Search results

Skeleton plays an important role in representing the essential feature of garment in image. General skeleton extraction methods often yield many short skeletal branches. Though short branches reflect the geometric details of the garment, they are obstacles in extracting the essential features. The purpose of this paper is to provide an approach to hierarchically remove them to reveal the level of details (LOD) of the skeleton, thus both the essential skeleton and the geometric skeletal branches can be definitely extracted and separated.

First, the initial garment image skeleton is extracted and smoothed. Then, the hierarchically removing mechanism is established on scoring the importance of each skeletal branch by an altered PageRank method and computing the symmetry among skeletal branches.

Experimental examples show that this method can extract and separate garment essential skeleton as well as geometric skeletal branches hierarchically. Garments in same class have a similar essential skeleton with detailed differences, so this approach can be potentially applied in garment recognition and style specification.

Traditionally, there is almost no work attempts to build LOD in skeleton of planar shapes. This paper provide an automatic device for building LOD skeleton for garment image. In another word, hierarchic skeletons with details in different prominence level are gradually established. And pairs of symmetric skeletal parts are found by taking advantage of symmetry characteristic of garment. This method is efficient in garment image skeleton extraction.

To remanufacture a disused part, a hybrid process needs to be taken in part production. Therefore, a reasonable machining route is necessary to be developed for the hybrid process. This paper aims to develop a novel process planning algorithm for additive and subtractive manufacturing (ASM) system to achieve this purpose.

First, a skeleton of the model is generated by using thinning algorithm. Then, the skeleton tree is constructed based on topological structure and shape feature. Further, a feature matching algorithm is developed for recognizing the different features between the initial model and the final model based on the skeleton tree. Finally, a reasonable hybrid machining route of the ASM system is generated in consideration of the machining method of each different sub-feature.

This paper proposes a hybrid process planning algorithm for the ASM system. Further, it generates new process planning insights on the hybrid process service provider market.

The proposed process planning algorithm enables engineers to obtain a proper hybrid machining route before product fabrication. And thereby, it extends the machining capability of the hybrid process to manufacture some parts accurately and efficiently.

This study addresses one gap in the hybrid process literature. It develops the first hybrid process planning strategy for remanufacturing of disused parts based on skeleton tree matching, which generates a more proper hybrid machining route than the currently available hybrid strategy studies. Also, this study provides technical support for the ASM system to repair damaged parts.

The purpose of this paper is to propose an automatic interpolation method for binarized confocal laser scanning microscopy (CLSM) images of a premotor neuron in the silkworm moth.

Partial deficiencies occur in binary images through the form extraction process because of noises in a CLSM image series. The proposed method selects several points from a binarized image series and connects these points with a Bezier curve based on premotor neuron characteristics in order to interpolate partial deficiencies.

To verify the availability of the proposed method, a three‐dimensional form of a premotor neuron of a silkworm moth was extracted. The results of each branch's relation of connection and of the interpolated neuron thickness show that the proposed method realizes to interpolate partial deficiencies and to extract three‐dimensional form of the premotor neuron.

The proposed method contributes to realize efficient premotor extraction process using image‐processing techniques. The extracted result by proposed method can be utilized for the form comparison among many data of the premotor neurons quickly. Moreover, it also contributes to provide the parameters of an accurate neuron model for realizing computer simulation of electrical of the neurons.

The proposed method extracts not only a topological form but also a premotor neuron's thickness by interpolating partial deficiencies based on specific characteristics of the neuron. Thickness values of the neuron are an important factor for a simulating accurate electrical response of the neuronal circuit.

It is a challenge to print a model with the size that is larger than the working volume of a three-dimensional (3D) printer. The purpose of this paper is to present a feasible approach to divide a large model into small printing parts to fit the volume of a printer and then assemble these parts into the final model.

The proposed approach is based on the skeletonization and the minima rule. The skeleton of a printing model is first extracted using the mesh contraction and the principal component analysis. The 3D model is then partitioned preliminarily into many smaller parts using the space sweep method and the minima rule. The preliminary partition is finally optimized using the greedy algorithm.

