Frame Difference Method Research Articles

Research on Sintering Machine Axle Fault Detection Based on Wheel Swing Characteristics

During the sintering process in iron production, wheel swing is a sign of sintering machine trolley axle faults, which may lead to the wheel falling off and affect the production operation of the sintering machine system in serious cases. To solve this problem, this paper proposes a fault detection and localization method based on the You Only Look Once version 9 (YOLOv9) object detection algorithm and frame difference method for detecting sintering machine trolley wheel swing. The wheel images transmitted from the camera were sent to a trolley wheel and side panel number detection model that was trained on YOLOv9 for recognition. The wheel recognition boxes of the previous and subsequent frames were fused into the wheel region of interest. In the wheel region of interest, the difference operation was carried out. The result of the difference operation was compared with the preset threshold to determine whether the trolley wheel swings. When a wheel swing fault occurs, the image of the side plate at the time of the fault is collected, and the number on the side plate is identified so as to accurately locate the faulty trolley and to assist the field personnel in troubleshooting the fault. The experimental results show that this method can detect wheel swing faults in the industrial field, and the detection accuracy of wheel swing faults was 93.33%. The trolley side plate numbers’ average precision was 99.2% in fault localization. Utilizing the aforementioned method to construct a system for detecting wheel swing can provide technical support for fault detection of the trolley axle on the sintering machine.

Pengolahan Citra Berbasis Video Proccesing dengan Metode Frame Difference untuk Deteksi Gerak

This study discusses the detection of motion of objects in video by utilizing the Frame difference method which aims to process video so as to produce Frames on moving objects. The use of mobile cameras produces video data that is used as test data, the test data is processed with the Frame difference method so as to produce a number of Frames on moving objects in order to detect moving objects in the video because the function of this method is a form of video background reduction that is simplified by a number of pixels in the video. This method process is based on the difference between two consecutive frames in the video aimed at finding differences that occur during the detection process. When processed for detection, the absolute value in the pixel is greater than the predetermined threshold value, it will be considered as a moving object, so that the detection results from the motion detection process will form a box object on the moving object. In this study, the test data used used 20 video data samples with descriptions, 10 test data with bright quality (daytime) and 10 unlit test data (night) with the aim of being able to see how much the level of performance accuracy of the Frame difference method. The test results obtained 16 out of 20 test data that were successfully detected correctly (True Positive), there were 2 test data that resulted in a False Positive error, and 2 test data that resulted in a False Negative error. This shows that the Frame difference method can provide a fairly high level of accuracy in detecting moving objects in the video. The percentage level of accuracy with confussion matrix testing has a precission value of 88%, recal 88% and an accuracy value of 80%.

Long-term video activity monitoring and anomaly alerting of group-housed pigs

The activity level of group-housed pigs can reflect their daily behavioral patterns and health conditions. Currently, most pig farms mainly rely on manual daily patrols to monitor the activities of group-housed pigs, which is labor-intensive and inaccurate. In this paper, we propose a computer vision-based method for the automatic monitoring and alerting of group-housed pigs activity anomaly. We established a pig segmentation model based on an improved Mask R-CNN incorporating the CBAM attention mechanism and CIoU loss function for segmenting pigs from video frames. The CBAM attention mechanism enables the model to focus more effectively on target regions, while CIoU loss function guides precise learning of object boundaries, outperforming the traditional IoU loss. Grounded on the segmentation results, we invocated a frame difference method to quantify the activity level of group-housed pigs. Subsequently, we adopted the K-means clustering algorithm to explore the daily behaviors of these pigs. Furthermore, we constructed a SARIMA model using historical data to proactively forecast potential shifts in activity levels. The experimental results demonstrated that the accuracy and recall rate of the pig instance segmentation model were 98.7% and 97.9%, respectively. The SARIMA model performed well in predicting activity levels of group-housed pigs with differing health status. For the pig herds under healthy status, the Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) were 6.01 and 7.67 respectively, while for the pig herds under unhealthy status, the MAE and RMSE were 6.41 and 9.30 respectively. We proposed an effectively method to monitor daily behavioral patterns and anomalies of group-housed pigs, providing valuable references for pig farm management.

Photothermal effect in X-ray images for computed tomography of metallic parts: Stainless steel spheres.

