Search results

Single-shot multi-category clothing recognition and retrieval play a crucial role in online searching and offline settlement scenarios. Existing clothing recognition methods based on RGBD clothing images often suffer from high-dimensional feature representations, leading to compromised performance and efficiency.

To address this issue, this paper proposes a novel method called Manifold Embedded Discriminative Feature Selection (MEDFS) to select global and local features, thereby reducing the dimensionality of the feature representation and improving performance. Specifically, by combining three global features and three local features, a low-dimensional embedding is constructed to capture the correlations between features and categories. The MEDFS method designs an optimization framework utilizing manifold mapping and sparse regularization to achieve feature selection. The optimization objective is solved using an alternating iterative strategy, ensuring convergence.

Empirical studies conducted on a publicly available RGBD clothing image dataset demonstrate that the proposed MEDFS method achieves highly competitive clothing classification performance while maintaining efficiency in clothing recognition and retrieval.

This paper introduces a novel approach for multi-category clothing recognition and retrieval, incorporating the selection of global and local features. The proposed method holds potential for practical applications in real-world clothing scenarios.

Time of flight (ToF) imaging is a promising emerging technology for the purposes of crop identification. This paper aim to presents localization system for identifying and localizing asparagus in the field based on point clouds from ToF imaging. Since the semantics are not included in the point cloud, it contains the geometric information of other objects such as stones and weeds other than asparagus spears. An approach is required for extracting the spear information so that a robotic system can be used for harvesting.

A real-time convolutional neural network (CNN)-based method is used for filtering the point cloud generated by a ToF camera, allowing subsequent processing methods to operate over smaller and more information-dense data sets, resulting in reduced processing time. The segmented point cloud can then be split into clusters of points representing each individual spear. Geometric filters are developed to eliminate the non-asparagus points in each cluster so that each spear can be modelled and localized. The spear information can then be used for harvesting decisions.

The localization system is integrated into a robotic harvesting prototype system. Several field trials have been conducted with satisfactory performance. The identification of a spear from the point cloud is the key to successful localization. Segmentation and clustering points into individual spears are two major failures for future improvements.

Most crop localizations in agricultural robotic applications using ToF imaging technology are implemented in a very controlled environment, such as a greenhouse. The target crop and the robotic system are stationary during the localization process. The novel proposed method for asparagus localization has been tested in outdoor farms and integrated with a robotic harvesting platform. Asparagus detection and localization are achieved in real time on a continuously moving robotic platform in a cluttered and unstructured environment.

Light field images (LFIs) have gained popularity as a technology to increase the field of view (FoV) of plenoptic cameras since they can capture information about light rays with a large FoV. Wide FoV causes light field (LF) data to increase rapidly, which restricts the use of LF imaging in image processing, visual analysis and user interface. Effective LFI coding methods become of paramount importance. This paper aims to eliminate more redundancy by exploring sparsity and correlation in the angular domain of LFIs, as well as mitigate the loss of perceptual quality of LFIs caused by encoding.

This work proposes a new efficient LF coding framework. On the coding side, a new sampling scheme and a hierarchical prediction structure are used to eliminate redundancy in the LFI's angular and spatial domains. At the decoding side, high-quality dense LF is reconstructed using a view synthesis method based on the residual channel attention network (RCAN).

In three different LF datasets, our proposed coding framework not only reduces the transmitted bit rate but also maintains a higher view quality than the current more advanced methods.

(1) A new sampling scheme is designed to synthesize high-quality LFIs while better ensuring LF angular domain sparsity. (2) To further eliminate redundancy in the spatial domain, new ranking schemes and hierarchical prediction structures are designed. (3) A synthetic network based on RCAN and a novel loss function is designed to mitigate the perceptual quality loss due to the coding process.

The paper examines the role and significance of gastronomic manifestations in the context of destination branding, within the framework of image transfer mechanisms and the Associative Network Memory Model.

The research was conducted on a sample of 53 gastronomic events in the tourist destination of Vojvodina.

The results indicate that gastronomic manifestations image has a positive impact on the brand image and brand identity of the destination, as well as the destination's overall image. Furthermore, the study found that the food experience has a positive influence on the image of gastronomic events and the destination.

The study contributes to the advancement of research on tourist destination branding.

This study aims to achieve superior localization and mapping performance in point cloud degradation scenarios through the effective removal of dynamic obstacles. With the continuous development of various technologies for autonomous vehicles, the LIDAR-based Simultaneous localization and mapping (SLAM) system is becoming increasingly important. However, in SLAM systems, effectively addressing the challenges of point cloud degradation scenarios is essential for accurate localization and mapping, with dynamic obstacle removal being a key component.

