Lucas-Kanade Algorithm Research Articles

CHEAT DETECTION IN ONLINE EXAMINATIONS USING ARTIFICIAL INTELLIGENCE

With increasing use of ICT and technical advancements in the education sector, distant and online education as well as examinations are being carried out frequently. However, online examination, as a method of assessment offers the risk of an unmonitored setting where students have full access to external resources. Online-proctored exams are the most efficient way for educational institutions to ensure academic honesty and ethics to counteract this. Typically, proctoring requires human assistance in the form of online proctors who remotely monitor students' performance. Yet, due to the rising demand for personnel and the intrusive nature of human proctoring, it is imperative to explore other areas. To tackle this pressing issue, this research work aims to devise a novel architecture that, through the development of a robust and automated Artificial Intelligence system, enables students to take exams remotely and reduces proctor involvement. The method overcomes the shortcomings of the previous automated proctoring system by combining important components of online exam cheating detection with cost-effective and efficient hardware. By proposing a Hybrid of FaceNet Model, Lucas Kanade Algorithm, and Active Appearance Model for Face Detection and Activity Monitoring of the student, the proposed system extracts semantic indicators to evaluate whether an applicant is cheating in an online examination. The proposed Cheat Detection system's experimental results measured via an F-score of 0.94 demonstrate its efficacy, and promising performance compared to the standard baseline techniques.

Brain-like position measurement method based on improved optical flow algorithm

In this paper, a brain-like navigation scheme based on fuzzy kernel C-means (FKCM) clustering assisted pyramid Lucas Kanade (LK) optical flow algorithm is developed to measure the position of vehicle. The Speed Cell and Place Cell in animals’ brain are introduced to construct the brain-like navigation mechanism which involves the optical flow method and image template matching to imitate the cells above-mentioned separately. To eliminate the singular values during optical flow calculation, the output of pyramid LK algorithm is clustered by FKCM algorithm firstly. Then, the velocity is calculated and integrated to get the position of the vehicle, and the brain-like navigation scheme is introduced to correct the position measurement errors by eliminating the accumulated errors resulting from velocity integration. The prominent advantages of the presented method are: (i) a pure visual brain-like position measurement method based on the concept of speed cells and place cells is proposed, making visual navigation more accurate and intelligent; (ii) the FKCM algorithm is used to eliminate the singular value of the pyramid LK algorithm, which improves the calculated velocity accuracy. Also, experimental comparison with classical pyramid LK algorithm is given to illustrate the superiority of the proposed method in position measurement.

Dynamic displacement measurement of hoisting rope in lateral and longitudinal direction by improving Lucas–Kanade algorithm

The hoisting rope has complex dynamic characteristics under external excitation during operation, characterized by large longitudinal movement and minor lateral oscillation. However, there are no appropriate approaches to acquire the dynamic displacement of the rope currently. In this study, a fast vision-based measurement framework, including initial value forecast (IVF) and target tracking based on Lucas–Kanade (LK) algorithm, called IVF-LK, is proposed to obtain the lateral-longitudinal displacement of the rope. Firstly, an IVF method is proposed to obtain the initial value of iteration, overcoming the problem of non-convergence of LK algorithm under large displacement. Secondly, a parameter update strategy makes the convergence speed of LK significantly improved. Then, the performance of IVF-LK algorithm was tested in the experimental bench, which reveal its superior capacity in rope-structure dynamic measurement both in efficiency and precision. Finally, a field experiment was implemented to analyze the dynamic displacement of the hoisting rope.