The environmental impact on industrial X-ray tomography systems has gained its attention in terms of image precision and metrology over recent years, yet is still complex due to the variety of applications. The current study explores the photothermal repercussions of the overall radiation exposure time. It shows the emerging dimensional uncertainty when measuring a stainless steel sphere by means of circular tomography scans. The authors develop a novel frame difference method for X-ray radiographies to evaluate the spatial changes induced in the projected absorption maps on the X-ray panel. The object of interest has a simple geometry for the purpose of proof of concept. The dominant source of the observed radial uncertainty is the photothermal effect due to high-energy X-ray scattering at the metal workpiece. Thermal variations are monitored by an infrared camera within the industrial tomography system, which confines that heat in the industrial grade X-ray system. The authors demonstrate that dense industrial computed tomography programs with major X-ray power notably affect the uncertainty of digital dimensional measurements. The registered temperature variations are consistent with dimensional changes in radiographies and hence form a source of error that might result in visible artifacts within the 3D image reconstruction. This contribution is of fundamental value to reach the balance between the number of projections and radial uncertainty tolerance when performing analysis with X-ray dimensional exploration in precision measurements with industrial tomography.

An Expository Examination of Temporally Evolving Graph-Based Approaches for the Visual Investigation of Autonomous Driving

With the continuous advancement of autonomous driving technology, visual analysis techniques have emerged as a prominent research topic. The data generated by autonomous driving is large-scale and time-varying, yet more than existing visual analytics methods are required to deal with such complex data effectively. Time-varying diagrams can be used to model and visualize the dynamic relationships in various complex systems and can visually describe the data trends in autonomous driving systems. To this end, this paper introduces a time-varying graph-based method for visual analysis in autonomous driving. The proposed method employs a graph structure to represent the relative positional relationships between the target and obstacle interferences. By incorporating the time dimension, a time-varying graph model is constructed. The method explores the characteristic changes of nodes in the graph at different time instances, establishing feature expressions that differentiate target and obstacle motion patterns. The analysis demonstrates that the feature vector centrality in the time-varying graph effectively captures the distinctions in motion patterns between targets and obstacles. These features can be utilized for accurate target and obstacle recognition, achieving high recognition accuracy. To evaluate the proposed time-varying graph-based visual analytic autopilot method, a comparative study is conducted against traditional visual analytic methods such as the frame differencing method and advanced visual analytic methods like visual lidar odometry and mapping. Robustness, accuracy, and resource consumption experiments are performed using the publicly available KITTI dataset to analyze and compare the three methods. The experimental results show that the proposed time-varying graph-based method exhibits superior accuracy and robustness. This study offers valuable insights and solution ideas for developing deep integration between intelligent networked vehicles and intelligent transportation. It provides a reference for advancing intelligent transportation systems and their integration with autonomous driving technologies.

Smart-sight: Video-based waste characterization for RDF-3 production

A material recovery facility (MRF) can transform municipal solid waste (MSW) into a valued commodity called refuse-derived fuel (RDF) as a promising solution to waste-to-energy conversion. The quality of the produced RDF significantly relies on the composition of in-feed waste and waste characterization method applied for auditing purposes, a process that is both time-consuming and fraught with potential hazards. This study focuses to enhance the workflow of the waste characterization process at an MRF. A solution named Smart Sight is proposed to detect and classify waste based on videos recorded after processing MSW through a mechanical sorting line consisting of bag breakers and trommel screens. A comprehensive dataset is created encompassing thirteen mixed waste classes from single and multi-family streams. The dataset is preprocessed with motion compensation techniques and frame differencing methods to extract and refine valuable frames. A one-stage YOLO detector model is then trained over the dataset. The experimental results show that the proposed method works efficiently at detecting and classifying waste objects in indoor MRF environments. Accuracy, precision, recall, and F1 score related to the proposed solution are found to be 0.70, 0.762, 0.69 and 0.72, respectively, with a mAP@0.5 of 0.716. The proposed approach is validated using data collected from local MRF by comparing the estimated waste composition values of the proposed solution with laboratory results obtained through current standardized industrial practices. Comparison reveals that waste characterization estimation obtained is consistent with the laboratory results, inferring that Smart-Sight is a viable tool for estimating waste composition.

