scholarly journals Person Search via Deep Integrated Networks

2019 ◽  
Vol 10 (1) ◽  
pp. 188
Author(s):  
Ju-Chin Chen ◽  
Cheng-Feng Wu ◽  
Chun-Huei Chen ◽  
Cheng-Rong Lin
Keyword(s):  
Accuracy Rate ◽  
Integrated Networks ◽  
Practical Applications ◽  
Detection And Identification ◽  
Person Search ◽  
Background Clutter ◽  
Manual Processing ◽  
Active Research ◽  
Bounding Boxes ◽  
Problem Setting

This study proposes an integrated deep network consisting of a detection and identification module for person search. Person search is a very challenging problem because of the large appearance variation caused by occlusion, background clutter, pose variations, etc., and it is still an active research issue in the academic and industrial fields. Although various studies have been proposed, following the protocols of the person re-identification (ReID) benchmarks, most existing works take cropped pedestrian images either from manual labelling or a perfect detection assumption. However, for person search, manual processing is unavailable in practical applications, thereby causing a gap between the ReID problem setting and practical applications. One fact is also ignored: an imperfect auto-detected bounding box or misalignment is inevitable. We design herein a framework for the practical surveillance scenarios in which the scene images are captured. For person search, detection is a necessary step before ReID, and previous studies have shown that the precision of detection results has an influence on person ReID. The detection module based on the Faster R-CNN is used to detect persons in a scene image. For identifying and extracting discriminative features, a multi-class CNN network is trained with the auto-detected bounding boxes from the detection module, instead of the manually cropped data. The distance metric is then learned from the discriminative features output by the identification module. According to the experimental results of the test performed in the scene images, the multi-class CNN network for the identification module can provide a 62.7% accuracy rate, which is higher than that for the two-class CNN network.

A unified framework for automated person re-indentification

2020 ◽  
Vol 71 (7) ◽  
pp. 868-880
Author(s):  
Nguyen Hong-Quan ◽  
Nguyen Thuy-Binh ◽  
Tran Duc-Long ◽  
Le Thi-Lan
Keyword(s):  
Deep Learning ◽  
Video Analysis ◽  
Camera Network ◽  
Unified Framework ◽  
Person Detection ◽  
Practical Applications ◽  
Detection And Tracking ◽  
Analysis System ◽  
Bounding Boxes

Along with the strong development of camera networks, a video analysis system has been become more and more popular and has been applied in various practical applications. In this paper, we focus on person re-identification (person ReID) task that is a crucial step of video analysis systems. The purpose of person ReID is to associate multiple images of a given person when moving in a non-overlapping camera network. Many efforts have been made to person ReID. However, most of studies on person ReID only deal with well-alignment bounding boxes which are detected manually and considered as the perfect inputs for person ReID. In fact, when building a fully automated person ReID system the quality of the two previous steps that are person detection and tracking may have a strong effect on the person ReID performance. The contribution of this paper are two-folds. First, a unified framework for person ReID based on deep learning models is proposed. In this framework, the coupling of a deep neural network for person detection and a deep-learning-based tracking method is used. Besides, features extracted from an improved ResNet architecture are proposed for person representation to achieve a higher ReID accuracy. Second, our self-built dataset is introduced and employed for evaluation of all three steps in the fully automated person ReID framework.

scholarly journals Representation and Reasoning about Strategic Abilities with ω-Regular Properties

Mathematics ◽  
2021 ◽  
Vol 9 (23) ◽  
pp. 3052
Author(s):  
Liping Xiong ◽  
Sumei Guo
Keyword(s):  
Temporal Logic ◽  
Linear Time ◽  
Dynamic Logic ◽  
Research Area ◽  
Regular Expressions ◽  
Multi Agent Systems ◽  
Practical Applications ◽  
Multi Agent ◽  
Strategy Logic ◽  
Active Research

