Study of road scene monotony evaluation method based on video processing technique

With the rapid development of modern video technology, the range of video applications is increasing, such as online video conferencing, online classroom, online medical, etc. However, due to the quantity of video data is large, video has to be compressed and encoded appropriately, but the encoding process may cause some distortions on video quality. Therefore, how to evaluate the video quality efficiently and accurately is essential in the fields of video processing, video quality monitoring and multimedia video applications. In this article, subjective, and comprehensive evaluation method of video quality were introduced, a video quality assessment system was completed, four ITU recommended videos were encoded and evaluated by Degradation Category Rating (DCR) and Structural Similarity (SSIM) methods using five different formats. After that, comprehensive evaluations with weights were applied. Results show that data of all three evaluations have good consistency; H.264 is the best encoding method, followed by Xvid and wmv8; the higher the encoding bit rate is, the better the evaluations are, but comparing to 1000kbps, the subjective and objective evaluation scores of 1400kbps couldn’t improve obviously. The whole process could also evaluate new encodings methods, and is applicable for high-definition video, finally plays a significant role in promoting the video quality evaluation and video encoding.

Download Full-text

Dial Instrument Calibration by both Automatic and Half-Automatic Methods

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.157-158.581 ◽

2012 ◽

Vol 157-158 ◽

pp. 581-588

Author(s):

Zhen Long Bai ◽

Xiang Li

Keyword(s):

Video Processing ◽

Processing Technique ◽

Automatic Calibration ◽

Automatic Method ◽

Edge Extraction ◽

Calibration System ◽

Practical Application ◽

Instrument Calibration ◽

Different Types ◽

Automatic Methods

This paper presents a calibration system by video processing technique. The system can calibrate large number of different types of dial instruments. The system is composed of an automatic recog-nition approach and a half-automatic approach. Both the automatic calibration and half-automatic calibration include four steps: 1st, dial plane circle edge extraction and center identification; 2nd, pointer extraction; 3rd, scale start and end position identification; 4th, result reading. For half-automatic method, the 1st step and 3rd step are manually indentified. By experiments and practical application in industry, it proves that our calibration system is effective for more than hundreds of different types of dial instruments.

Download Full-text

GPU Accelerated real-time Melanoma Detection

International Journal of Engineering & Technology ◽

10.14419/ijet.v7i3.13169 ◽

2018 ◽

Vol 7 (3) ◽

pp. 1208

Author(s):

Ajai Sunny Joseph ◽

Elizabeth Isaac

Keyword(s):

Real Time ◽

Video Processing ◽

Processing Technique ◽

Video Data ◽

Image Processing Technique ◽

Processing Unit ◽

Central Processing ◽

Melanoma Detection ◽

Real Time Analysis ◽

Graphical Processing

Melanoma is recognized as one of the most dangerous type of skin cancer. A novel method to detect melanoma in real time with the help of Graphical Processing Unit (GPU) is proposed. Existing systems can process medical images and perform a diagnosis based on Image Processing technique and Artiﬁcial Intelligence. They are also able to perform video processing with the help of large hardware resources at the backend. This incurs signiﬁcantly higher costs and space and are complex by both software and hardware. Graphical Processing Units have high processing capabilities compared to a Central Processing Unit of a system. Various approaches were used for implementing real time detection of Melanoma. The results and analysis based on various approaches and the best approach based on our study is discussed in this work. A performance analysis for the approaches on the basis of CPU and GPU environment is also discussed. The proposed system will perform real-time analysis of live medical video data and performs diagnosis. The system when implemented yielded an accuracy of 90.133% which is comparable to existing systems.

Download Full-text

Early Smoke Detection on Video Using Wavelet Energy

Indonesian Journal on Computing (Indo-JC) ◽

10.21108/indojc.2017.2.2.180 ◽

2017 ◽

Vol 2 (2) ◽

pp. 79 ◽

Cited By ~ 1

Author(s):

Muhammad Zulfiqar Shafar ◽

Tjokorda Agung Budi Wirayuda ◽

Febryanti Sthevanie

Keyword(s):

Spatial Analysis ◽

Video Processing ◽

Detection System ◽

Color Space ◽

Temporal Analysis ◽

Processing Technique ◽

Color Analysis ◽

Smoke Detection ◽

Wavelet Energy ◽

Spatio Temporal

<p>Most of the smoke detection system these days still using sensors that have to receive specific particles before it could give a warning. But, this system takes some time to react and quite difficult to place in spacious room or the outdoor. To overcome this, there is some research that build smoke detection system using many kind video processing technique that could provide early warning. In this research, wavelet energy was used to detect smoke in the video. To determine candidate blocks in a frame that contain smoke, this research performed background subtraction and color analysis based on HSV color space. Then implementing spatial analysis and spatio-temporal analysis by using wavelet energy method and accumulative motion orientation to detect the smoke. This system using combination of dataset from previous research [1], downloaded from various sources and self-made dataset. Based on testing process using those dataset, this system reaches 91.05% accuracy for block-level and 72.22% accuracy for frame-level.</p><strong>Keywords: </strong>Accumulative motion orientation, smoke detection, spatial analysis, spatio-temporal analysis, video processing, wavelet energy

Download Full-text

An Investigation into Dynamic Puncture Resistance of the Polyester Needled Nonwoven Geotextiles using Video Processing Technique

Autex Research Journal ◽

10.1515/aut-2017-0012 ◽

2018 ◽

Vol 18 (1) ◽

pp. 73-79 ◽

Cited By ~ 1

Author(s):