Moving Object Detection Method Based on the Fusion of Online Moving Window Robust Principal Component Analysis and Frame Difference Method

The accuracy of moving object detection has a great impact on the accuracy of extracting the shape center coordinates of moving workpieces. The classic inter-frame difference method has "cavity" and "double shadow" issues for workpieces with comparable internal colors. In order to solve this problem, a moving object detection algorithm combining the three-frame difference method and Online Moving Window Robust Principal Component Analysis (OMWRPCA) is proposed. By using the OMWRPCA to extract the background image in the current frame and comparing it to the previous and current frames, the "cavity" and "double shadow" problems are avoided as well as the effects of background pixels. This paper presents a case study of a visual sorting experiment bench in an "intelligent manufacturing production demonstration line". The experiments show that the workpiece shape center coordinates obtained by the improved moving object detection algorithm are closer to the actual value than those obtained by the traditional algorithm, and the F-measure scores are above 0.8, which are more accurate than the other two algorithms. It is compared with the traditional algorithm of the frame difference method and the Online Mixture of Gaussian Matrix Factorization (OMoGMF).

Vehicle Speed Detection using Haar Cascade Classifier and Correlation Tracking

Objectives: The aim of this study is to develop an efficient and cost-effective solution for predicting vehicle speeds using recorded video data. Methods: The proposed system employs a combination of image processing techniques and computer vision to calibrate cameras for traffic simulation, enabling the extraction of information on average vehicle speeds. It utilizes the Haar Cascade Classifier for object detection, followed by a correlation tracker for vehicle tracking. Speed estimation is achieved through the frame differencing method. The dataset comprises 90 minutes of recorded data from highway cameras, showcasing diverse traffic scenarios with various vehicle types (trucks, trailers, cars, buses, and bikes) at varying speeds. Predicted values are compared with ground truth data obtained from a GPS-equipped car, using Mean Absolute Error (MAE) as the evaluation metric. Findings: The algorithm's performance is evaluated, resulting in an average error rate of 1.72 km/h (2.07%). These findings are compared with state-of-the-art data. Novelty: This study introduces a novel system that combines the Haar Cascade Classifier, correlation tracker, and frame differencing method to track vehicle positions, incorporating bike detection into the analysis, and calculate their moving speeds. A relative analysis underscores the system's performance, emphasizing its effectiveness in real-world applications and demonstrating refinement in accuracy assessment. Keywords: Image processing, Vehicle speed estimation, Haar Cascade Classifier, Correlation tracker, Error rate calculation, Computer vision

Quantification and correlation analysis of bubble characteristics and heat transfer performance in direct contact heat exchanger

In this work, a combination of morphological processing and watershed algorithm is proposed to measure bubble size, based on which an improved frame difference method is proposed to obtain bubble velocities with an F1 score of 0.96. Empirical equations for the boiling properties of flow in immiscible fluids and their influencing factors are developed. Correlation equations for the Nusselt (Nu) number and Colburn (j) factor are developed, with mean deviations of 5.42% and 5.47%, respectively. The results show that the increase in bubble rise rate and the trend of bubble growth become slower with the increase in the flow rate of the dispersed phase. In contrast, the temperature of the continuous phase has a negative correlation on the bubble growth and almost no effect on the bubble velocity. In addition, the heat transfer coefficient, which increases with the increase of the flow rate of the dispersed phase, has a negative correlation with the initial temperature difference. The main objective of this study is to provide a new method for measuring bubble parameters during direct contact boiling heat transfer and to provide new ideas for studying direct contact boiling heat transfer.

An Improved Vibe Algorithm Based on Adaptive Thresholding and the Deep Learning-Driven Frame Difference Method

Foreground detection is the main way to identify regions of interest. The detection effectiveness determines the accuracy of subsequent behavior analysis. In order to enhance the detection effect and optimize the problems of low accuracy, this paper proposes an improved Vibe algorithm combining the frame difference method and adaptive thresholding. First, we adopt a shallow convolutional layer of VGG16 to extract the lower-level features of the image. Features images with high correlation are fused into a new image. Second, adaptive factors based on the spatio-temporal domain are introduced to divide the foreground and background. Finally, we construct an inter-frame average speed value to measure the moving speed of the foreground, which solves the mismatch problem between background change rate and model update rate. Experimental results show that our algorithm can effectively solve the drawback of the traditional method and prevent the background model from being contaminated. It suppresses the generation of ghosting, significantly improves detection accuracy, and reduces the false detection rate.

