, some artifacts are produced in the DIBR process and reduce the visual quality of virtual view. Due to the diversity of artifacts, effectively handling them becomes a challenging task. In this paper, an artifact handling method based on depth image is proposed. The reference image and its depth image are extended to fill the holes that belong to the out-of-field regions. A depth image preprocessing method is applied to project the ghosts to their correct place. The 3D warping process is optimized by an adaptive one-to-four method to deal with the cracks and pixel overlapping. For disocclusions, we calculate depth and background terms of the filling priority based on depth information. The search for the best matching patch is performed simultaneously in the reference image and the virtual image. Moreover, adaptive patch size is used in all hole-filling processes. Experimental results demonstrate the effectiveness of the proposed method, which has better performance compared with previous methods in subjective and objective evaluation.

scholarly journals DOPSIE: Deep-Order Proximity and Structural Information Embedding

2019 ◽  
Vol 1 (2) ◽  
pp. 684-697
Author(s):  
Mario Manzo ◽  
Alessandro Rozza
Keyword(s):  
Vector Space ◽  
Structural Information ◽  
Graph Embedding ◽  
Depth Information ◽  
Classification Problems ◽  
Characteristic Path Length ◽  
Topological Information ◽  
Neighborhood Information ◽  
Information Embedding ◽  
Optimal Network

Graph-embedding algorithms map a graph into a vector space with the aim of preserving its structure and its intrinsic properties. Unfortunately, many of them are not able to encode the neighborhood information of the nodes well, especially from a topological prospective. To address this limitation, we propose a novel graph-embedding method called Deep-Order Proximity and Structural Information Embedding (DOPSIE). It provides topology and depth information at the same time through the analysis of the graph structure. Topological information is provided through clustering coefficients (CCs), which is connected to other structural properties, such as transitivity, density, characteristic path length, and efficiency, useful for representation in the vector space. The combination of individual node properties and neighborhood information constitutes an optimal network representation. Our experimental results show that DOPSIE outperforms state-of-the-art embedding methodologies in different classification problems.

Multiple Classifiers-Based Feature Fusion for RGB-D Object Recognition

2017 ◽  
Vol 31 (05) ◽  
pp. 1750014 ◽  
Author(s):  
Yan Wu ◽  
Jiqian Li ◽  
Jing Bai
Keyword(s):  
Object Recognition ◽  
Feature Fusion ◽  
Classification Performance ◽  
Depth Image ◽  
Depth Information ◽  
The Past ◽  
Depth Images ◽  
Comparable Performance ◽  
Accuracy Difference ◽  
Rgb Image

RGB-D-based object recognition has been enthusiastically investigated in the past few years. RGB and depth images provide useful and complementary information. Fusing RGB and depth features can significantly increase the accuracy of object recognition. However, previous works just simply take the depth image as the fourth channel of the RGB image and concatenate the RGB and depth features, ignoring the different power of RGB and depth information for different objects. In this paper, a new method which contains three different classifiers is proposed to fuse features extracted from RGB image and depth image for RGB-D-based object recognition. Firstly, a RGB classifier and a depth classifier are trained by cross-validation to get the accuracy difference between RGB and depth features for each object. Then a variant RGB-D classifier is trained with different initialization parameters for each class according to the accuracy difference. The variant RGB-D-classifier can result in a more robust classification performance. The proposed method is evaluated on two benchmark RGB-D datasets. Compared with previous methods, ours achieves comparable performance with the state-of-the-art method.

Sign in / Sign up

Export Citation Format

Share Document