Detection of clouds in multiple wind velocity fields using ground-based infrared sky images

To improve the performance of an intra-hour global solar irradiance forecasting algorithm, it is important to detect multiple layers of clouds. Horizontal atmospheric wind shear causes wind velocity fields to have different directions and speeds. In images of clouds acquired using ground-based sky imagers, clouds may be moving in different wind layers. The information provided by a solar forecasting algorithm is necessary to optimize and schedule the solar generation resources and storage devices in a smart grid. This investigation studies the performance of unsupervised learning techniques when detecting the number of cloud layers in infrared sky images. The images are acquired using an innovative infrared sky imager mounted on a solar tracker. Different mixture models are used to infer the distribution of the cloud features. Multiple Bayesian metrics and a sequential hidden Markov model are implemented to find the optimal number of clusters in the mixture models, and their performances are compared. The motion vectors are computed using a probabilistic implementation of the Lucas-Kanade algorithm. The correlations between the cloud motion vectors and temperatures are analyzed to discover the method that leads to the most accurate results. The findings point that a sequential hidden Markov model outperforms the detection accuracy of standard Bayesian model selection metrics.

Application of optical flow algorithm for drift correction in electron microscopy images.

Transmission electron microscopy (TEM) image drift correction has been effectively addressed using diverse approaches, including the cross correlation algorithm (CC) and other strategies. However, most of the strategies fall short of achieving sufficient accuracy or cannot strike a balance between time consumption and accuracy. The present study proposes a TEM image drift correction strategy that enhances accuracy without any additional time consumption. Unlike the CC algorithm that matches pixels one by one, our approach involves the extraction of multiple feature points from the first TEM image and then uses the Lucas-Kanade (LK) optical flow algorithm to calculate the optical field of these feature points in the subsequent TEM images. The LK algorithm is used to calculate the instantaneous velocity of these feature points, which can help track the movement of the TEM image series. In addition, a high-precision sub-pixel level correction strategy by the utilization of linear interpolation during the correction process is developed in this work. Experimental results confirm that this strategy offers superior accuracy in comparison with the CC algorithm and also is insensitive to the size of the image. Furthermore, we offer a semantic segmentation neural network for electron microscope image pre-processing, thereby expanding the applicability of our methodology.

Strain Prediction Using Deep Learning during Solidification Crack Initiation and Growth in Laser Beam Welding of Thin Metal Sheets

The strain field can reflect the initiation time of solidification cracks during the welding process. The traditional strain measurement is to first obtain the displacement field through digital image correlation (DIC) or optical flow and then calculate the strain field. The main disadvantage is that the calculation takes a long time, limiting its suitability to real-time applications. Recently, convolutional neural networks (CNNs) have made impressive achievements in computer vision. To build a good prediction model, the network structure and dataset are two key factors. In this paper, we first create the training and test sets containing welding cracks using the controlled tensile weldability (CTW) test and obtain the real strain fields through the Lucas–Kanade algorithm. Then, two new networks using ResNet and DenseNet as encoders are developed for strain prediction, called StrainNetR and StrainNetD. The results show that the average endpoint error (AEE) of the two networks on our test set is about 0.04, close to the real strain value. The computation time could be reduced to the millisecond level, which would greatly improve efficiency.

A spatiotemporal attention network-based analysis of golden pompano school feeding behavior in an aquaculture vessel

Behavior analysis and recognition of fish school have substantial management value and optimization implications for many aquaculture activities, such as feeding, which is currently the most expensive and polluting element of the aquaculture process. However, fish school behaviors analysis for complex marine environments is an extremely challenging task. Recent developments in artificial intelligence have demonstrated that Deep-Learning techniques can be ideally adapted for behavior analysis. Seeing such prospects, a spatiotemporal attention network (STAN) was proposed in this study to analyse the feeding states and behaviors of golden pompano school. Specifically, spatial images and optical flow images were created from videos using image processing techniques and the Lucas–Kanade algorithm. STAN was then used to extract intuitive and perceptual features from the intuitive channel and perceptual channel, respectively. Finally, the states of Feeding or Non-Feeding of the golden pompano school were established by the fusing channel with LSTM and Fully–connected networks. To evaluate the performance of the proposed method, quantitative and qualitative experiments were conducted. Results showed that STAN outperformed other models with a test accuracy of 97.97%. Further validation on a genuine golden pompano farming vessel was implemented, showing that the STAN architecture delivers state-of-the-art accuracy in the task of analysing feeding behavior for golden pompano school in aquaculture.