Fast and accurate semantic segmentation of road crack video in a complex dynamic environment

ABSTRACT This paper proposes a fast and accurate semantic segmentation of road crack video in a complex dynamic environment. First, a fast key frame selection algorithm is designed by combining the interframe dissimilarity constrained video frame difference method (FDM) and shot interval sampling method (SISM). Second, the complex and dynamic characteristics of application scenarios are studied, and a high-precision crack semantic segmentation DBPNet containing a densely diverse branch module (DDBM) and diverse branch pyramid module (DBPM) is proposed, which can not only focus on the local aggregation of the same scale feature but also fuse and reconstruct long-distance related semantic features. Finally, a dynamic video data set of cracks in complex environments, including multiple types of interference, different weather and lighting is established, and experimental analysis is carried out. The results show that the proposed method can improve the efficiency of video crack detection by 5–7 times compared to the method without using key frames, and the detection accuracy can reach 72.85%, which can adapt to dynamic video changes in a variety of complex scenes. The proposed network, DBPNet, outperforms the current state-of-the-art methods in road crack semantic segmentation on challenging data sets in terms of both Dice and MIOU.

Face Recognition of Remote Teaching Video Image Based on Improved Frame Difference Method

Face Recognition of Remote Teaching Video Image Based on Improved Frame Difference Method

Automatic identification and analysis of multi-object cattle rumination based on computer vision.

Rumination in cattle is closely related to their health, which makes the automatic monitoring of rumination an important part of smart pasture operations. However, manual monitoring of cattle rumination is laborious and wearable sensors are often harmful to animals. Thus, we propose a computer vision-based method to automatically identify multi-object cattle rumination, and to calculate the rumination time and number of chews for each cow. The heads of the cattle in the video were initially tracked with a multi-object tracking algorithm, which combined the You Only Look Once (YOLO) algorithm with the kernelized correlation filter (KCF). Images of the head of each cow were saved at a fixed size, and numbered. Then, a rumination recognition algorithm was constructed with parameters obtained using the frame difference method, and rumination time and number of chews were calculated. The rumination recognition algorithm was used to analyze the head image of each cow to automatically detect multi-object cattle rumination. To verify the feasibility of this method, the algorithm was tested on multi-object cattle rumination videos, and the results were compared with the results produced by human observation. The experimental results showed that the average error in rumination time was 5.902% and the average error in the number of chews was 8.126%. The rumination identification and calculation of rumination information only need to be performed by computers automatically with no manual intervention. It could provide a new contactless rumination identification method for multi-cattle, which provided technical support for smart pasture.

基于YOLOX的群养猪只异常检测

In order to solve the problem that the complex pig house environment leads to the difficulty and low accuracy of abnormal detection of group pigs. The video of 9 adult fattening pigs were collected, and the video key frames were obtained by the frame differential method as the training set, and the YOLOX model for abnormal detection of group pigs was constructed. The results show that the average accuracy of YOLOX model on the test set is 98.0%. The research results can provide a reference for the detection of pig anomalies in the breeding environment of pig farms.

A new machine vision detection method for identifying and screening out various large foreign objects on coal belt conveyor lines

Large foreign object transporting by coal mine conveyor belt may lead to production safety hazards. To reduce safety accidents during coal mining, a large foreign object detection method based on machine vision is proposed in this paper. An adaptive weighted multi-scale Retinex (MSR) image enhancement algorithm is proposed to improve the captured image quality of the belt conveyor line. An improved multi-scale template matching algorithm is designed by combining the frame difference and area methods to screen and identify large foreign objects mixed in coals. The multi-layer perceptron (MLP) network optimized by the Gray Wolf algorithm is introduced to identify the large objects. Experimental results show that the identification accuracy reaches 98.8% for the large foreign objects. Furthermore, industrial field test is carried out in the Gaoyang coal mine, and the filed test results demonstrate that the identification accuracy of the proposed method is more than 95%. Hence, the proposed method meets the industrial detection requirements and can be used in practices for detecting the large foreign objects.

Security Camera Implementation System on Smart Home Using Web-Based Frame Difference Methods

The development of technology in the field of security has a big impact on people's lives throughout the world. The security is threatened when there is a burglary in the neighborhood. One of the applications of image processing is the frame difference method, which used comparison of the captured image frame circuit according to time order. Frame difference algorithm applied to grayscale image computing using ESP32-CAM cameras for security cameras. This research was developed with a system that can monitor objects detected in real-time by streaming using a website. The ESP32-CAM camera and the PC have a packet loss value of 4.29% and an average delay of 0.3 seconds so that the images captured by the camera can be well received by the PC. The frame difference method with moving objects is used and detected well during the day due to solar lighting, but at night only depends on luminous objects. This method has the disadvantage that when moving objects inhabit the same field of view, the system will define it as movement so that the frame difference method is not adaptive from changes in the captured area.

