scholarly journals Key-Frame Detection and Video Retrieval Based on DC Coefficient-Based Cosine Orthogonality and Multivariate Statistical Tests

2020 ◽  
Vol 37 (5) ◽  
pp. 773-784
Author(s):  
Gowrisankar Kalakoti ◽  
Prabakaran G
Keyword(s):  
Feature Vector ◽  
Video Retrieval ◽  
Statistical Tests ◽  
Multivariate Statistical ◽  
Key Frame ◽  
Feature Vectors ◽  
Retrieval Rate ◽  
Dc Coefficient ◽  
Equality Of Mean Vectors ◽  
Mean Vector

This paper presents a method, which is developed based on the Discrete Cosine (DC) coefficient and multivariate parametric statistical tests, such as tests for equality of mean vectors and the covariance matrices. Background scenes and forefront objects are separated from the key-frame, and the salient features, such as colour and Gabor texture, are extracted from the background and forefront components. The extracted features are formulated as a feature vector. The feature vector is compared to that of the feature vector database, based on the statistical tests. First, the feature vectors are compared with respect to covariance. If the feature vector of the key-frame and the feature vector of the feature vector database pass the test, then the test for equality of mean vector is performed; otherwise, the testing process is stopped. If the feature vectors pass both tests, then it is inferred that the query key-frame represents the target video in the video database. Otherwise, it is concluded that the query key-frame not representing the video; and the proposed system takes the next feature vector for matching. The proposed method results in an average retrieval rate of 97.232%, 96.540%, and 96.641% for CC_WEB, UCF101, and our newly constructed database, respectively. Further, the mAP scores computed for each video datasets, which resulted in 0.807, 0.812, and 0.814 for CC_WEB, UCF101, and our newly constructed database, respectively. The output results obtained by the proposed method are comparable to the existing methods.

Wavelet-Contourlet Retrieval Using Energy and Kurtosis Features

2011 ◽  
Vol 201-203 ◽  
pp. 2330-2333
Author(s):  
Xin Wu Chen ◽  
Zhan Qing Ma ◽  
Li Wei Liu
Keyword(s):  
Standard Deviation ◽  
Retrieval System ◽  
Feature Vector ◽  
Contourlet Transform ◽  
Feature Vectors ◽  
System A ◽  
Retrieval Rate ◽  
Retrieval Systems ◽  
Single Feature ◽  
Canberra Distance

To improve the retrieval rate of contourlet transform retrieval system and reduce the redundancy of contourlet which cost two much time in building feature vector database, a new wavelet-contourlet transform retrieval system was proposed. Six different features, including mean, standard deviation, absolute mean energy, L2 energy, skewness and kurotis contributions to retrieval rates were examined. Based on the single feature ability in retrieval system, a new contourlet retrieval system was proposed. The feature vectors were constructed by cascading the absolute mean energy and kurtosis of each sub-band contourlet coefficients and the similarity measure used here is Canberra distance. Experimental results on 109 brodatz texture images show that using the features cascaded by absolute mean and kurtosis can lead to a higher retrieval rate than several contourlet transform retrieval systems which utilize the combination feature of standard deviation and absolute mean energy most commonly used today under same dimension of feature vectors.

scholarly journals Large-Scale Video Retrieval via Deep Local Convolutional Features

2020 ◽  
Vol 2020 ◽  
pp. 1-8
Author(s):  
Chen Zhang ◽  
Bin Hu ◽  
Yucong Suo ◽  
Zhiqiang Zou ◽  
Yimu Ji
Keyword(s):  
Large Scale ◽  
Video Retrieval ◽  
Video Data ◽  
Query Image ◽  
Key Frame Extraction ◽  
Key Frame ◽  
Storage Cost ◽  
Extraction Algorithm ◽  
Feature Aggregation ◽  
And Storage

In this paper, we study the challenge of image-to-video retrieval, which uses the query image to search relevant frames from a large collection of videos. A novel framework based on convolutional neural networks (CNNs) is proposed to perform large-scale video retrieval with low storage cost and high search efficiency. Our framework consists of the key-frame extraction algorithm and the feature aggregation strategy. Specifically, the key-frame extraction algorithm takes advantage of the clustering idea so that redundant information is removed in video data and storage cost is greatly reduced. The feature aggregation strategy adopts average pooling to encode deep local convolutional features followed by coarse-to-fine retrieval, which allows rapid retrieval in the large-scale video database. The results from extensive experiments on two publicly available datasets demonstrate that the proposed method achieves superior efficiency as well as accuracy over other state-of-the-art visual search methods.