The skeleton of a 3D model can effectively represent a simplified version of the geometry of the 3D model. Using a model’s skeleton to partition the model is an efficient way. As it is generally desirable to have segmentations at concave creases and seams, the cutting position should be located in the concave region. The proposed approach can partition large models effectively to well retain the integrity of meaningful parts.

The proposed approach is new in the rapid prototyping field using the model skeletonization and the minima rule. Based on the authors’ knowledge, there is no method that concerns the integrity of meaningful parts for partitioning. The proposed method can achieve satisfactory results by the integrity of meaningful parts and assemblability for most 3D models.

As a means of data acquisition for the situation awareness, computer vision-based motion capture technologies have increased the potential to observe and assess manual activities for the prevention of accidents and injuries in construction. This study thus aims to present a computationally efficient and robust method of human motion data capture for the on-site motion sensing and analysis.

This study investigated a tracking approach to three-dimensional (3D) human skeleton extraction from stereo video streams. Instead of detecting body joints on each image, the proposed method tracks locations of the body joints over all the successive frames by learning from the initialized body posture. The corresponding body joints to the ones tracked are then identified and matched on the image sequences from the other lens and reconstructed in a 3D space through triangulation to build 3D skeleton models. For validation, a lab test is conducted to evaluate the accuracy and working ranges of the proposed method, respectively.

Results of the test reveal that the tracking approach produces accurate outcomes at a distance, with nearly real-time computational processing, and can be potentially used for site data collection. Thus, the proposed approach has a potential for various field analyses for construction workers’ safety and ergonomics.

Recently, motion capture technologies have rapidly been developed and studied in construction. However, existing sensing technologies are not yet readily applicable to construction environments. This study explores two smartphones as stereo cameras as a potentially suitable means of data collection in construction for the less operational constrains (e.g. no on-body sensor required, less sensitivity to sunlight, and flexible ranges of operations).

To find a successful human action recognition system (HAR) for the unmanned environments.

This paper describes the key technology of an efficient HAR system. In this paper, the advancements for three key steps of the HAR system are presented to improve the accuracy of the existing HAR systems. The key steps are feature extraction, feature descriptor and action classification, which are implemented and analyzed. The usage of the implemented HAR system in the self-driving car is summarized. Finally, the results of the HAR system and other existing action recognition systems are compared.

This paper exhibits the proposed modification and improvements in the HAR system, namely the skeleton-based spatiotemporal interest points (STIP) feature and the improved discriminative sparse descriptor for the identified feature and the linear action classification.

The experiments are carried out on captured benchmark data sets and need to be analyzed in a real-time environment.

The middleware support between the proposed HAR system and the self-driven car system provides several other challenging opportunities in research.

The authors’ work provides the way to go a step ahead in machine vision especially in self-driving cars.

The method for extracting the new feature and constructing an improved discriminative sparse feature descriptor has been introduced.

The primary objective of this study is to tackle the enduring challenge of preserving feature integrity during the manipulation of geometric data in computer graphics. Our work aims to introduce and validate a variational sparse diffusion model that enhances the capability to maintain the definition of sharp features within meshes throughout complex processing tasks such as segmentation and repair.

We developed a variational sparse diffusion model that integrates a high-order L₁ regularization framework with Dirichlet boundary constraints, specifically designed to preserve edge definition. This model employs an innovative vertex updating strategy that optimizes the quality of mesh repairs. We leverage the augmented Lagrangian method to address the computational challenges inherent in this approach, enabling effective management of the trade-off between diffusion strength and feature preservation. Our methodology involves a detailed analysis of segmentation and repair processes, focusing on maintaining the acuity of features on triangulated surfaces.

Our findings indicate that the proposed variational sparse diffusion model significantly outperforms traditional smooth diffusion methods in preserving sharp features during mesh processing. The model ensures the delineation of clear boundaries in mesh segmentation and achieves high-fidelity restoration of deteriorated meshes in repair tasks. The innovative vertex updating strategy within the model contributes to enhanced mesh quality post-repair. Empirical evaluations demonstrate that our approach maintains the integrity of original, sharp features more effectively, especially in complex geometries with intricate detail.