Vision-Based Measurement for the Transverse–Longitudinal–Rotational Displacement of Hoisting Rope by Modified Lucas–Kanade Algorithm

Vision-Based Measurement for the Transverse–Longitudinal–Rotational Displacement of Hoisting Rope by Modified Lucas–Kanade Algorithm

Abnormal Crowd Behavior Detection Using Optimized Pyramidal Lucas-Kanade Technique

Abnormal behavior detection is challenging and one of the growing research areas in computer vision. The main aim of this research work is to focus on panic and escape behavior detections that occur during unexpected/uncertain events. In this work, Pyramidal Lucas Kanade algorithm is optimized using EMEHOs to achieve the objective. First stage, OPLKT-EMEHOs algorithm is used to generate the optical flow from MIIs. Second stage, the MIIs optical flow is applied as input to 3 layer CNN for detect the abnormal crowd behavior. University of Minnesota (UMN) dataset is used to evaluate the proposed system. The experimental result shows that the proposed method provides better classification accuracy by comparing with the existing methods. Proposed method provides 95.78% of precision, 90.67% of recall, 93.09% of f-measure and accuracy with 91.67%.

A Fast 3D/3D Registration Method Based on Water Equivalent Path Length for Heavy-Ion Radiotherapy

<h3>Purpose/Objective(s)</h3> The accuracy of patient setup needs to be high in heavy-ion radiotherapy. Accordingly, there is an increasing demand for three-dimensional (3D) image-guided systems because of the limitations of the present two-dimensional imaging registration technology. One of the limitations is the inability to directly compare with planning computed tomography (CT) images. Due to this uncertainty in conformation, high dose per fraction radiotherapy is difficult. This study proposes a fast 3D/3D registration method comparing with water equivalent path length (WEPL) that uses planning and treatment CT images to minimize range variations by using the Lucas-Kanade (LK) algorithm. <h3>Materials/Methods</h3> A six-degrees-of-freedom (6DOF) couch correction was simulated for patient positioning at our center by performing automatic rigid image registration (RIR) and using the resultant translation/rotation. Our automatic RIR algorithm was used to align the planning CT and treatment CT images, simulating 6DOF. The alignment values (Δ<i>V</i>), which represents a six-dimensional vector of the amounts of 6DOF couch movement, were calculated by minimizing the following error function: E(<i>ΔV</i>)=Σ <i>_i</i>_∈Ω [<i>T_i</i> (<i>V+ΔV</i>)-<i>P_i</i> (<i>V</i>)]², where <i>V</i> is a six-dimensional vector that denotes a CT position and rotation in a treatment room; <i>T_i</i> (<i>V</i>) and <i>P_i</i> (<i>V</i>) are treatment and planning CT images respectively, whose position in the room is represented by <i>V; i</i> is a 3D vector which denotes a point in the room; and Ω is a set of calculation points, which was assigned a planning target volume (PTV) of Ω in this study. We minimized the error function by using the LK algorithm. To minimize the range variations, each pixel value of the CT images was changed into WEPL values and the alignment values were calculated in the same manner as the above algorithm. The method was evaluated using a dataset containing eight prostate cancer patient images, including a planning CT image with PTV and treatment CT images of four fraction with a fan-beam CT. The range variations were measured by calculating WEPL variations between the planning CT and treatment CT at (1) before registration and after registration based on (2) CT pixel values and (3) WEPL values, respectively. In addition, the calculation time was measured on a workstation with a single GPU. <h3>Results</h3> The mean WEL variation across the 32 cases (eight patients of four fractions) was (1) 1.8 ± 1.16 mm, (2) 1.08 ± 0.52 mm, and (3) 0.22 ± 0.17 mm. The worst WEPL variation were (1) 6.23 mm, (2) 3.06 mm, and (3) 1.17 mm. The mean calculation time were (2) 89 ms and (3) 1066 ms. <h3>Conclusion</h3> We developed a fast 3D/3D RIR method for reducing range variations to realize more accurate heavy-ion radiotherapy. We performed experiments involving eight prostate cancer patients, and our proposed method obtained high accuracy and short computation time.

