Dynamic Image Segmentation Research Articles

A novel multi-loss dynamic fusion-enhanced image segmentation model for welding spatter measurement

Quantitative detection of welding spatter is not only critical for evaluating and optimizing welding energy consumption, but also significant for improving welding quality. Inspired by the welder's visual estimation of the amount of spatter, a novel welding spatter measurement method based on image segmentation is proposed. Considering the challenges of welding spatter such as small object, aggregation, and unclear boundary, four loss functions, namely, Focal loss, Dice loss, Boundary loss, and Count loss, are designed to achieve global optimization for complex welding spatter. Furthermore, for the different spatter characteristics with different optimization difficulties, a multi-loss dynamic fusion method with differential optimization capability is designed. Finally, a welding spatter segmentation dataset is established and a comprehensive ablation and comparison test of the proposed methodology is carried out. The results indicate that the proposed method has an average F1-score metric of 83.52 % and a mean intersection over union metric of 75.11 %. These findings suggest the potential for vision-based quantitative estimation of welding spatter.

Surgical robot navigation based on SLAM technology

With the widespread application of surgical robots and the development of computer vision, SLAM-applicated surgery is receiving increasing attention. However, due to the unique surgical environment, SLAM faces some challenges. Two key issues will be discussed in this article: dynamic object detection and image segmentation, as well as scene reconstruction under data scarcity. Firstly, dynamic object detection and image segmentation is an important issue in SLAM applications. During the surgical process, doctors often use surgical instruments, which may partially or completely obscure the object, making it difficult to detect the target. Methods based on traditional feature matching may not be able to accurately detect dynamic targets perform image segmentation. Therefore, this article will combine semantic networks for analysis to improve the performance. In addition, scene reconstruction under data scarcity is another challenge in SLAM applications. Traditional SLAM methods typically rely on a large amount of feature points or map data. But in surgery, due to the complexity of occlusion and geometric structure, reliable data may not be easily obtained. This article will develop with the steps of reconstruction and analyze feasible methods that can improve the accuracy and stability of reconstruction. To conclude, this article will concentrate on these two issues, analyze recent papers, and ultimately summarize some feasible solutions, providing ideas and references for other researchers in this field.

Dynamic image segmentation and recognition measurement of axial compression experiment based on image clustering and semantic segmentation in RC column with FRP tubes

This paper introduces a dynamic image recognition and measurement method for Reinforced Concrete (RC) Column with Fiber Reinforced Polymer (FRP) tubes axial compression experiments based on image segmentation, which includes two image processing modes: clustering segmentation and semantic segmentation. The method uses image processing techniques to extract and segment the deformation of RC column with FRP tube in the axial compression experiment, enabling tracking and measurement of the axial deformation process. Both visual segmentation methods have undergone a series of processes including image preprocessing, image segmentation, deformation tracking measurement, system optimization, and deformation comparison and validation analysis. In order to evaluate the performance of the proposed method, the measurements obtained from the proposed methods are compared with the one using the linear variable differential transformer (LVDT). An experiment has been conducted with 9 groups in RC column with FRP tube to assess the performance of the proposed methods. The comparison with the LVDT measurements shows that standard deviation of the average maximum offset measured by the K-means clustering algorithm is 1.65 mm, and the mean relative error of measurement is 1.03 %; while the standard deviation of the average maximum offset measured by the U-Net semantic segmentation algorithm is 0.95 mm, and the mean relative error of measurement is 0.44 %. The results suggest that the U-Net semantic segmentation algorithm perform slightly better than the K-means clustering algorithm in deformation tracking measurement. Even in circumstances where traditional LVDT measurements failure due to equipment malfunctions or exceeding the measurement limits, the visual displacement measurement methods are still capable for providing consistent and reliable displacement data. In cases of human occlusion issues within the video, correction can be implemented using outlier frame removal techniques. Moreover, the visual measurement techniques are capable of distinguishing the deformation directions, i.e. deformation towards east or vice versa. The proposed method has potential application value in practical engineering applications and can provide effective technical support for axial compression experiments and deformation monitoring of reinforced concrete structures.

Damage detection method of automobile hub based on image texture feature

With the rapid growth in the number of motor vehicles worldwide, the general public is beginning to attach importance to the quality inspection of wheels before they leave the factory. The current wheel defect detection systems are often cumbersome to operate and have low practical performance. Therefore, this research will use dynamic image segmentation, image texture feature extraction and Back Propagation neural network classification based on wheel image defect feature analysis algorithm to achieve automatic intelligent detection of automotive wheel defects. In this study, an intelligent detection system for automotive wheel defects is also designed, and finally the performance of the detection system is tested experimentally to illustrate its practicality. The experimental results show that the proposed intelligent detection system for automotive wheel defects based on image texture features identifies defects in wheel castings with a correct rate of 96% and a false positive rate of only 2%. This illustrates that the detection system proposed in this study has a high recognition rate and can provide a useful reference for the automotive industry inspection.

