scholarly journals Application Research on End-To-End Deep Person Re-Identification

2021 ◽  
Author(s):  
Qingzhen Xu ◽  
Han Qiao ◽  
Shuang Liu ◽  
Shouqiang Liu
Keyword(s):  
Recognition Accuracy ◽  
Pedestrian Detection ◽  
Image Features ◽  
Identification Accuracy ◽  
Identification System ◽  
Learning Method ◽  
Application Research ◽  
Target Image ◽  
Training Set ◽  
Identification Methods

Abstract Pedestrian detection refers to the technology of predicting and locating the location of pedestrians in video or image. However, the recognition accuracy of existing re-identification methods needs to be improved. In this paper, the deep learning method is adopted, and the pedestrian detection based on YOLOV3-spp is combined with the pedestrian re-identification based on Resnet50, to construct the deep pedestrian re-identification system. In the training part, the COCO training set containing only pedestrian images is used to train pedestrian detection. WGAN-GP was used to expand the pedestrian re-identification training set of Market1501, and pedestrian re-recognition training was carried out on the expanded dataset to reduce the interference of pose diversity in the learning process. In the detection part, the system first uses the pedestrian detection to locate the original image and cut out the corresponding image, then input the cut image and the target image into the person re-identification network to learn the image features, and finally the classifier judges the image containing the target. In the experiment, the identification accuracy of the system is 87.5% on the Market-1501 test set, and the identification speed of each picture is 0.12s.

scholarly journals More Adaptive and Updatable: An Online Sparse Learning Method for Face Recognition

2019 ◽  
Vol 2019 ◽  
pp. 1-7
Author(s):  
Qiaoling Han ◽  
Jianbo Su ◽  
Yue Zhao
Keyword(s):  
Face Recognition ◽  
Learning Strategy ◽  
Recognition Accuracy ◽  
State Of The Art ◽  
Facial Feature ◽  
Sparse Learning ◽  
Learning Method ◽  
Training Set ◽  
Feature Description ◽  
The Face

In the actual face recognition applications, the sample sets are updated constantly. However, most of the face recognition models with learning strategy do not consider this fact and using a fixed training set to learn the face recognition models for once. Besides that, the testing samples are discarded after the testing process is completed. Namely, the training and testing processes are separated and the later does not give a feedback to the former for better recognition results. To attenuate these problems, this paper proposed an online sparse learning method for face recognition. It can update the salience evaluation vector in real time to construct a dynamical facial feature description model. Also, a strategy for updating the gallery set is proposed in this proposed method. Both the dynamical facial feature description model and the gallery set are employed to recognize faces. Experimental results show that the proposed method improves the face recognition accuracy, comparing with the classical learning models and other state-of-the-art face recognition methods.

scholarly journals Comparative Analysis of Identification Methods for Mechanical Dynamics of Large-Scale Wind Turbine

Energies ◽  
2019 ◽  
Vol 12 (18) ◽  
pp. 3429 ◽  
Author(s):  
Chu ◽  
Yuan ◽  
Hu ◽  
Pan ◽  
Pan
Keyword(s):  
Mutual Information ◽  
Parameter Identification ◽  
Wind Turbines ◽  
Closed Loop ◽  
Control Design ◽  
Identification Accuracy ◽  
Mass Model ◽  
Identification Methods ◽  
Advanced Control ◽  
Mechanical Dynamics

With increasing size and flexibility of modern grid-connected wind turbines, advanced control algorithms are urgently needed, especially for multi-degree-of-freedom control of blade pitches and sizable rotor. However, complex dynamics of wind turbines are difficult to be modeled in a simplified state-space form for advanced control design considering stability. In this paper, grey-box parameter identification of critical mechanical models is systematically studied without excitation experiment, and applicabilities of different methods are compared from views of control design. Firstly, through mechanism analysis, the Hammerstein structure is adopted for mechanical-side modeling of wind turbines. Under closed-loop control across the whole wind speed range, structural identifiability of the drive-train model is analyzed in qualitation. Then, mutual information calculation among identified variables is used to quantitatively reveal the relationship between identification accuracy and variables’ relevance. Then, the methods such as subspace identification, recursive least square identification and optimal identification are compared for a two-mass model and tower model. At last, through the high-fidelity simulation demo of a 2 MW wind turbine in the GH Bladed software, multivariable datasets are produced for studying. The results show that the Hammerstein structure is effective for simplify the modeling process where closed-loop identification of a two-mass model without excitation experiment is feasible. Meanwhile, it is found that variables’ relevance has obvious influence on identification accuracy where mutual information is a good indicator. Higher mutual information often yields better accuracy. Additionally, three identification methods have diverse performance levels, showing their application potentials for different control design algorithms. In contrast, grey-box optimal parameter identification is the most promising for advanced control design considering stability, although its simplified representation of complex mechanical dynamics needs additional dynamic compensation which will be studied in future.