An Improved Method for Estimating the Velocity Field of Coronal Propagating Disturbances

The solar corona is host to a continuous flow of propagating disturbances (PD). These are continuous and ubiquitous across broad regions of the corona, including the quiet Sun. The aim of this article is to present an improved, efficient method to create velocity vector field maps based on the direction and magnitude of the PD as observed in time series of extreme ultraviolet (EUV) images. The method presented here is for use with the Atmospheric Imaging Assembly (AIA)/Solar Dynamics Observatory (SDO) EUV channels and takes as input approx 2 hours of images at the highest 12 s cadence. Data from a region near disc centre is extracted, and a process called time normalisation is applied to the co-aligned data. Following noise reduction using à trous decomposition, the PD are effectively revealed. A modified Lucas–Kanade algorithm is then used to map the velocity field. The method described here runs comfortably on a desktop computer in a few minutes and offers an order of magnitude improvement in efficiency compared to a previous implementation. As applied to a region of the quiet Sun, we find that the velocity field describes a mosaic of cells of coherent outwardly-diverging PD flows of typical size 50 to 100'' (36 to 72 Mm). The flows originate from points and narrow corridors in the cell centres and end in the narrow boundaries between cells. Visual comparison with ultraviolet AIA images shows that the flow sources are correlated with the bright photospheric supergranular network boundaries. Assuming that the PD follow the local magnetic field, the velocity flow field is a proxy for the plane-of-sky distribution of the coronal magnetic field, and therefore the maps offer a unique insight into the topology of the corona. These are particularly valuable for quiet Sun regions where the appearance of structures in EUV images is hard to interpret.

Gray consistency optical flow algorithm based on mask-R-CNN and a spatial filter for velocity calculation.

The optical flow method has been widely used to measure the vehicle velocity by observing the stationary ground with a camera looking-down. However, when there are moving objects on the stationary ground, the interfering optical flow field will be generated, which decreases the velocity measurement accuracy of a vehicle relative to the ground. In order to reduce the effects caused by moving objects, this paper integrates pyramid Lucas-Kanade (LK) algorithm with the gray consistency method to use the information of color images thoroughly. First, a mask region with convolutional neural network (Mask-R-CNN) is used to recognize the objects that have motions relative to the ground, and it covers them with masks to enhance the similarity between pixels and to reduce the impacts of the noisy moving pixels. Then images are decomposed into three channels, red, green, and blue (i.e., R, G, and B), and processed by median filter. Based on the gray consistency method, the optical flow can be obtained by the pyramid LK algorithm. Finally, the velocity is calculated by the optical flow value. The prominent advantages of the proposed algorithm are: (i) increase the velocity measurement accuracy of a vehicle relative to the ground; (ii) use the information of color images acquired with cameras thoroughly and obtain velocity calculation outputs with less fluctuation; (iii) reduce wrong values caused by noises that are from the origin image and introduced by similar color masks. Four experiments are conducted to test the proposed algorithm and results with superior precision and reliability show the feasibility and effectiveness of the proposed method for the velocity measurement accuracy of a vehicle relative to the ground.

Accurate Realtime Motion Estimation Using Optical Flow on an Embedded System

Motion estimation has become one of the most important techniques used in realtime computer vision application. There are several algorithms to estimate object motions. One of the most widespread techniques consists of calculating the apparent velocity field observed between two successive images of the same scene, known as the optical flow. However, the high accuracy of dense optical flow estimation is costly in run time. In this context, we designed an accurate motion estimation system based on the calculation of the optical flow of a moving object using the Lucas–Kanade algorithm. Our approach was applied on a local treatment region implemented into Raspberry Pi 4, with several improvements. The efficiency of our accurate realtime implementation was demonstrated by the experimental results, showing better performance than with the conventional calculation.