Memory‐augmented neural networks based dynamic complex image segmentation in digital twins for self‐driving vehicle

With the continuous increase of the amount of information, people urgently need to identify the information in the image in more detail in order to obtain richer information from the image. This work explores the dynamic complex image segmentation of self-driving vehicle under Digital Twins (DTs) based on Memory-augmented Neural Networks (MANNs), so as to further improve the performance of self-driving in intelligent transportation. In view of the complexity of the environment and the dynamic changes of the scene in intelligent transportation, this work constructs a segmentation model for dynamic complex image of self-driving vehicle under DTs based on MANNs by optimizing the Deep Learning algorithm and further combining with the DTs technology, so as to recognize the information in the environment image during the self-driving. Finally, the performance of the constructed model is analyzed by experimenting with different image datasets (PASCALVOC 2012, NYUDv2, PASCAL CONTEXT, and real self-driving complex traffic image data). The results show that compared with other classical algorithms, the established MANN-based model has an accuracy of about 85.80%, the training time is shortened to 107.00 s, the test time is 0.70 s, and the speedup ratio is high. In addition, the average algorithm parameter of the given energy function α=0.06 reaches the maximum value. Therefore, it is found that the proposed model shows high accuracy and short training time, which can provide experimental reference for future image visual computing and intelligent information processing.

Dynamic Video Image Segmentation Based on Dual Channel Convolutional Kernel and Multi-Frame Feature Fusion.

The color image of the fire hole is key for the working condition identification of the aluminum electrolysis cell (AEC). However, the image of the fire hole is difficult for image segmentation due to the nonuniform distributed illuminated background and oblique beam radiation. Thus, a joint dual channel convolution kernel (DCCK) and multi-frame feature fusion (MFF) method is developed to achieve dynamic fire hole video image segmentation. Considering the invalid or extra texture disturbances in the edge feature images, the DCCK is used to select the effective edge features. Since the obtained edge features of the fire hole are not completely closed, the MFF algorithm is further applied to complement the missing portion of the edge. This method can assist to obtain the complete fire hole image of the AEC. The experiment results demonstrate that the proposed method has higher precision, recall rate, and lower boundary redundancy rate with well segmented image edge for the aid of working condition identification of the AEC.

Application Of Dynamic Segmentation In Stroke Detection Software With ANN

One way to find out whether there is a stroke is to do a CT scan . But the results of the examination with a new CT scan can be obtained in quite a long time. In addition, sometimes there are differences of opinion between doctors and radiologists regarding what is seen from the results of the examination. This research was conducted to produce a software that can later be integrated with the existing system on the CT Scan tool so that it can immediately be known whether or not stroke is present from the CT Scan results. In this study, a dynamic image segmentation method is implemented, namely the watershed transformation method which will later produce regions as a feature for the stroke detection process carried out with the backpropagation algorithm. From experiments conducted on CT scan images of the brain, this method can detect stroke well. The results obtained are 100% for training data and 90% for test data.

A New Dynamic Feature Extraction Method for Biometric Images

The image of biometric properties in humans is used in many fields today. Regardless of these features, it is necessary to first translate it into data that the computer understands. In this study, automatic and dynamic image segmentation was performed by using 300x300 fingerprint images. A fingerprint database with a total of 80 images and 10 different classes was used. The features of the images were subtracted from the sub-segments obtained from these images by the feature extraction algorithm that was originally developed. The 300x300 images were divided into 25x25 sub-images and the feature vector was obtained. 144x80 inputs obtained after image segmentation were kept in areas in separate tables. The developed segmentation and feature extraction algorithm can be applied to any image of equal size.

A Novel Dynamic Fingerprint Segmentation Method Based on Fuzzy C-Means and Genetic Algorithm

In automatic fingerprint identification system (AFIS), fingerprint segmentation plays a crucial role in improving detection accuracy and reducing the computation time of feature extraction. With the goal of refining performance of AFIS, in this paper, we investigate a novel dynamic fingerprint segmentation algorithm. The proposed algorithm is based on the existed dynamic image segmentation algorithm using fuzzy c-means (FCM) and genetic algorithm. Specifically, relying on different gray level of histogram and improved post-processing method, we establish a well-performed fingerprint segmentation system. The extensive results from our empirical experiments demonstrate the high performance of our proposed dynamic fingerprint segmentation algorithm, and its better performance than other competing approaches.