scholarly journals A machine learning approach for accurate and real-time DNA sequence identification

BMC Genomics ◽  
2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Yiren Wang ◽  
Mashari Alangari ◽  
Joshua Hihath ◽  
Arindam K. Das ◽  
M. P. Anantram
Keyword(s):  
Real Time ◽  
Dna Sequence ◽  
Single Molecule ◽  
Identification Accuracy ◽  
Measuring System ◽  
Identification System ◽  
Genetic Sequencing ◽  
Sequence Identification ◽  
Tree Classifier ◽  
Single Mismatch

Abstract Background The all-electronic Single Molecule Break Junction (SMBJ) method is an emerging alternative to traditional polymerase chain reaction (PCR) techniques for genetic sequencing and identification. Existing work indicates that the current spectra recorded from SMBJ experimentations contain unique signatures to identify known sequences from a dataset. However, the spectra are typically extremely noisy due to the stochastic and complex interactions between the substrate, sample, environment, and the measuring system, necessitating hundreds or thousands of experimentations to obtain reliable and accurate results. Results This article presents a DNA sequence identification system based on the current spectra of ten short strand sequences, including a pair that differs by a single mismatch. By employing a gradient boosted tree classifier model trained on conductance histograms, we demonstrate that extremely high accuracy, ranging from approximately 96 % for molecules differing by a single mismatch to 99.5 % otherwise, is possible. Further, such accuracy metrics are achievable in near real-time with just twenty or thirty SMBJ measurements instead of hundreds or thousands. We also demonstrate that a tandem classifier architecture, where the first stage is a multiclass classifier and the second stage is a binary classifier, can be employed to boost the single mismatched pair’s identification accuracy to 99.5 %. Conclusions A monolithic classifier, or more generally, a multistage classifier with model specific parameters that depend on experimental current spectra can be used to successfully identify DNA strands.

scholarly journals Campus Violence Detection Based on Artificial Intelligent Interpretation of Surveillance Video Sequences

2021 ◽  
Vol 13 (4) ◽  
pp. 628
Author(s):  
Liang Ye ◽  
Tong Liu ◽  
Tian Han ◽  
Hany Ferdinando ◽  
Tapio Seppänen ◽  
...  
Keyword(s):  
Neural Network ◽  
Recognition Accuracy ◽  
Role Playing ◽  
School Bullying ◽  
Image Features ◽  
Campus Violence ◽  
Surveillance Video ◽  
Acoustic Features ◽  
Mel Frequency Cepstral Coefficients ◽  
Violence Detection

Campus violence is a common social phenomenon all over the world, and is the most harmful type of school bullying events. As artificial intelligence and remote sensing techniques develop, there are several possible methods to detect campus violence, e.g., movement sensor-based methods and video sequence-based methods. Sensors and surveillance cameras are used to detect campus violence. In this paper, the authors use image features and acoustic features for campus violence detection. Campus violence data are gathered by role-playing, and 4096-dimension feature vectors are extracted from every 16 frames of video images. The C3D (Convolutional 3D) neural network is used for feature extraction and classification, and an average recognition accuracy of 92.00% is achieved. Mel-frequency cepstral coefficients (MFCCs) are extracted as acoustic features, and three speech emotion databases are involved. The C3D neural network is used for classification, and the average recognition accuracies are 88.33%, 95.00%, and 91.67%, respectively. To solve the problem of evidence conflict, the authors propose an improved Dempster–Shafer (D–S) algorithm. Compared with existing D–S theory, the improved algorithm increases the recognition accuracy by 10.79%, and the recognition accuracy can ultimately reach 97.00%.

