scholarly journals Computer Vision-based Human Activity Recognition for Elderly Home Care

2019 ◽  
Vol 9 (1S) ◽  
pp. 299-303
Keyword(s):  
Computer Vision ◽  
Elderly People ◽  
Orientation Angle ◽  
Major Axis ◽  
Gaussian Mixture ◽  
Minor Axis ◽  
Video Sequences ◽  
Novel Approach ◽  
Human Object ◽  
Axis Length

Video-based monitoring of elderly people at home receives more attention in recent days. In this paper, we propose a novel approach to develop smart monitoring system for elderly people using computer vision techniques. Gaussian Mixture Model (GMM) based algorithm is used for background and foreground separation inorder to track the activities of human object. The minimum bounding box of the human object is traced and features like major axis length, minor axis length and orientation angle are extracted. The proposed approach is evaluated on the video sequences of fall dataset.

scholarly journals Electric field bridging pattern of pre-breakdown and breakdown condition in transformer oil

2020 ◽  
Vol 19 (3) ◽  
pp. 1210
Author(s):  
Nur Badariah Ahmad Mustafa ◽  
N H Nik Ali ◽  
H. Zainuddin ◽  
Marizuana Mat Daud ◽  
Farah Hani Nordin
Keyword(s):  
Electric Field ◽  
Electrical Power ◽  
Major Axis ◽  
Dielectric Strength ◽  
Minor Axis ◽  
Transformer Oil ◽  
Support Vector ◽  
Electrical Power System ◽  
Feature Descriptors ◽  
Axis Length

Transformer is considered as one of the most important equipment in electrical power system networks. However, most problems occurred in transformer were related to the defects and weakness of the insulation systems. The oils used in transformer act as coolant and insulation purposes hence maintaining the dielectric strength of the transformer. In this work, electric field bridging pattern is observed from pre-breakdown and breakdown condition. The electric field bridging formation was recorded in the experimental setup and images were captured per frame. 193 images were randomly chosen from the whole video frames where 102 images were the pre-breakdown images and 91 images were the breakdown images. This system comprises of four stages: (i) a preprocessing stage to mark the electrodes tips and background subtraction; (ii) a segmentation stage to extract the electric field bridging formation in region of interest; (iii) a feature extraction stage to extract electric field bridging using feature descriptors, <em>area</em>, <em>minor-axis </em>and <em>major-axis length  </em> (iv) a classification stage to identify the pre-breakdown and breakdown condition. System performance was evaluated using support vector machine (SVM), <em>k</em>-nearest neighbour (<em>k</em>-NN) and random forest (RF) and SVM provided the most promising accuracy that was 99%. The results show that the combination of three feature descriptors, <em>area</em>, <em>minor-axis </em>and <em>major-axis length </em>are the best features combination in identifying the transformer oil condition. In future work, further studies will be conducted to investigate the pattern of pre- and post-breakdown due to some similarity found in image pattern. Due to that, more feature descriptors will be identified to find a unique pattern between pre- and post-breakdown condition

scholarly journals Automatic Tajweed Rules Recognition using K-Nearest Neighbour (K-NN)

2019 ◽  
Vol 8 (2S11) ◽  
pp. 552-557
Keyword(s):  
Classification Accuracy ◽  
Major Axis ◽  
Shape Descriptor ◽  
Processing Technique ◽  
Input Image ◽  
Minor Axis ◽  
Image Processing Technique ◽  
Nearest Neighbour ◽  
The People ◽  
Axis Length

Tajweed refers to a pronunciation rule for Al-Quran recitation in Islam. It acts as guidance for Muslims in reciting the Al-Quran in a correct manner. Yet, Tajweed rules could be complicated as it consists of various types of laws. It could also be confusing, and difficult to remember particularly for the people who have less knowledge in Tajweed rules. Thus, a study on automatic tajweed rules recognition using image processing technique is proposed. The scope of this study is limited to Idgham laws only. Initially, the input image went through the pre-processing process which includes four sub-processes which are greyscale conversion, binary conversion, thinning and flip, and word segmentation. Next, six attributes of shape descriptor which are major axis length, minor axis length, eccentricity, filled area, solidity, and perimeter were extracted from each input image. A technique of k-Nearest Neighbour (k-NN) is employed to recognize the two types of Idgham Laws which are Idgham Maal Ghunnah and Idgham Bila Ghunnah. The performance of the proposed study is evaluated to 180 testing images which returned 84.44% of classification accuracy. The outcome of this study is expected to recognize the Tajweed rules automatically and may assist the user on a proper recitation of Al-Quran.