RETRACTED: Virtual scene dynamic interactive image segmentation technology based on OpenGL module

A virtual scene dynamic interactive image segmentation technology based on OpenGL sky module is proposed to improve the performance of image dynamic interactive recognition algorithm and the recognition effect of image segmentation. First, an automatic dynamic interactive image segmentation algorithm is proposed, a probability segmentation model of Gauss mixture fracture based on multi-scale crack enhancement filter is established, and expectation maximization algorithm is used to determine the parameters of GMM (Gaussian Mixture Model) and the underlying segmentation; second, the drawing function of OpenGL is used to draw the graph, and the drawing method needs to be calculated. That is to say, a mathematical model is established, which converts the graph into the calculation of vertex coordinates for drawing. It uses an extended cost function to guide dynamic interactive image segmentation using a set of cracks from the population to be segmented. Finally, the validity of the algorithm is verified by experimental simulation.

A robust segmentation method with triple-factor non-negative matrix factorization for myocardial blood flow quantification from dynamic 82 Rb positron emission tomography.

In this work, we proposed a triple-factor non-negative matrix factorization (TNMF) method to semiautomatically segment the regions of interest (ROIs) of the left ventricular (LV) cavity and myocardium to improve the reproducibility of myocardial blood flow (MBF) quantification from dynamic 82 Rb positron emission tomography (PET). The proposed TNMF method was evaluated using NCAT phantom simulation with three noise levels. The segmented ROIs, time-activity curves (TACs), and K1 derived from the TNMF method were compared with the ground truth simulated. The TNMF method was further evaluated in two patients each undergone both rest and stress 82 Rb PET studies. The TNMF and manual segmentations were implemented by two different observers, and the interoperator variations of MBF and myocardial flow reserve (MFR) were compared between the two methods. Our simulation results showed that the TNMF method for dynamic PET image segmentation was robust as evidenced by the high Dice similarity coefficient, regardless of high or low count level. The relative bias in K1 estimation was less than 1%. Our patient results also showed that reasonable ROIs for the LV cavity and myocardium could be obtained precisely for patients with and without myocardial perfusion defects. The TACs derived from the TNMF method were highly correlated with those obtained with the manual method (R2 ≥0.964). The interoperator variations of MBF and MFR were markedly reduced using the TNMF method. In conclusion, the TNMF method is highly feasible for semiautomatic segmentation of the LV cavity and myocardium, with the potential to improve the precision of MBF quantification by improving segmentation.

A Dynamic Flame Image Segmentation Method and Its Application in Video Monitoring of Fused Magnesium Furnace Process

A Dynamic Flame Image Segmentation Method and Its Application in Video Monitoring of Fused Magnesium Furnace Process

Dynamic Post-Earthquake Image Segmentation with an Adaptive Spectral-Spatial Descriptor

The region merging algorithm is a widely used segmentation technique for very high resolution (VHR) remote sensing images. However, the segmentation of post-earthquake VHR images is more difficult due to the complexity of these images, especially high intra-class and low inter-class variability among damage objects. Herein two key issues must be resolved: the first is to find an appropriate descriptor to measure the similarity of two adjacent regions since they exhibit high complexity among the diverse damage objects, such as landslides, debris flow, and collapsed buildings. The other is how to solve over-segmentation and under-segmentation problems, which are commonly encountered with conventional merging strategies due to their strong dependence on local information. To tackle these two issues, an adaptive dynamic region merging approach (ADRM) is introduced, which combines an adaptive spectral-spatial descriptor and a dynamic merging strategy to adapt to the changes of merging regions for successfully detecting objects scattered globally in a post-earthquake image. In the new descriptor, the spectral similarity and spatial similarity of any two adjacent regions are automatically combined to measure their similarity. Accordingly, the new descriptor offers adaptive semantic descriptions for geo-objects and thus is capable of characterizing different damage objects. Besides, in the dynamic region merging strategy, the adaptive spectral-spatial descriptor is embedded in the defined testing order and combined with graph models to construct a dynamic merging strategy. The new strategy can find the global optimal merging order and ensures that the most similar regions are merged at first. With combination of the two strategies, ADRM can identify spatially scattered objects and alleviates the phenomenon of over-segmentation and under-segmentation. The performance of ADRM has been evaluated by comparing with four state-of-the-art segmentation methods, including the fractal net evolution approach (FNEA, as implemented in the eCognition software, Trimble Inc., Westminster, CO, USA), the J-value segmentation (JSEG) method, the graph-based segmentation (GSEG) method, and the statistical region merging (SRM) approach. The experiments were conducted on six VHR subarea images captured by RGB sensors mounted on aerial platforms, which were acquired after the 2008 Wenchuan Ms 8.0 earthquake. Quantitative and qualitative assessments demonstrated that the proposed method offers high feasibility and improved accuracy in the segmentation of post-earthquake VHR aerial images.