The originality of this research lies in the novel application of a high-order L₁ regularization framework to the field of mesh processing, a method not conventionally applied in this context. The value of our work is in providing a robust solution to the problem of feature degradation during the mesh manipulation process. Our model’s unique vertex updating strategy and the use of the augmented Lagrangian method for optimization are distinctive contributions that enhance the state-of-the-art in geometry processing. The empirical success of our model in preserving features during mesh segmentation and repair presents an advancement in computer graphics, offering practical benefits to both academic research and industry applications.

Periodic inspection and maintenance are essential for effective pavement preservation. Cracks not only affect the appearance of the road and reduce the levelness, but also shorten the life of road. However, traditional road crack detection methods based on manual investigations and image processing are costly, inefficiency and unreliable. The research aims to replace the traditional road crack detection method and further improve the detection effect.

In this paper, a crack detection method based on matrix network fusing corner-based detection and segmentation network is proposed to effectively identify cracks. The method combines ResNet 152 with matrix network as the backbone network to achieve feature reuse of the crack. The crack region is identified by corners, and segmentation network is constructed to extract the crack. Finally, parameters such as the length and width of the cracks were calculated from the geometric characteristics of the cracks and the relative errors with the actual values were 4.23 and 6.98% respectively.

To improve the accuracy of crack detection, the model was optimized with the Adam algorithm and mixed with two publicly available datasets for model training and testing and compared with various methods. The results show that the detection performance of our method is better than many excellent algorithms, and the anti-interference ability is strong.

This paper proposed a new type of road crack detection method. The detection effect is better than a variety of detection algorithms and has strong anti-interference ability, which can completely replace traditional crack detection methods and meet engineering needs.

Crack detection of pavement is a critical task in the periodic survey. Efficient, effective and consistent tracking of the road conditions by identifying and locating crack contributes to establishing an appropriate road maintenance and repair strategy from the promptly informed managers but still remaining a significant challenge. This research seeks to propose practical solutions for targeting the automatic crack detection from images with efficient productivity and cost-effectiveness, thereby improving the pavement performance.

This research applies a novel deep learning method named TransUnet for crack detection, which is structured based on Transformer, combined with convolutional neural networks as encoder by leveraging a global self-attention mechanism to better extract features for enhancing automatic identification. Afterward, the detected cracks are used to quantify morphological features from five indicators, such as length, mean width, maximum width, area and ratio. Those analyses can provide valuable information for engineers to assess the pavement condition with efficient productivity.

In the training process, the TransUnet is fed by a crack dataset generated by the data augmentation with a resolution of 224 × 224 pixels. Subsequently, a test set containing 80 new images is used for crack detection task based on the best selected TransUnet with a learning rate of 0.01 and a batch size of 1, achieving an accuracy of 0.8927, a precision of 0.8813, a recall of 0.8904, an F1-measure and dice of 0.8813, and a Mean Intersection over Union of 0.8082, respectively. Comparisons with several state-of-the-art methods indicate that the developed approach in this research outperforms with greater efficiency and higher reliability.

The developed approach combines TransUnet with an integrated quantification algorithm for crack detection and quantification, performing excellently in terms of comparisons and evaluation metrics, which can provide solutions with potentially serving as the basis for an automated, cost-effective pavement condition assessment scheme.

The aim of this paper is to develop autonomous mobile home healthcare robots, which are capable of observing patients’ motions, recognizing the patients’ behaviours based on observation data, and providing automatically calling for medical personnel in emergency situations. The robots to be developed will bring about cost‐effective, safe and easier at‐home rehabilitation to most motor‐function impaired patients (MIPs).

The paper has developed following programs/control algorithms: control algorithms for a mobile robot to track and follow human motions, to measure human joint trajectories, and to calculate angles of lower limb joints; and algorithms for recognizing human gait behaviours based on the calculated joints angle data.

A Hidden Markov Model (HMM) based human gait behaviour recognition taking lower limb joint angles and body angle as input was proposed. The proposed HMM based gait behaviour recognition is compared with the Nearest Neighbour (NN) classification methods. Experimental results showed that a human gait behaviour recognition using HMM can be achieved from the lower limb joint trajectory with higher accuracy than compared classification methods.

The research addresses human motion tracking and recognition by a mobile robot. Human gait behaviour recognition is HMM based lower limb joints and body angle data from extracted from kinect sensor at the mobile robot.