scholarly journals Advantages of petrosectomy for superficial temporal artery to superior cerebellar artery bypass based on three-dimensional distance measurements using cadaver heads

2021 ◽  
Author(s):  
Kenji Uda ◽  
Kuniaki Tanahashi ◽  
Takashi Mamiya ◽  
Fumiaki Kanamori ◽  
Kinya Yokoyama ◽  
...  
Keyword(s):  
Superficial Temporal Artery ◽  
Three Dimensional ◽  
Major Axis ◽  
Temporal Artery ◽  
Minor Axis ◽  
Field Size ◽  
Superior Cerebellar Artery ◽  
Operative Field ◽  
Axis Length ◽  
Optimal Approach

AbstractSuperficial temporal artery (STA) to superior cerebellar artery (SCA) bypass is usually performed via the subtemporal approach (StA), anterior transpetrosal approach (ApA), or combined petrosal approach (CpA), but no study has yet reported a quantitative comparison of the operative field size provided by each approach, and the optimal approach is unclear. The objective of this study is to establish evidence for selecting the approach by using cadaver heads to measure the three-dimensional distances that represent the operative field size for STA–SCA bypass. Ten sides of 10 cadaver heads were used to perform the four approaches: StA, ApA with and without zygomatic arch osteotomy (ApA-ZO− and ApA-ZO+), and CpA. For each approach, the major-axis length and the minor-axis length at the anastomosis site (La-A and Li-A), the major-axis length and the minor-axis length at the brain surface (La-B and Li-B), the depth from the brain surface to the anastomosis site (Dp), and the operating angles of the major axis and the minor axis (OAa and OAi) were measured. Shallower Dp and wider operating angle were obtained in the order CpA, ApA-ZO+, ApA-ZO−, and StA. In all parameters, ApA-ZO− extended the operative field more than StA. ApA-ZO+ extended La-B and OAa more than ApA-ZO−, whereas it did not contribute to Dp and OAi. CpA significantly decreased Dp, and widened OAa and OAi more than ApA-ZO+. ApA and CpA greatly expanded the operative field compared with StA. These results provide criteria for selecting the optimal approach for STA-SCA bypass in light of an individual surgeon’s anastomosis skill level.

scholarly journals A novel approach to control the Jointed Arm Robot by tracking the position of the moving object on a conveyor using an Integrated Computer Vision system

2021 ◽  
Author(s):  
Pramod Kumar Thotapalli ◽  
◽  
CH. R. Vikram Kumar ◽  
B.ChandraMohana Reddy ◽  
◽  
...  
Keyword(s):  
Computer Vision ◽  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Moving Objects ◽  
Vision System ◽  
Autonomous Systems ◽  
Gaussian Mixture ◽  
Vital Role ◽  
Work Cell ◽  
Novel Approach

Computer vision algorithms play a vital role in developing self-sustained autonomous systems. The objective of the present work is to integrate the robotic system with a moving conveyor using a single camera by adopting a Gaussian Mixture Model (GMM) based background subtraction method. In this work, a simple web camera is placed above the work cell to capture the continuous images of the moving objects on the conveyor along with a jointed arm robot are connected to a microcontroller through the computer. The position of the object with time and its features are extracted from the captured image frames by subtracting its background using the Gaussian Mixture Model (GMM). The output images of GMM are further processed by image processing techniques to extract the features like shape, color, center coordinates. The extracted coordinates of objects of interest are used as input parameters to the controller to activate the base rotation of a joint arm robot to perform different manipulations. The developed algorithm is evaluated on an indigenously fabricated work cell integrated with a computer vision setup.