scholarly journals Intelligent Sports Video Classification Based on Deep Neural Network (DNN) Algorithm and Transfer Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Xiaoping Guo
Keyword(s):  
Neural Network ◽  
Optical Flow ◽  
Transfer Learning ◽  
Deep Neural Network ◽  
Mutation Detection ◽  
Video Retrieval ◽  
Flow Analysis ◽  
Key Frame Extraction ◽  
Sports Video ◽  
Key Frame

Traditional text annotation-based video retrieval is done by manually labeling videos with text, which is inefficient and highly subjective and generally cannot accurately describe the meaning of videos. Traditional content-based video retrieval uses convolutional neural networks to extract the underlying feature information of images to build indexes and achieves similarity retrieval of video feature vectors according to certain similarity measure algorithms. In this paper, by studying the characteristics of sports videos, we propose the histogram difference method based on using transfer learning and the four-step method based on block matching for mutation detection and fading detection of video shots, respectively. By adaptive thresholding, regions with large frame difference changes are marked as candidate regions for shots, and then the shot boundaries are determined by mutation detection algorithm. Combined with the characteristics of sports video, this paper proposes a key frame extraction method based on clustering and optical flow analysis, and experimental comparison with the traditional clustering method. In addition, this paper proposes a key frame extraction algorithm based on clustering and optical flow analysis for key frame extraction of sports video. The algorithm effectively removes the redundant frames, and the extracted key frames are more representative. Through extensive experiments, the keyword fuzzy finding algorithm based on improved deep neural network and ontology semantic expansion proposed in this paper shows a more desirable retrieval performance, and it is feasible to use this method for video underlying feature extraction, annotation, and keyword finding, and one of the outstanding features of the algorithm is that it can quickly and effectively retrieve the desired video in a large number of Internet video resources, reducing the false detection rate and leakage rate while improving the fidelity, which basically meets people’s daily needs.

scholarly journals Within and Between Shot Information Utilisation in Video Key Frame Extraction

2011 ◽  
Vol 10 (03) ◽  
pp. 247-259 ◽  
Author(s):  
Dianting Liu ◽  
Mei-Ling Shyu ◽  
Chao Chen ◽  
Shu-Ching Chen
Keyword(s):  
Extraction Method ◽  
Video Sequence ◽  
Video Retrieval ◽  
Video Browsing ◽  
High Quality ◽  
Key Frame Extraction ◽  
Key Frame ◽  
Video Shot ◽  
Key Frames ◽  
Candidate Set

In consequence of the popularity of family video recorders and the surge of Web 2.0, increasing amounts of videos have made the management and integration of the information in videos an urgent and important issue in video retrieval. Key frames, as a high-quality summary of videos, play an important role in the areas of video browsing, searching, categorisation, and indexing. An effective set of key frames should include major objects and events of the video sequence, and should contain minimum content redundancies. In this paper, an innovative key frame extraction method is proposed to select representative key frames for a video. By analysing the differences between frames and utilising the clustering technique, a set of key frame candidates (KFCs) is first selected at the shot level, and then the information within a video shot and between video shots is used to filter the candidate set to generate the final set of key frames. Experimental results on the TRECVID 2007 video dataset have demonstrated the effectiveness of our proposed key frame extraction method in terms of the percentage of the extracted key frames and the retrieval precision.

scholarly journals Intelligent recognition of acoustic emission signals from damage of glass fiber-reinforced plastics

2020 ◽  
Vol 29 ◽  
pp. 2633366X2097468
Author(s):  
Qiufeng Li ◽  
Tiantian Qi ◽  
Lihua Shi ◽  
Yao Chen ◽  
Lixia Huang ◽  
...  
Keyword(s):  
Acoustic Emission ◽  
Glass Fiber ◽  
Feature Vector ◽  
Wavelet Packet ◽  
Feature Vectors ◽  
Reinforced Plastics ◽  
Glass Fiber Reinforced ◽  
Fiber Reinforced Plastics ◽  
Intelligent Recognition ◽  
Ae Signals

Glass fiber-reinforced plastics (GFRP) is widely used in many industrial fields. When acoustic emission (AE) technology is applied for dynamic monitoring, the interfering signals often affect the damage evaluation results, which significantly influences industrial production safety. In this work, an effective intelligent recognition method for AE signals from the GFRP damage is proposed. Firstly, the wavelet packet analysis method is used to study the characteristic difference in frequency domain between the interfering and AE signals, which can be characterized by feature vector. Then, the model of back-propagation neural network (BPNN) is constructed. The number of nodes in the input layer is determined according to the feature vector, and the feature vectors from different types of signals are input into the BPNN for training. Finally, the wavelet packet feature vectors of the signals collected from the experiment are input into the trained BPNN for intelligent recognition. The accuracy rate of the proposed method reaches to 97.5%, which implies that the proposed method can be used for dynamic and accurate monitoring of GFRP structures.