scholarly journals Unsupervised Deep Feature Learning for Remote Sensing Image Retrieval

2018 ◽  
Vol 10 (8) ◽  
pp. 1243 ◽  
Author(s):  
Xu Tang ◽  
Xiangrong Zhang ◽  
Fang Liu ◽  
Licheng Jiao
Keyword(s):  
Remote Sensing ◽  
Image Retrieval ◽  
Feature Learning ◽  
Remote Sensing Image ◽  
Code Word ◽  
Image Features ◽  
Learning Method ◽  
L1 Norm ◽  
Image Descriptor ◽  
Image Archives

Due to the specific characteristics and complicated contents of remote sensing (RS) images, remote sensing image retrieval (RSIR) is always an open and tough research topic in the RS community. There are two basic blocks in RSIR, including feature learning and similarity matching. In this paper, we focus on developing an effective feature learning method for RSIR. With the help of the deep learning technique, the proposed feature learning method is designed under the bag-of-words (BOW) paradigm. Thus, we name the obtained feature deep BOW (DBOW). The learning process consists of two parts, including image descriptor learning and feature construction. First, to explore the complex contents within the RS image, we extract the image descriptor in the image patch level rather than the whole image. In addition, instead of using the handcrafted feature to describe the patches, we propose the deep convolutional auto-encoder (DCAE) model to deeply learn the discriminative descriptor for the RS image. Second, the k-means algorithm is selected to generate the codebook using the obtained deep descriptors. Then, the final histogrammic DBOW features are acquired by counting the frequency of the single code word. When we get the DBOW features from the RS images, the similarities between RS images are measured using L1-norm distance. Then, the retrieval results can be acquired according to the similarity order. The encouraging experimental results counted on four public RS image archives demonstrate that our DBOW feature is effective for the RSIR task. Compared with the existing RS image features, our DBOW can achieve improved behavior on RSIR.

scholarly journals Experimental Evaluation of PSO Based Transfer Learning Method for Meteorological Visibility Estimation

Atmosphere ◽  
2021 ◽  
Vol 12 (7) ◽  
pp. 828
Author(s):  
Wai Lun Lo ◽  
Henry Shu Hung Chung ◽  
Hong Fu
Keyword(s):  
Transfer Learning ◽  
Experimental Evaluation ◽  
Estimation Method ◽  
Image Features ◽  
Parameters Estimation ◽  
Image Feature ◽  
Support Vector ◽  
Learning Method ◽  
Feature Vectors ◽  
Visibility Estimation

Estimation of Meteorological visibility from image characteristics is a challenging problem in the research of meteorological parameters estimation. Meteorological visibility can be used to indicate the weather transparency and this indicator is important for transport safety. This paper summarizes the outcomes of the experimental evaluation of a Particle Swarm Optimization (PSO) based transfer learning method for meteorological visibility estimation method. This paper proposes a modified approach of the transfer learning method for visibility estimation by using PSO feature selection. Image data are collected at fixed location with fixed viewing angle. The database images were gone through a pre-processing step of gray-averaging so as to provide information of static landmark objects for automatic extraction of effective regions from images. Effective regions are then extracted from image database and the image features are then extracted from the Neural Network. Subset of Image features are selected based on the Particle Swarming Optimization (PSO) methods to obtain the image feature vectors for each effective sub-region. The image feature vectors are then used to estimate the visibilities of the images by using the Multiple Support Vector Regression (SVR) models. Experimental results show that the proposed method can give an accuracy more than 90% for visibility estimation and the proposed method is effective and robust.