Temporal aggregation network using micromotion features for early lameness recognition in dairy cows

Lameness severely affects dairy cow welfare and potential milk production while reducing dairy farm economics. Most existing computer vision-based lameness recognition methods extract a single class of lameness features, and it is difficult to accurately recognize early lameness in dairy cows with only slight gait abnormalities. In this paper, a temporal aggregation network using micromotion features is proposed, which can capture micromotion features and spatiotemporal features to recognize early lameness in dairy cows. First, a Gaussian filter is used to remove noise in videos of a dairy cow walking. Second, frame-difference images containing motion features are constructed by the frame-difference method. Third, micromotion features in the frame-difference images are extracted using the designed focal convolutional layer. Fourth, the acquired micromotion feature sequence is input into temporal attention mechanisms to extract multigranularity temporal features. Finally, a fully connected layer is used to classify the dairy cow lameness. To evaluate the performance of the proposed model, 621 videos were randomly selected from 888 videos as training videos, 87 videos were randomly selected as validation videos, and the remaining 180 videos were selected as test videos. The lameness recognition accuracy of the proposed model was 98.89%, which was better than state-of-the-art lameness recognition methods. The experimental results showed that the proposed model can extract the micromotion features and multigranularity temporal features in the frame-difference images, thereby improving the early lameness recognition accuracy in dairy cows.

Detection and Tracking of Infrared Small Targets in Complex Dynamic Backgrounds by Using Image Registration and Pipeline Filter

This paper propses an infrared small target detection method in complex dynamic backgrounds in sequence images by using image registration and pipeline filter. For dynamic scenes caused by camera movements, registration of image frames and reference frame images is conducted by using the feature point matching algorithm. Next, the frame difference method is used to detect small mobile target in video image sequences. Finally, the impact of ground clutter noise and random noise are eliminated by using a pipeline filter to precisely track the trajectory of small moving targets. The experiment results show that the proposed method is superior to the classic infrared small target detection algorithm in terms of accuracy and stability in complex ground backgrounds.

Small Low-Contrast Target Detection: Data-Driven Spatiotemporal Feature Fusion and Implementation.

Detecting small low-contrast targets in the airspace is an essential and challenging task. This article proposes a simple and effective data-driven support vector machine (SVM)-based spatiotemporal feature fusion detection method for small low-contrast targets. We design a novel pixel-level feature, called a spatiotemporal profile, to depict the discontinuity of each pixel in the spatial and temporal domains The spatiotemporal profile is a local patch of the spatiotemporal feature maps concatenated by the spatial feature maps and temporal feature maps in channelwise, which are generated by the morphological black-hat filter and a ghost-free dark-focusing frame difference methods, respectively. Instead of the handcrafted feature fusion mechanisms in previous works, we use the labeled spatiotemporal profiles to train an SVM classifier to learn the spatiotemporal feature fusion mechanism automatically. To speed up detection for high-resolution videos, the serial SVM classification process on central processing units (CPUs) is reformed as parallel convolution operations on graphics processing unit (GPUs), which exhibits over 1000+ times speedup in our real experiments. Finally, blob analysis is applied to generate final detection results. Elaborate experiments are conducted, and experimental results demonstrate that the proposed method performs better than 12 baseline methods for the small low-contrast target detection. The field tests manifest that the parallel implementation of the proposed method can realize real-time detection at 15.3 FPS for videos at a resolution of 2048×1536 and the maximum detection distance can reach 1 km for drones in sunny weather.

Measurement of the Attenuation Coefficient in Fresh Water Using the Adjacent Frame Difference Method

The attenuation coefficient of a water body is one of the important factors for describing its features. However, its remote measurement in real time is still a challenge. In this paper, we demonstrated a novel method to realize real-time remote measurements of the attenuation coefficient of fresh water using flash imaging lidar based on the adjacent frame difference (AFD) method and a water body backscattering model. In general, we firstly investigated the relationship between the backscattering intensity and the attenuation coefficient based on the backscattering model of the water body. Then, the backscattering intensity at the front and back edges of the range-gate obtained by the AFD method was brought into this relationship to obtain the attenuation coefficient. Experiments on the measurements of the average attenuation coefficient of the 532 nm laser in fresh water at 3–8 m were further carried out using our self-developed flash lidar with the AFD method. The acquired water attenuation coefficients were 0.1334±0.02 and 0.1382±0.03 with a delay step time of 1 ns and 2 ns in the AFD method, respectively. We compared these values to the one achieved following the conventional Beer–Lambert law (0.1330±0.02), and they matched well with each other. These results fully illustrated the feasibility and reliability of the proposed method for measuring the attenuation coefficient of water bodies.