Purpose To evaluate the postoperative changes with a computer vision algorithm for anterior full-face photographs of patients who have undergone upper eyelid blepharoplasty surgery with, or without, a Muller's mus...
详细信息
Purpose To evaluate the postoperative changes with a computer vision algorithm for anterior full-face photographs of patients who have undergone upper eyelid blepharoplasty surgery with, or without, a Muller's muscle-conjunctival resection (MMCR). Methods All patients who underwent upper eyelid blepharoplasty surgery (Group I), or upper eyelid blepharoplasty with MMCR (Group II) were included. Both preoperative and 6-month postoperative anterior full-face photographs of 55 patients were analyzed. computervision and image processing technologies were used to measure the palpebral distance (PD), eye-opening area (EA), and average eyebrow height (AEBH) for both eyes. Preoperative and postoperative measurements were calculated and compared between the two groups. Results In Group II, change in postoperative Right PD, Left PD, Right EA, Left EA was significantly higher than in Group I (p = 0.004 for REPD;p = 0.001 for LEPD;p = 0.004 for REA;p = 0.002 for LEA, p < 0.05). In Group II, the postoperative change in Right AEBH, Left AEBH was significantly higher than in Group I (p = 0.001 for RABH and LABH, p < 0.05). Conclusion Eyelid surgery for esthetic purposes requires artistic judgment and objective evaluation. Because of the slight differences in photograph sizes and dynamic factors of the face due to head movements and facial expressions, it is hard to compare and make a truly objective evaluation of the eyelid operations. With a computer vision algorithm, using the face and facial landmark detection system, the photographs are normalized and calibrated. This system offers a simple, standardized, objective, and repeatable method of patient assessment. This can be the first step of Artificial Intelligence algorithm to evaluate the patients who had undergone eyelid operations.
In modern industrial and engineering fields, fatigue detection of equipment and structures is an important link to ensure safety and extend service life. Traditional detection methods often rely on direct physical mon...
详细信息
In modern industrial and engineering fields, fatigue detection of equipment and structures is an important link to ensure safety and extend service life. Traditional detection methods often rely on direct physical monitoring, which has certain limitations. In recent years, infrared thermal radiation imaging technology has attracted wide attention because of its non-contact and high sensitivity. This study aims to explore a new fatigue detection method based on infrared thermal radiation images by combining optical fiber sensor and computer vision algorithm, so as to improve the accuracy and real-time performance of fatigue diagnosis. In this study, a fiber optic sensor is used to monitor strain data in real time by applying periodic loads to different material and structural samples in an experimental environment. At the same time, infrared thermal imaging camera was used to obtain the temperature distribution information of the material surface. The infrared thermal radiation image is combined with the sensor data, and the deep learning algorithm is used to extract the feature and identify the fatigue state. The experimental results show that the infrared thermal radiation image can effectively reflect the temperature change of the material in the fatigue process, and complement the mechanical information provided by the optical fiber sensor. Through the constructed computervision model, the classification accuracy of fatigue state is obviously better than the traditional detection means, which provides a new and effective method for fatigue detection, which can realize more efficient and accurate real-time monitoring, and has a wide application prospect.
Semi-flexible pavements (SFP) are extensively used in high-traffic zones owing to their outstanding resistance against rutting. Nonetheless, interface cracking persists as a prominent issue within SFP composites. This...
详细信息
Semi-flexible pavements (SFP) are extensively used in high-traffic zones owing to their outstanding resistance against rutting. Nonetheless, interface cracking persists as a prominent issue within SFP composites. This study establishes a finite element model of SFP using a computer vision algorithm to analyze its mechanical properties at the internal interface. Two interface components, namely the aggregate-asphalt and asphalt-grout interfaces, were developed to simulate stress distribution, crack initiation, and extension within the multiphase composite of SFP. The examination of transition zone properties within the asphalt-grout interface shed light on damage morphology and mechanical response. The results demonstrate that incorporating the interface layer significantly enhances the accuracy of force behavior analysis in simulating SFP materials. Furthermore, reinforcing the interface transition zone boosts the overall peak compressive strain strength of SFP materials in tandem with increased interface strength. Moreover, the grout joints and asphalt-grout interfaces within SFP act as vulnerable points where cracks propagate swiftly, leading to the detachment of cementitious grout from the base asphalt mixture.