RF-Identity

2021 ◽  
Vol 5 (1) ◽  
pp. 1-23
Author(s):  
Chao Feng ◽  
Jie Xiong ◽  
Liqiong Chang ◽  
Fuwei Wang ◽  
Ju Wang ◽  
...  
Keyword(s):  
Data Augmentation ◽  
Critical Role ◽  
Training Data ◽  
Identification Accuracy ◽  
Identification System ◽  
Frequency Bandwidth ◽  
Person Identification ◽  
Data Set ◽  
Rf Devices ◽  
Large Frequency

Person identification plays a critical role in a large range of applications. Recently, RF based person identification becomes a hot research topic due to the contact-free nature of RF sensing that is particularly appealing in current COVID-19 pandemic. However, existing systems still have multiple limitations: i) heavily rely on the gait patterns of users for identification; ii) require a large amount of data to train the model and also extensive retraining for new users and iii) require a large frequency bandwidth which is not available on most commodity RF devices for static person identification. This paper proposes RF-Identity, an RFID-based identification system to address the above limitations and the contribution is threefold. First, by integrating walking pattern features with unique body shape features (e.g., height), RF-Identity achieves a high accuracy in person identification. Second, RF-Identity develops a data augmentation scheme to expand the size of the training data set, thus reducing the human effort in data collection. Third, RF-Identity utilizes the tag diversity in spatial domain to identify static users without a need of large frequency bandwidth. Extensive experiments show an identification accuracy of 94.2% and 95.9% for 50 dynamic and static users, respectively.

GaitSense: Towards Ubiquitous Gait-Based Human Identification with Wi-Fi

2022 ◽  
Vol 18 (1) ◽  
pp. 1-24
Author(s):  
Yi Zhang ◽  
Yue Zheng ◽  
Guidong Zhang ◽  
Kun Qian ◽  
Chen Qian ◽  
...  
Keyword(s):  
Data Augmentation ◽  
Gait Recognition ◽  
Wearable Sensors ◽  
Human Identification ◽  
Training Data ◽  
Identification Accuracy ◽  
Identification System ◽  
Gait Patterns ◽  
Training Samples ◽  
Augmentation Techniques

Gait, the walking manner of a person, has been perceived as a physical and behavioral trait for human identification. Compared with cameras and wearable sensors, Wi-Fi-based gait recognition is more attractive because Wi-Fi infrastructure is almost available everywhere and is able to sense passively without the requirement of on-body devices. However, existing Wi-Fi sensing approaches impose strong assumptions of fixed user walking trajectories, sufficient training data, and identification of already known users. In this article, we present GaitSense , a Wi-Fi-based human identification system, to overcome the above unrealistic assumptions. To deal with various walking trajectories and speeds, GaitSense first extracts target specific features that best characterize gait patterns and applies novel normalization algorithms to eliminate gait irrelevant perturbation in signals. On this basis, GaitSense reduces the training efforts in new deployment scenarios by transfer learning and data augmentation techniques. GaitSense also enables a distinct feature of illegal user identification by anomaly detection, making the system readily available for real-world deployment. Our implementation and evaluation with commodity Wi-Fi devices demonstrate a consistent identification accuracy across various deployment scenarios with little training samples, pushing the limit of gait recognition with Wi-Fi signals.

scholarly journals Multilayer Hybrid Deep-Learning Method for Waste Classification and Recycling

2018 ◽  
Vol 2018 ◽  
pp. 1-9 ◽  
Author(s):  
Yinghao Chu ◽  
Chen Huang ◽  
Xiaodan Xie ◽  
Bohai Tan ◽  
Shyam Kamal ◽  
...  
Keyword(s):  
Deep Learning ◽  
High Resolution ◽  
Classification Accuracy ◽  
Image Features ◽  
Learning System ◽  
Multilayer Perceptrons ◽  
Learning Method ◽  
Waste Classification ◽  
Feature Information ◽  
Public Area

This study proposes a multilayer hybrid deep-learning system (MHS) to automatically sort waste disposed of by individuals in the urban public area. This system deploys a high-resolution camera to capture waste image and sensors to detect other useful feature information. The MHS uses a CNN-based algorithm to extract image features and a multilayer perceptrons (MLP) method to consolidate image features and other feature information to classify wastes as recyclable or the others. The MHS is trained and validated against the manually labelled items, achieving overall classification accuracy higher than 90% under two different testing scenarios, which significantly outperforms a reference CNN-based method relying on image-only inputs.

Sign in / Sign up

Export Citation Format

Share Document