Specification and verification of coalitional strategic abilities have been an active research area in multi-agent systems, artificial intelligence, and game theory. Recently, many strategic logics, e.g., Strategy Logic (SL) and alternating-time temporal logic (ATL*), have been proposed based on classical temporal logics, e.g., linear-time temporal logic (LTL) and computational tree logic (CTL*), respectively. However, these logics cannot express general ω-regular properties, the need for which are considered compelling from practical applications, especially in industry. To remedy this problem, in this paper, based on linear dynamic logic (LDL), proposed by Moshe Y. Vardi, we propose LDL-based Strategy Logic (LDL-SL). Interpreted on concurrent game structures, LDL-SL extends SL, which contains existential/universal quantification operators about regular expressions. Here we adopt a branching-time version. This logic can express general ω-regular properties and describe more programmed constraints about individual/group strategies. Then we study three types of fragments (i.e., one-goal, ATL-like, star-free) of LDL-SL. Furthermore, we show that prevalent strategic logics based on LTL/CTL*, such as SL/ATL*, are exactly equivalent with those corresponding star-free strategic logics, where only star-free regular expressions are considered. Moreover, results show that reasoning complexity about the model-checking problems for these new logics, including one-goal and ATL-like fragments, is not harder than those of corresponding SL or ATL*.

scholarly journals Estimation of the Squirt-Flow Length Based on Crack Properties in Tight Sandstones

Lithosphere ◽  
2022 ◽  
Vol 2022 (Special 3) ◽  
Author(s):  
Chunfang Wu ◽  
Jing Ba ◽  
Lin Zhang ◽  
José M. Carcione
Keyword(s):  
Wave Attenuation ◽  
Direct Method ◽  
Wave Impedance ◽  
Practical Applications ◽  
Detection And Identification ◽  
Flow Length ◽  
Seismic Characterization ◽  
Porosity And Permeability ◽  
The Sichuan Basin ◽  
Fluid Detection

Abstract Tight sandstones have low porosity and permeability and strong heterogeneities with microcracks, resulting in small wave impedance contrasts with the surrounding rock and weak fluid-induced seismic effects, which make the seismic characterization for fluid detection and identification difficult. For this purpose, we propose a reformulated modified frame squirt-flow (MFS) model to describe wave attenuation and velocity dispersion. The squirt-flow length (R) is an important parameter of the model, and, at present, no direct method has been reported to determine it. We obtain the crack properties and R based on the DZ (David-Zimmerman) model and MFS model, and how these properties affect the wave propagation, considering ultrasonic experimental data of the Sichuan Basin. The new model can be useful in practical applications related to exploration areas.

scholarly journals TOPOLOGY-AWARE 3D MODELLING OF INDOOR SPACES FROM POINT CLOUDS

2021 ◽  
Vol XLIII-B4-2021 ◽  
pp. 267-274
Author(s):  
H. Zavar ◽  
H. Arefi ◽  
S. Malihi ◽  
M. Maboudi
Keyword(s):  
3D Model ◽  
Ground Truth ◽  
Point Clouds ◽  
Data Set ◽  
Adjacency Graph ◽  
Practical Applications ◽  
Benchmark Data ◽  
Data Driven Approach ◽  
Active Research ◽  
Indoor Spaces

Abstract. In this paper we introduce a topology-aware data-driven approach for 3D reconstruction of indoor spaces, which is an active research topic with several practical applications. After separating floor and ceiling, segmentation is followed by computing the α-shapes of the segment. The adjacency graph of all α-shapes is used to find the intersecting planes. By employing a B-rep approach, an initial 3D model is computed. Afterwards, adjacency graph of the intersected planes which constitute the initial model is analyzed in order to refine the 3D model. This leads to a water-tight and topologically correct 3D model. The performance of our proposed approach is qualitatively and quantitatively evaluated on an ISPRS benchmark data set. On this dataset, we achieved 77% completeness, 53% correctness and 1.7–5 cm accuracy with comparison of the final 3D model to the ground truth.

scholarly journals Fast and Robust Object Tracking Using Tracking Failure Detection in Kernelized Correlation Filter