Zahra Dehghan-Banadaki ◽

Hasan Mashroteh ◽

Mohammad Saleh Ahmadi

Keyword(s):

Penetration Depth ◽

Video Processing ◽

Processing Technique ◽

Frame Rate ◽

Linear Regression Method ◽

Independent Variables ◽

Needle Penetration ◽

Significant Relationships ◽

Multiple Linear Regression Method ◽

Expansion Energy

AbstractIn this study, the dynamic puncture behavior of nonwoven needle-punched polyester geotextiles has been studied using video processing technique. Twenty-seven needle-punched geotextile samples were produced by changing areal weight, needle penetration depth and punch density as independent variables. Cone drop test was carried out on the samples. In addition to measuring the hole diameter (HD), the video processing technique with a high frame rate camera was employed to calculate the energy absorbed by geotextile fabric up to puncture point (Ep) and the hole expansion energy (Ee). Multiple linear regression method was used to develop the predicting relationships between independent and reply variables. The models showed that an increase in areal weight results in an increase in Ep, whereas it causes a decrease in Ee and HD. Moreover, increasing punch density and needle penetration depth, leads to less Ep, and more Ee and HD. In addition, it was also found that significant relationships exist for Ep-HD and Ee-HD.

Download Full-text

Evaluation of Beef Cattle Temperament Using Video Technology

Transactions of the ASABE ◽

10.13031/trans.14044 ◽

2020 ◽

Vol 63 (6) ◽

pp. 1905-1911

Author(s):

Xiaoming Chen ◽

William Ogdahl ◽

Md. Saidul Borhan ◽

Xin Sun

Keyword(s):

Beef Cattle ◽

Video Processing ◽

Evaluation Method ◽

Pearson Correlation ◽

Correlation Coefficients ◽

Processing Technology ◽

List Type ◽

Video Technology ◽

Movement Distance ◽

Field Deployment

HighlightsVideo processing technology was used to evaluate beef cattle temperament objectively.Multiple beef cattle temperament methods were compared with video processing technology.Potential automatic temperament evaluation systems could be developed based on our video processing method.Abstract. Cattle temperament has potential impacts on growth, carcass characteristics, and meat quality. Both objective and subjective methods have been used to assess temperament, such as temperament score (TS), docility score (DS), flight speed (FS), and exposed eye white percentage (EW). Subjective methods for evaluating cattle temperament are labor-intensive and potentially stressful for the animals. Video technology (VT) has advantages of being noninvasive, automated and remotely operable, and compatible with cloud-based complex algorithms, which facilitates immediate field deployment of results. Because VT has not been reported as a beef cattle temperament evaluation method, the objectives of this study were to (1) verify the feasibility of VT as an evaluation method for beef cattle temperament, and (2) assess the accuracy and reliability of the VT measurements in comparison with TS and DS. A total of 170 calves were video recorded while they were in a squeeze chute; simultaneously, DS and TS measurements of the same calves were conducted. Maximum movement distance (MMD), average movement distance (AMD), and moving frequency (MF) were calculated according to the distances measured from the videos using an algorithm developed in this research. Pearson correlation coefficients among MMD, AMD, MF, TS, and DS were calculated and were 0.264 (p < 0.001) for DS versus TS, 0.438 (p < 0.001) for MF versus TS, 0.017 (p = 0.838) for AMD versus DS, 0.107 (p = 0.192) for AMD versus TS, 0.058 (p = 0.481) for MMD versus DS, and 0.077 (p = 0.350) for MMD versus TS. This study showed that MF could be a good indicator for assessing cattle temperament coupled with VT as a quantitative tool, requiring minimal equipment and thus providing an objective method for selecting cattle with appropriate temperaments. Keywords: Beef cattle, Temperament, Video technology.

Download Full-text

Estimating Vocal Fold Contact Pressure from Raw Laryngeal High-Speed Videoendoscopy Using a Hertz Contact Model

Applied Sciences ◽

10.3390/app9112384 ◽

2019 ◽

Vol 9 (11) ◽

pp. 2384 ◽

Cited By ~ 4

Author(s):

Manuel E. Díaz-Cádiz ◽

Sean D. Peterson ◽

Gabriel E. Galindo ◽

Víctor M. Espinoza ◽

Mohsen Motie-Shirazi ◽

...

Keyword(s):

Contact Pressure ◽

Video Processing ◽

Vocal Fold ◽

High Speed ◽

Numerical Models ◽

Objective Assessment ◽

Direct Methods ◽

Vocal Folds ◽

Processing Technique ◽

Tissue Properties

The development of trauma-induced lesions of the vocal folds (VFs) has been linked to a high collision pressure on the VF surface. However, there are no direct methods for the clinical assessment of VF collision, thus limiting the objective assessment of these disorders. In this study, we develop a video processing technique to directly quantify the mechanical impact of the VFs using solely laryngeal kinematic data. The technique is based on an edge tracking framework that estimates the kinematic sequence of each VF edge with a Kalman filter approach and a Hertzian impact model to predict the contact force during the collision. The proposed formulation overcomes several limitations of prior efforts since it uses a more relevant VF contact geometry, it does not require calibrated physical dimensions, it is normalized by the tissue properties, and it applies a correction factor for using a superior view only. The proposed approach is validated against numerical models, silicone vocal fold models, and prior studies. A case study with high-speed videoendoscopy recordings provides initial insights between the sound pressure level and contact pressure. Thus, the proposed method has a high potential in clinical practice and could also be adapted to operate with laryngeal stroboscopic systems.

Download Full-text