Feature Point Extraction and Motion Tracking of Cardiac Color Ultrasound under Improved Lucas-Kanade Algorithm.

The purpose of this research is to study the application effect of Lucas–Kanade algorithm in right ventricular color Doppler ultrasound feature point extraction and motion tracking under the condition of scale invariant feature transform (SIFT). This study took the right ventricle as an example to analyze the extraction effect and calculation rate of SIFT algorithm and improved Lucas–Kanade algorithm. It was found that the calculation time before and after noise removal by the SIFT algorithm was 0.49 s and 0.46 s, respectively, and the number of extracted feature points was 703 and 698, respectively. The number of feature points extracted by the SIFT algorithm and the calculation time were significantly better than those of other algorithms (P < 0.01). The mean logarithm of the matching points of the SIFT algorithm for order matching and reverse order matching was 20.54 and 20.46, respectively. The calculation time and the number of feature points for the SIFT speckle tracking method were 1198.85 s and 81, respectively, and those of the optical flow method were 3274.19 s and 80, respectively. The calculation time of the SIFT speckle tracking method was significantly lower than that of the optical flow method (P < 0.05), and there was no statistical difference in the number of feature points between the SIFT speckle tracking method and the optical flow method (P > 0.05). In conclusion, the improved Lucas–Kanade algorithm based on SIFT significantly improves the accuracy of feature extraction and motion tracking of color Doppler ultrasound, which shows the value of the algorithm in the clinical application of color Doppler ultrasound.

Augmented Reality Objek Wisata Bogor Menggunakan Algoritma Lucas Kanade Dengan Metode Marker Based Tracking

Information technology today, is very developed and easy to find. Especially in information on Bogor tourist attractions such as the Bogor Palace, Tugu Kujang, and Pakansari Stadium. However, the data information held is not completely valid. Because many tourists get data that is not suitable, due to the lack of information obtained. Therefore, the researchers tried to make an android-based "Tourism Object in Bogor" application using Augmented Reality (AR) technology and the Lucas Kanade Algorithm, as well as Marker Based Tracking efforts to make it easier to get the information desired by tourism. Bogor is one of the cities in West Java Province that attracts many tourists, especially domestic tourists. However, there are still many tourist attractions in Bogor that are still many tourist attractions that have not been visited and are still not widely known by tourists. Until now, researchers have tried to make an android-based "Tourism Object in Bogor" application so that tourists know the shape of objects and information such as the Bogor Palace, Tugu Kujang, and Pakansari Stadium. Using Augmented Reality (AR) technology, the technology itself has photos, sounds, and 3d objects that can bring virtual 3d objects into the real world. The "Tourism Object in Bogor" application uses Android Studio, Unity, Sketchup, Vuforia, and Visual Studio. In order to make it easier for tourists to identify data on tourist attractions they want to visit. The application "Tourism Objects in Bogor" serves to share data information for local and foreign tourists, because this is an opportunity for the Bogor Regional Government to improve services and facilities in Bogor, so that tourists feel safe arriving and visiting Bogor.

An Action Recognition Algorithm for Sprinters Using Machine Learning

The advancements in modern science and technology have greatly promoted the progress of sports science. Advanced technological methods have been widely used in sports training, which have not only improved the scientific level of training but also promoted the continuous growth of sports technology and competition results. With the development of sports science and the gradual deepening of sport practices, the use of scientific training methods and monitoring approaches has improved the effect of sports training and athletes’ performance. This paper takes sprint as the research problem and constructs the image of sprinter’s action recognition based on machine learning. In view of the shortcomings of traditional dual-stream convolutional neural network for processing long-term video information, the time-segmented dual-stream network, based on sparse sampling, is used to better express the characteristics of long-term motion. First, the continuous video frame data is divided into multiple segments, and a short sequence of data containing user actions is formed by randomly sampling each segment of the video frame sequence. Next, it is applied to the dual-stream network for feature extraction. The optical flow image extraction involved in the dual-stream network is implemented by the system using the Lucas–Kanade algorithm. The system in this paper has been tested in actual scenarios, and the results show that the system design meets the expected requirements of the sprinters.