2020 ◽  
Vol 10 (2) ◽  
pp. 713 ◽  
Author(s):  
Jungsup Shin ◽  
Heegwang Kim ◽  
Dohun Kim ◽  
Joonki Paik
Keyword(s):  
Object Tracking ◽  
Real Time ◽  
Processing Speed ◽  
Motion Vector ◽  
Failure Detection ◽  
Correlation Filter ◽  
Tracking Accuracy ◽  
Practical Applications ◽  
Feature Based ◽  
Active Research

Object tracking has long been an active research topic in image processing and computer vision fields with various application areas. For practical applications, the object tracking technique should be not only accurate but also fast in a real-time streaming condition. Recently, deep feature-based trackers have been proposed to achieve a higher accuracy, but those are not suitable for real-time tracking because of an extremely slow processing speed. The slow speed is a major factor to degrade tracking accuracy under a real-time streaming condition since the processing delay forces skipping frames. To increase the tracking accuracy with preserving the processing speed, this paper presents an improved kernelized correlation filter (KCF)-based tracking method that integrates three functional modules: (i) tracking failure detection, (ii) re-tracking using multiple search windows, and (iii) motion vector analysis to decide a preferred search window. Under a real-time streaming condition, the proposed method yields better results than the original KCF in the sense of tracking accuracy, and when a target has a very large movement, the proposed method outperforms a deep learning-based tracker, such as multi-domain convolutional neural network (MDNet).

scholarly journals Efficient and Deep Vehicle Re-Identification Using Multi-Level Feature Extraction

2019 ◽  
Vol 9 (7) ◽  
pp. 1291 ◽  
Author(s):  
Zakria ◽  
Jingye Cai ◽  
Jianhua Deng ◽  
Muhammad Aftab ◽  
Muhammad Khokhar ◽  
...  
Keyword(s):  
Intelligent Transportation System ◽  
Research Area ◽  
Incident Detection ◽  
Query Image ◽  
Practical Applications ◽  
Novel Approach ◽  
Proposed Model ◽  
Toll Collection ◽  
Active Research ◽  
The Given

The intelligent transportation system is currently an active research area, and vehicle re-identification (Re-Id) is a fundamental task to implement it. It determines whether the given vehicle image obtained from one camera has already appeared over a camera network or not. There are many possible practical applications where the vehicle Re-Id system can be employed, such as intelligent vehicle parking, suspicious vehicle tracking, vehicle incident detection, vehicle counting, and automatic toll collection. This task becomes more challenging because of intra-class similarity, viewpoint changes, and inconsistent environmental conditions. In this paper, we propose a novel approach that re-identifies a vehicle in two steps: first we shortlist the vehicle from a gallery set on the basis of appearance, and then in the second step we verify the shortlisted vehicle’s license plates with a query image to identify the targeted vehicle. In our model, the global channel extracts the feature vector from the whole vehicle image, and the local region channel extracts more discriminative and salient features from different regions. In addition to this, we jointly incorporate attributes like model, type, and color, etc. Lastly, we use a siamese neural network to verify license plates to reach the exact vehicle. Extensive experimental results on the benchmark dataset VeRi-776 demonstrate the effectiveness of the proposed model as compared to various state-of-the-art methods.

Contourlet Transform Based Texture Analysis for Smoke and Fog Classification

2011 ◽  
Vol 88-89 ◽  
pp. 537-542 ◽  
Author(s):  
Yang Zhao ◽  
Jian Hui Zhao ◽  
Jing Huang ◽  
Shi Zhong Han ◽  
Cheng Jiang Long ◽  
...  
Keyword(s):  
Texture Analysis ◽  
Local Binary Pattern ◽  
Fire Detection ◽  
Contourlet Transform ◽  
Support Vector ◽  
Smoke Detection ◽  
Accuracy Rate ◽  
Practical Applications ◽  
Detection Algorithms ◽  
Important Research Topic