In sports training and competition, the traditional methods of athlete posture monitoring often rely on complex equipment and expensive technology, which is difficult to be widely used. This study aims to explore a po...
详细信息
In sports training and competition, the traditional methods of athlete posture monitoring often rely on complex equipment and expensive technology, which is difficult to be widely used. This study aims to explore a posture monitoring and correction technology based on wireless sensing and computer vision algorithms to provide a low-cost, efficient and easy-to-use solution. In this study, wireless sensors are used to collect real-time data of athletes during training and competition, and computer vision algorithms are combined to analyze athletes' posture. The wireless sensors include an inertial measurement unit (IMU) that captures the athlete's movement trajectory and changes in Angle. Using computervision technology, the video images of athletes are obtained by cameras, and the posture recognition and dynamic analysis are carried out. Data fusion method combines sensor data with visual data to improve the accuracy and reliability of posture monitoring. The experimental results show that the posture monitoring system based on wireless sensing and computer vision algorithm can accurately identify and evaluate the athlete's posture. The system can feedback athletes' postural deviation in real time, provide effective correction suggestions, and significantly improve athletes' postural performance.
Japanese medaka (Oryzias latipes) is highly valuable in the field of monitoring the safety of drinking water. The previous study cannot extract the characteristics which can reflect the toxicity of water real-time and...
详细信息
ISBN:
(纸本)9781845648442;9781845648435
Japanese medaka (Oryzias latipes) is highly valuable in the field of monitoring the safety of drinking water. The previous study cannot extract the characteristics which can reflect the toxicity of water real-time and accurately. According to the shortcomings of the previous research, this paper discusses a new water toxicity monitoring system adopting a new observation from the bottom to top, and more effective computer vision algorithms simply. In order to effectively extract the features such as swimming speed changing, gills opening and closing, and pectoral fins and tail swing, we have used the automatic threshold segmentation, foreground extraction, classification, skeleton extraction, morphological and geometrical moment algorithm. The preliminary test results show that the hardware designing and algorithms for extracting the characteristic information of medaka are effective and feasible.
Plant density is useful variable that determines the fate of the wheat crop. The most commonly used method for plant density quantification is based on visual counting from ground level. The objective of this study is...
详细信息
Plant density is useful variable that determines the fate of the wheat crop. The most commonly used method for plant density quantification is based on visual counting from ground level. The objective of this study is to develop and evaluate a method for estimating wheat plant density at the emergence stage based on high resolution imagery taken from UAV at very low altitude with application to high throughput phenotyping in field conditions. A Sony ILCE alpha 5100L RGB camera with 24 Mpixels and equipped with a 60 mm focal length lens was flying aboard an hexacopter at 3 to 7 m altitude at about 1 m/s speed. This allows getting ground resolution between 0.20 mm to 0.45 mm, while providing 59-77% overlap between images. The camera was looking with 45 degrees zenith angle in a compass direction perpendicular to the row direction to maximize the cross section viewed of the plants and minimize the effect of the wind created by the rotors. Agisoft photoscan software was then used to derive the position of the cameras for each image. Images were then projected on the ground surface to finally extract subsamples used to estimate the plant density. The extracted images were first classified to separate the green pixels from the background and the rows were then identified and extracted. Finally, image object (group of connected green pixels) was identified on each row and the number of plants they contain was estimated using a Support Vector Machine whose training was optimized using a Particle Swarm Optimization. Three experiments were conducted in Greoux, Avignon and Clermont sites with some variability in the sowing dates, densities, genotypes, flight altitude, and growth stage at the time of the image acquisition. The application of the method on the 270 samples available over the three sites provides a RMSE and relative RMSE on estimates of 34.05 plants/m(2) and 14.31% with a bias of 9.01 plants/m(2). However, differences in performances were observed between the thre
This paper presents Specular Photometric Stereo (SPS), which is a Photometric Stereo (PS) technique incorporating specular reflection. The proposed SPS uses multiple images of a surface under different lighting condit...