scholarly journals Assessment of the Impact of Forestry and Settlement-Forest Use of the Catchments on the Parameters of Surface Water Quality: Case Studies for Chechło Reservoir Catchment, Southern Poland

Water ◽  
2019 ◽  
Vol 11 (5) ◽  
pp. 964 ◽  
Author(s):  
Andrzej Bogdał ◽  
Andrzej Wałęga ◽  
Tomasz Kowalik ◽  
Agnieszka Cupak
Keyword(s):  
Water Quality ◽  
Total Phosphorus ◽  
Surface Waters ◽  
Forest Cover ◽  
Statistical Tests ◽  
Surface Water Quality ◽  
Anthropogenic Factors ◽  
Multivariate Statistical ◽  
Forest Use ◽  
The Impact

The aim of the study was to determine the impact of natural and anthropogenic factors on the values of 22 quality indicators of surface waters flowing out of two small catchments differing in physiographic parameters and land use, in particular forest cover and urbanization of the area. The research was carried out in the years 2012–2014 at four measurement-control points located on the Chechło river and the Młoszówka stream (Poland), which are the main tributaries of the retention reservoir. Basic descriptive statistics, statistical tests, as well as cluster analysis and factor analysis were used to interpret the research results. The water that outflowed from the forestry-settlement catchment of the Młoszówka stream contained higher concentrations of total phosphorus, phosphates, nitrite, and nitrate nitrogen and salinity indicators than outflow from the Chechło river. Water from the Młoszówka stream was characterized by more favourable oxygen conditions. Higher oxygen concentration in the catchment influenced a large slope of the watercourse and thus higher water velocity, which is promoted by the mixed process. In the case of the forest catchment of the Chechło river, the water quality was generally better than in the Młoszówka stream, mainly in cases of total suspended solids TSS, total phosphorus TP, phosphates PO43−, total nitrogen TN, nitrite N–NO2−, nitrate N–NO3−, and salinity parameters. Despite it being a short section of the river taken into the study, favourable self-purification processes like mixed, nitrification, and denitrification were observed in its water. The research shows that forest areas have a positive effect on the balance of most substances dissolved in water, and natural factors in many cases shape the quality and utility values of surface waters on an equal footing with anthropogenic factors. In the case of a large number of examined parameters and complex processes occurring in water, the interpretation of the results makes it much easier by applying multivariate statistical methods.

Feature Vector Identification and Prognostics of SAC305 PCB’s for Varying Conditions of Temperature and Vibration Loads

2020 ◽  
Author(s):  
Pradeep Lall ◽  
Tony Thomas ◽  
Ken Blecker
Keyword(s):  
Feature Vector ◽  
Sac305 Solder ◽  
Feature Vectors ◽  
Operating Environments ◽  
Electronic Board ◽  
Different Types ◽  
Varying Environments ◽  
Temperature Constant ◽  
Temperature Levels ◽  
Strain Signal

Abstract This study focuses on the feature vector identification of SAC305 solder alloy PCB’s of two different configurations during varying conditions of temperature and vibration. The feature vectors are identified from the strain signals, that are acquired from four symmetrical locations of the PCB at regular intervals during vibration. The changes in the vibration characteristics of the PCB are characterized by three different types of experiments. First type of analysis emphasizes the vibration characteristic for varying conditions of acceleration levels keeping the temperature constant during vibration. The second analysis studies the characteristics changes for varying temperature levels by keeping the acceleration levels constant. Finally, the third analysis focuses on the combined changes in temperature and acceleration levels for the board during vibration. The above analyses try to imitate the actual working conditions of an electronic board in an automobile which is subjected to varying environments of temperature and vibration. The strain signals acquired during each of these experiments are compared based on both time and frequency domain characteristics. Different statistical and frequency based techniques were used to identify the variations in the strain signal with changes in the environment and loading conditions. The feature vectors of failure at a constant working condition and load were identified and as an extension to the previous work, the effectiveness of the feature vectors during these varying conditions of temperature and acceleration levels are investigated using the above analyses. The feature vector of a PCB under varying conditions of temperature and load are identified and compared with different operating environments.

Sign in / Sign up

Export Citation Format

Share Document