Fire detection has long been an important research topic in image processing and pattern recognition, while smoke is a vital indication of fire’s existence. However, current smoke detection algorithms are far from meeting the requirements of practical applications. One major reason is that the existing methods can not distinguish smoke from fog because their colors and shapes are both very similar. This paper proposes a novel texture analysis based algorithm which has the ability to classify smoke and fog more efficiently. First the texture images are decomposed using Contourlet Transform (CT), and then we extract the feature vector from Contourlet coefficients, finally we make use of Support Vector Machine (SVM) to classify the textures. Experiments are performed on the sample images of smoke and fog taking accuracy rate of classification as evaluation criterion, and the accuracy rate of our algorithm is 97%. To illustrate its performance, our method has also been compared with the algorithms using Gray Level Co-occurrence Matrixes (GLCM), Local Binary Pattern (LBP) and Wavelet Transform (WT).

scholarly journals A unified framework for automated person re-identification

2020 ◽  
Vol 71 (7) ◽  
pp. 868-880
Author(s):  
Nguyen Hong Quan ◽  
Nguyen Thuy Binh ◽  
Tran Duc Long ◽  
Le Thi Lan
Keyword(s):  
Deep Learning ◽  
Video Analysis ◽  
Camera Network ◽  
Unified Framework ◽  
Person Detection ◽  
Practical Applications ◽  
Detection And Tracking ◽  
Analysis System ◽  
Bounding Boxes

Along with the strong development of camera networks, a video analysis system has been become more and more popular and has been applied in various practical applications. In this paper, we focus on person re-identification (person ReID) task that is a crucial step of video analysis systems. The purpose of person ReID is to associate multiple images of a given person when moving in a non-overlapping camera network. Many efforts have been made to person ReID. However, most of studies on person ReID only deal with well-alignment bounding boxes which are detected manually and considered as the perfect inputs for person ReID. In fact, when building a fully automated person ReID system the quality of the two previous steps that are person detection and tracking may have a strong effect on the person ReID performance. The contribution of this paper are two-folds. First, a unified framework for person ReID based on deep learning models is proposed. In this framework, the coupling of a deep neural network for person detection and a deep-learning-based tracking method is used. Besides, features extracted from an improved ResNet architecture are proposed for person representation to achieve a higher ReID accuracy. Second, our self-built dataset is introduced and employed for evaluation of all three steps in the fully automated person ReID framework.

scholarly journals A Deep Learning Based Printing Defect Classification Method with Imbalanced Samples

Symmetry ◽  
2019 ◽  
Vol 11 (12) ◽  
pp. 1440 ◽  
Author(s):  
Erhu Zhang ◽  
Bo Li ◽  
Peilin Li ◽  
Yajun Chen
Keyword(s):  
Deep Learning ◽  
Classification Method ◽  
Coarse Grained ◽  
Defect Classification ◽  
Accuracy Rate ◽  
Practical Applications ◽  
Fine Grained ◽  
Deep Model ◽  
Different Types ◽  
Classification Tasks

Deep learning has been successfully applied to classification tasks in many fields due to its good performance in learning discriminative features. However, the application of deep learning to printing defect classification is very rare, and there is almost no research on the classification method for printing defects with imbalanced samples. In this paper, we present a deep convolutional neural network model to extract deep features directly from printed image defects. Furthermore, considering the asymmetry in the number of different types of defect samples—that is, the number of different kinds of defect samples is unbalanced—seven types of over-sampling methods were investigated to determine the best method. To verify the practical applications of the proposed deep model and the effectiveness of the extracted features, a large dataset of printing detect samples was built. All samples were collected from practical printing products in the factory. The dataset includes a coarse-grained dataset with four types of printing samples and a fine-grained dataset with eleven types of printing samples. The experimental results show that the proposed deep model achieves a 96.86% classification accuracy rate on the coarse-grained dataset without adopting over-sampling, which is the highest accuracy compared to the well-known deep models based on transfer learning. Moreover, by adopting the proposed deep model combined with the SVM-SMOTE over-sampling method, the accuracy rate is improved by more than 20% in the fine-grained dataset compared to the method without over-sampling.

Sign in / Sign up

Export Citation Format

Share Document