详细信息
ISBN:
(纸本)9783030177980;9783030177973
This paper presents Specular Photometric Stereo (SPS), which is a Photometric Stereo (PS) technique incorporating specular reflection. The proposed SPS uses multiple images of a surface under different lighting conditions to obtain surface normals similarly to the conventional PS, but uniquely utilizes specular components of a dark surface, which reflects little diffuse light. The proposed framework consists of two sequential numerical steps, which are the conversion of a highly non-linear specular reflection model to a non-linear equation with only one non-linear parameter, and then the iterative removal of the diffuse components. The proposed SPS can estimate normals of dark surfaces, which is not possible by the conventional PS. The proposed SPS was examined using synthesized data and then tested with real-world surfaces. The results of surface normal estimation show that the capability of the proposed SPS over the existing PS in both accuracy and computational cost.
Image processing and computer vision algorithms extensively use projections, such as homography, as one of the processing steps. Systems for homography calculation usually observe homography as an inverse problem and ...
详细信息
ISBN:
(纸本)9781479960163
Image processing and computer vision algorithms extensively use projections, such as homography, as one of the processing steps. Systems for homography calculation usually observe homography as an inverse problem and provide an exact solution. However, the systems processing larger resolution images cannot meet inherently tight real-time constraints. Look-up table based systems provide an option for forward homography solutions, but they require large memory availability. Recent compressed look-up table methods reduce the memory requirements at the expense of lower peak signal-to-noise-ratio. In this work, we present a forward homography estimation algorithm which provides higher image quality than compressed look-up table methods. The algorithm is based on bounding the homography error, and neglecting the pixels out of the determined bound. The presented FPGA implementation of the estimation system requires a small amount of hardware, and no memory storage. The prototype system project an image frame onto a spherical surface at 295 Mpixels/s rate which is, up to our knowledge, currently the fastest homography system.
The assessment of gaze behaviour is essential for understanding the psychology of communication. Mobile eye-tracking glasses are useful to measure gaze behaviour during dynamic interactions. Eye-tracking data can be a...
详细信息
The assessment of gaze behaviour is essential for understanding the psychology of communication. Mobile eye-tracking glasses are useful to measure gaze behaviour during dynamic interactions. Eye-tracking data can be analysed by using manually annotated areas-of-interest. computer vision algorithms may alternatively be used to reduce the amount of manual effort, but also the subjectivity and complexity of these analyses. Using additional re-identification (Re-ID) algorithms, different participants in the interaction can be distinguished. The aim of this study was to compare the results of manual annotation of mobile eye-tracking data with the results of a computer vision algorithm. We selected the first minute of seven randomly selected eye-tracking videos of consultations between physicians and patients in a Dutch Internal Medicine out-patient clinic. Three human annotators and a computer vision algorithm annotated mobile eye-tracking data, after which interrater reliability was assessed between the areas-of-interest annotated by the annotators and the computer vision algorithm. Additionally, we explored interrater reliability when using lengthy videos and different area-of-interest shapes. In total, we analysed more than 65 min of eye-tracking videos manually and with the algorithm. Overall, the absolute normalized difference between the manual and the algorithm annotations of face-gaze was less than 2%. Our results show high interrater agreements between human annotators and the algorithm with Cohen's kappa ranging from 0.85 to 0.98. We conclude that computer vision algorithms produce comparable results to those of human annotators. Analyses by the algorithm are not subject to annotator fatigue or subjectivity and can therefore advance eye-tracking analyses.
In this paper, we present a case study on the transition to informed automated decision-making processes in smart agriculture. Our focus is on addressing the challenges posed by the new invasive global pest, Halyomorp...
详细信息
ISBN:
(纸本)9798350312720
In this paper, we present a case study on the transition to informed automated decision-making processes in smart agriculture. Our focus is on addressing the challenges posed by the new invasive global pest, Halyomorpha halys (HH), which causes significant economic damage to fruit orchards. Specifically, we aim to automate the time- and labor-intensive process of HH scouting, which is traditionally performed by phytosanitary operators. Our objective is to demonstrate the pipeline of technological and methodological decisions necessary for automating the scouting process. To gather images from the orchard, we utilized a drone equipped with an RGB camera as well as other devices such as smartphones. Despite the suboptimal quality of the images captured by the drone's camera, our computer vision algorithm for HH detection yields promising results. These findings serve as an encouragement to further explore the possibilities of technology transfer to the agriculture.
暂无评论