Development and performance assessment of an advanced Lucas-Kanade algorithm for dose mapping of cervical cancer external radiotherapy and brachytherapy plans.

PurposeThe aim of this study was to verify the possibility of summing the dose distributions of combined radiotherapeutic treatment of cervical cancer using the extended Lucas‐Kanade algorithm for deformable image registration.Materials and methodsFirst, a deformable registration of planning computed tomography images for the external radiotherapy and brachytherapy treatment of 10 patients with different parameter settings of the Lucas‐Kanade algorithm was performed. By evaluating the registered data using landmarks distance, root mean square error of Hounsfield units and 2D gamma analysis, the optimal parameter values were found. Next, with another group of 10 patients, the accuracy of the dose mapping of the optimized Lucas‐Kanade algorithm was assessed and compared with Horn‐Schunck and modified Demons algorithms using dose differences at landmarks.ResultsThe best results of the Lucas‐Kanade deformable registration were achieved for two pyramid levels in combination with a window size of 3 voxels. With this registration setting, the average landmarks distance was 2.35 mm, the RMSE was the smallest and the average gamma score reached a value of 86.7%. The mean dose difference at the landmarks after mapping the external radiotherapy and brachytherapy dose distributions was 1.33 Gy. A statistically significant difference was observed on comparing the Lucas‐Kanade method with the Horn‐Schunck and Demons algorithms, where after the deformable registration, the average difference in dose was 1.60 Gy (P‐value: 0.0055) and 1.69 Gy (P‐value: 0.0012), respectively.ConclusionLucas‐Kanade deformable registration can lead to a more accurate model of dose accumulation and provide a more realistic idea of the dose distribution.

Improvement of a face recognition method for high jumper with a single sample based on Lucas-Kanade algorithm

In order to improve the identification accuracy of a dynamic single sample, a face recognition method based on Lucas-Kanade algorithm is proposed. The weighted Lucas-Kanade (LK) algorithm is used to obtain the single-sample affine transformation parameters of the high jumper's side face block and the corresponding front face block, and the optimal parameters of face pose correction are found through the maximum Gabor similarity, the method of face recognition for high jumper with a single sample is completed. Simulation results show that both the front face recognition rate and side-face recognition rate of the proposed method can reach more than 95% and the face recognition recall rate of the proposed method ranges from 90% to 100%. Compared with the traditional method, the recall rate has been significantly improved. In addition, when there are 440 face images, the recognition time is 1,177 ms, which is shorter than the traditional method.

Improvement of a face recognition method for high jumper with a single sample based on Lucas-Kanade algorithm

Improvement of a face recognition method for high jumper with a single sample based on Lucas-Kanade algorithm

A Vision Based approach for Fall Detection System for Elderly People

There is a surge in the aging population, it is important for doctors and guardians to be conscious of issues related to health, which could impact majorly to the health of the elderly. Falling is one of the significant concerns that lead to fatal health problems in the case of the older population. The proposed system is especially for elderly people who are living alone in their homes or for old age homes. A vision-based fall detection approach has been used below in a home environment. A UR dataset of kinetic sensor’s output videos is used which classify into two categories i.e. fall and activities of daily living which are considered for experimentation. The MOG2 algorithm is used for background subtraction to focus on the human object and ignore the rest of the surrounding environment. The Shi Tomasi algorithm is used for finding interest points that are tracked using the optical flow method: Lucas-Kanade algorithm. Using interest points we compute its maximum displacement along with direction and speed of motion. For fall activity the last positions of interest points were observed. So the system detects a person in the environment, keeps tracking the person, and calculates the optical flow in case of a fall. If the fall is above the threshold point, an alert is sent to the concerned people and medical authorities.