Dynamic speckle image segmentation using self-organizing maps

The aim of this work is to build a computational model able to automatically identify, after training, dynamic speckle pattern regions with similar properties. The process is carried out using a set of descriptors applied to the intensity variations with time in every pixel of a speckle image sequence. An image obtained by projecting a self-organized map is converted into regions of similar activity that can be easily distinguished. We propose a general procedure that could be applied to numerous situations. As examples we show different situations: (a) an activity test in a simplified situation; (b) a non-biological example and (c) biological active specimens. The results obtained are encouraging; they significantly improve upon those obtained using a single descriptor and will eventually permit automatic quantitative assessment.

Discrete-Time Dynamic Image Segmentation Using Oscillators with Adaptive Coupling

In this study, we propose a novel discrete-time coupled model to generate oscillatory responses via periodic points with a high periodic order. Our coupled system comprises one-dimensional oscillators based on the Rulkov map and a single globally coupled oscillator. Because the waveform of a one-dimensional oscillator has sharply defined peaks, the coupled system can be applied to dynamic image segmentation. Our proposed system iteratively transforms the coupling of each oscillator based on an input value that corresponds to the pixel value of an input image. This approach enables our system to segment image regions in which pixel values gradually change with respect to a connected region. We conducted a bifurcation analysis of a single oscillator and a three-coupled model. Through simulations, we demonstrated that our system works well for gray-level images with three isolated image regions.

Dynamic image segmentation algorithm in 3D descriptions of remote sensing images

The dynamic image segmentation algorithm with multiple stepwise evaluation machines was applied to resultant the new boundary from image contents. The concept of data fusion is also discussed in th...

Real Time Decoding of Color Symbol for Optical Positioning System

This paper presents the design and real-time decoding of a color symbol that can be used as a reference marker for optical navigation. The designed symbol has a circular shape and is printed on paper using two distinct colors. This pair of colors is selected based on the highest achievable signal to noise ratio. The symbol is designed to carry eight bit information. Real time decoding of this symbol is performed using a heterogeneous combination of Field Programmable Gate Array (FPGA) and a microcontroller. An image sensor having a resolution of 1600 by 1200 pixels is used to capture images of symbols in complex backgrounds. Dynamic image segmentation, component labeling and feature extraction was performed on the FPGA. The region of interest was further computed from the extracted features. Feature data belonging to the symbol was sent from the FPGA to the microcontroller. Image processing tasks are partitioned between the FPGA and microcontroller based on data intensity. Experiments were performed to verify the rotational independence of the symbols. The maximum distance between camera and symbol allowing for correct detection and decoding was analyzed. Experiments were also performed to analyze the number of generated image components and sub-pixel precision versus different light sources and intensities. The proposed hardware architecture can process up to 55 frames per second for accurate detection and decoding of symbols at two Megapixels resolution. The power consumption of the complete system is 342mw.

Dynamic Image Segmentation for Sport Graphics Based on Wavelet Transform

In this paper, a image segmentation algorithm based on wavelet transform are presented. The proposed image segmentation algorithm performs the segmentation in the combined intensity-texture-position feature space in order to produce connected regions that correspond to the real-life objects shown in the image. This segmentation algorithm is applied to reduced versions of the original images in order to speed-up the completion of the segmentation. As shown by experimental evaluation, this novel scheme provides fast segmentation with high perceptual segmentation quality.

Dynamic Image Segmentation using Fuzzy CMeans based Genetic Algorithm

This paper describes an evolutionary approach for unsupervised gray-scale image segmentation that segments an image into its constituent parts automatically. The aim of this algorithm is to produce precise segmentation of images using intensity information along with neighborhood relationships. In this paper, fuzzy c-means clustering helps in generating the population of Genetic algorithm which there by automatically segments the image. This technique is a powerful method for image segmentation and works for both single and multiplefeature data with spatial information. Validity index has been utilized for introducing a robust technique for finding the number of components in an image. Experimental results shown that the algorithm generates good quality segmented image.

Discrete‐time dynamic image segmentation based on oscillations by destabilizing a fixed point

AbstractWe have developed a discrete‐time dynamical system consisting of a global inhibitor and chaotic neurons that can generate oscillatory responses. We have also found that our system can work as a dynamic image‐segmentation system utilizing oscillatory responses of chaotic neurons. Dynamic image segmentation is to severally extract isolated image regions from a static image and is to exhibit segmented images in time series according to oscillatory responses of chaotic neurons. At certain parameter values, chaotic neurons can generate adequate oscillatory responses for dynamic image segmentation. However, they generate non‐oscillatory responses for certain initial values due to the coexistence of a stable fixed point corresponding to non‐oscillatory responses. Their appearances indicate that our system does not work as a dynamic image‐segmentation system. In this study, we designed a destabilizer for a stable fixed point to prevent its appearance. We also demonstrated that our system with a designed destabilizer worked well. © 2011 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.