Inertia-Based Ear Biometrics: A Novel Approach

2016 ◽  
Vol 25 (3) ◽  
pp. 401-416
Author(s):  
M.A. Jayaram ◽  
G.K. Prashanth ◽  
Sachin C. Patil
Keyword(s):  
Recognition Rate ◽  
Principal Component ◽  
Major Axis ◽  
Minor Axis ◽  
Moment Of Inertia ◽  
Radius Of Gyration ◽  
Identification System ◽  
Person Identification ◽  
Ear Biometrics ◽  
Novel Approach

AbstractThe human ear has been deemed to be a source of data for person identification in recent years. Ear biometrics has distinct advantages, such as visibility from a distance and ease with which images could be captured. This paper elaborates on a novel approach to ear biometrics. We propose moment of inertia-based biometric for the ears in any random orientation. The features concerned are the moment of inertia about the major and minor axes, corresponding radii of gyration, and the planar surface area of the ear. The databases of the said features were collected through ear images of 600 subjects. Principal component analysis of the features demonstrated that the radius of gyration with respect to the major axis, moment of inertia about the minor axis, and radius of gyration about the minor axis are significant attributes contributing to major variability. The person identification system developed showed recognition rates of 99% with just three attributes, when compared with the 96% recognition rate when all five attributes were considered. The evaluation of the system was done on several metrics. All metrics were found to be insignificant in their magnitude, which is suggestive of robustness and excellent authentication performance.

scholarly journals lakemorpho: Calculating lake morphometry metrics in R

F1000Research ◽  
2017 ◽  
Vol 6 ◽  
pp. 1718 ◽  
Author(s):  
Jeffrey Hollister ◽  
Joseph Stachelek
Keyword(s):  
Software Tool ◽  
Major Axis ◽  
R Package ◽  
Minor Axis ◽  
Lake Morphometry ◽  
Shoreline Development ◽  
Lake Ecology ◽  
Digital Elevation ◽  
Scale Modelling ◽  
Axis Length

Metrics describing the shape and size of lakes, known as lake morphometry metrics, are important for any limnological study. In cases where a lake has long been the subject of study these data are often already collected and are openly available. Many other lakes have these data collected, but access is challenging as it is often stored on individual computers (or worse, in filing cabinets) and is available only to the primary investigators. The vast majority of lakes fall into a third category in which the data are not available. This makes broad scale modelling of lake ecology a challenge as some of the key information about in-lake processes are unavailable. While this valuable in situ information may be difficult to obtain, several national datasets exist that may be used to model and estimate lake morphometry. In particular, digital elevation models and hydrography have been shown to be predictive of several lake morphometry metrics. The R package lakemorpho has been developed to utilize these data and estimate the following morphometry metrics: surface area, shoreline length, major axis length, minor axis length, major and minor axis length ratio, shoreline development, maximum depth, mean depth, volume, maximum lake length, mean lake width, maximum lake width, and fetch. In this software tool article we describe the motivation behind developing lakemorpho, discuss the implementation in R, and describe the use of lakemorpho with an example of a typical use case.

scholarly journals Neoangiogenesis and microvascular density in myelodysplastic syndrome – a single center experience

2019 ◽  
Vol 2 (2) ◽  
pp. 40-50
Author(s):  
Anita Skrtic ◽  
Njetocka Gredelj-Simec ◽  
Ika Kardum-Skelin ◽  
Eva Lovric ◽  
Darija Muzinic ◽  
...  
Keyword(s):  
High Risk ◽  
Major Axis ◽  
Risk Groups ◽  
Microvascular Density ◽  
Minor Axis ◽  
Control Group ◽  
Bone Marrow Biopsies ◽  
Single Center Experience ◽  
Axis Length ◽  
Network Transformation

Angiogenesis has a significant part in the pathogenesis of hematological malignancies, such as leukemia and myelodysplastic syndromes (MDS). We evaluated the relationship between morphometric, morphological and clinical features of MDS. Blood vessels of 31 newly diagnosed MDS bone marrow biopsies were immunohistochemically analyzed using CD34 and compared with 8 controls and 13 chronic myelomonocytic leukemias (CMML). MDS were categorized into three risk groups: low-, intermediate- and high-risk MDS. Microvascular density (MVD) and major and minor axis length were analyzed using digital image analysis. Overall, MDS had significantly higher MVD and lower minor axis values than the control group and CMML. High-risk MDS had significantly higher MVD compared to the controls, while all MDS risk groups had lower minor axis values than the control group. Increased minor and major axis values were prognostic predictors of shorter overall survival in all MDS risk groups and CMML patients. In conclusion, angiogenesis presents one of the essential factors in MDS pathogenesis and progression characterized by descriptive marrow microvascular network transformation. The size-related features are powerful indicators of survival in MDS patients.

scholarly journals Colorectal endoscopic submucosal dissection using the pocket-creation method with single clip traction: a feasibility study

2021 ◽  
Vol 09 (05) ◽  
pp. E653-E658
Author(s):  
Tatsuma Nomura ◽  
Yoshikazu Hayashi ◽  
Takaaki Morikawa ◽  
Masahiro Okada ◽  
Hisashi Fukuda ◽  
...  
Keyword(s):  
Endoscopic Submucosal Dissection ◽  
Major Axis ◽  
En Bloc Resection ◽  
Bloc Resection ◽  
Success Rates ◽  
En Bloc ◽  
Submucosal Dissection ◽  
Mucosal Incision ◽  
Axis Length ◽  
Colorectal Endoscopic Submucosal Dissection

Abstract Background and study aims The pocket-creation method (PCM) facilitates dissection of the central part of a tumor. We previously developed the PCM with clip traction (PCM-CT) to facilitate opening the mucosal pocket, which otherwise could become cumbersome. In the present study, we aimed to examine the feasibility of PCM-CT for colorectal endoscopic submucosal dissection (ESD). Patients and methods PCM-CT was performed on 30 patients with early colorectal tumors from October 2019 to April 2020. PCM-CT allows efficient opening of the mucosal pocket by using the PCM to dissect the center of the lesion and then apply traction with a single clip after making a circumferential mucosal incision. Results The median specimen major axis length, ESD time, ESD speed, and en bloc resection rate were 48 mm, 84 minutes, 20 mm2/min, and 100 % (30/30), respectively. The success rates for the traction clip and median single-clip-traction time were 100 % (30/30) and 1.5 minutes, respectively. Conclusions Colorectal ESD using PCM-CT is a simple and promising method.

scholarly journals Adaptive Method for Modeling of Temporal Dependencies between Fields of Vision in Multi-Camera Surveillance Systems

Electronics ◽  
2021 ◽  
Vol 10 (11) ◽  
pp. 1303
Author(s):  
Karol Lisowski ◽  
Andrzej Czyżewski
Keyword(s):  
Statistical Data ◽  
Input Parameter ◽  
Gaussian Mixture ◽  
Adaptive Method ◽  
Transition Time ◽  
Surveillance Systems ◽  
Modified Particle Swarm Optimization ◽  
Novel Approach ◽  
Transition Times ◽  
Temporal Dependencies

A method of modeling the time of object transition between given pairs of cameras based on the Gaussian Mixture Model (GMM) is proposed in this article. Temporal dependencies modeling is a part of object re-identification based on the multi-camera experimental framework. The previously utilized Expectation-Maximization (EM) approach, requiring setting the number of mixtures arbitrarily as an input parameter, was extended with the algorithm that automatically adapts the model to statistical data. The probabilistic model was obtained by matching to the histogram of transition times between a particular pair of cameras. The proposed matching procedure uses a modified particle swarm optimization (mPSO). A way of using models of transition time in object re-identification is also presented. Experiments with the proposed method of modeling the transition time were carried out, and a comparison between previous and novel approach results are also presented, revealing that added swarms approximate normalized histograms very effectively. Moreover, the proposed swarm-based algorithm allows for modelling the same statistical data with a lower number of summands in GMM.

Multi Object Detection and Tracking from Video File

2014 ◽  
Vol 533 ◽  
pp. 218-225 ◽  
Author(s):  
Rapee Krerngkamjornkit ◽  
Milan Simic
Keyword(s):  
Computer Vision ◽  
Background Subtraction ◽  
Moving Objects ◽  
Gaussian Mixture Models ◽  
Gaussian Mixture ◽  
Video Tracking ◽  
Partial Occlusion ◽  
Video File ◽  
Detection And Tracking ◽  
Over Time

This paper describes computer vision algorithms for detection, identification, and tracking of moving objects in a video file. The problem of multiple object tracking can be divided into two parts; detecting moving objects in each frame and associating the detections corresponding to the same object over time. The detection of moving objects uses a background subtraction algorithm based on Gaussian mixture models. The motion of each track is estimated by a Kalman filter. The video tracking algorithm was successfully tested using the BIWI walking pedestrians datasets [. The experimental results show that system can operate in real time and successfully detect, track and identify multiple targets in the presence of partial occlusion.

Sign in / Sign up

Export Citation Format

Share Document