This paper proposes a method that combines adaptive feature extraction and loop closure detection algorithms to address this challenge. In the SLAM system, the ground point cloud and non-ground point cloud are separated to reduce the impact of noise. And based on the cylindrical projection image of the point cloud, the intensity features are adaptively extracted, the degradation direction is determined by the degradation factor and the intensity features are matched with the map to correct the degraded pose. Moreover, through the difference in raster distribution of the point clouds before and after two frames in the loop process, the dynamic point clouds are identified and removed, and the map is updated.

Experimental results show that the method has good performance. The absolute displacement accuracy of the laser odometer is improved by 27.1%, the relative displacement accuracy is improved by 33.5% and the relative angle accuracy is improved by 23.8% after using the adaptive intensity feature extraction method. The position error is reduced by 30% after removing the dynamic target.

Compared with LiDAR odometry and mapping algorithm, the method has greater robustness and accuracy in mapping and localization.

The swivel construction method is a specially designed process used to build bridges that cross rivers, valleys, railroads and other obstacles. To carry out this construction method safely, real-time monitoring of the bridge rotation process is required to ensure a smooth swivel operation without collisions. However, the traditional means of monitoring using Electronic Total Station tools cannot realize real-time monitoring, and monitoring using motion sensors or GPS is cumbersome to use.

This study proposes a monitoring method based on a series of computer vision (CV) technologies, which can monitor the rotation angle, velocity and inclination angle of the swivel construction in real-time. First, three proposed CV algorithms was developed in a laboratory environment. The experimental tests were carried out on a bridge scale model to select the outperformed algorithms for rotation, velocity and inclination monitor, respectively, as the final monitoring method in proposed method. Then, the selected method was implemented to monitor an actual bridge during its swivel construction to verify the applicability.

In the laboratory study, the monitoring data measured with the selected monitoring algorithms was compared with those measured by an Electronic Total Station and the errors in terms of rotation angle, velocity and inclination angle, were 0.040%, 0.040%, and −0.454%, respectively, thus validating the accuracy of the proposed method. In the pilot actual application, the method was shown to be feasible in a real construction application.

In a well-controlled laboratory the optimal algorithms for bridge swivel construction are identified and in an actual project the proposed method is verified. The proposed CV method is complementary to the use of Electronic Total Station tools, motion sensors, and GPS for safety monitoring of swivel construction of bridges. It also contributes to being a possible approach without data-driven model training. Its principal advantages are that it both provides real-time monitoring and is easy to deploy in real construction applications.

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.

To ensure the motion attitude and stable contact force of massage robot working on unknown human tissue environment, this study aims to propose a robotic system for autonomous massage path planning and stable interaction control.

First, back region extraction and acupoint recognition based on deep learning is proposed, which provides a basis for determining the working area and path points of the robot. Second, to realize the standard approach and movement trajectory of the expert massage, 3D reconstruction and path planning of the massage area are performed, and normal vectors are calculated to control the normal orientation of robot-end. Finally, to cope with the soft and hard changes of human tissue state and body movement, an adaptive force tracking control strategy is presented to compensate the uncertainty of environmental position and tissue hardness online.

Improved network model can accomplish the acupoint recognition task with a large accuracy and integrate the point cloud to generate massage trajectories adapted to the shape of the human body. Experimental results show that the adaptive force tracking control can obtain a relatively smooth force, and the error is basically within ± 0.2 N during the online experiment.

This paper incorporates deep learning, 3D reconstruction and impedance control, the robot can understand the shape features of the massage area and adapt its planning massage path to carry out a stable and safe force tracking control during dynamic robot–human contact.

This study aims to investigate the ecological awareness of Chinese consumers towards fast fashion and examine the effect of social sustainability claims on green brand image and purchase intentions in China, considering China’s unique environmental policy landscape and its significant role in the global fast fashion industry. The study explores the role of altruistic values in promoting sustainability within the well-known fast fashion brand “H” and how they shape brand image, consumer satisfaction and brand equity.

The study collected data from 257 Chinese participants and used a serial mediation model through the PROCESS macro in SPSS to analyse the correlation between green brand image, created through sustainability claims and consumer purchase intentions. The model also assessed the intermediary effects of brand image, satisfaction and equity.

The findings of the research indicate a direct and positive relationship between green brand image and consumer purchase intentions, emphasising the need for clothing and textile industry marketers to strategically promote altruistic values in their sustainability efforts and highlighting the importance of ecological awareness in shaping consumer behaviour in the Chinese context. This approach enhances green satisfaction and green brand equity and ultimately leads to higher green purchase intentions.

This study provides significant insights into the effectiveness of incorporating social sustainability claims in advertising to improve a brand’s green image and influence consumer behaviour. It emphasises the importance of altruistic values in sustainability strategies, offering valuable guidelines for marketers in enhancing green satisfaction and brand equity, thereby boosting consumer purchase intentions in the context of green branding and sustainability advertising. Focussing specifically on the Chinese market, this research sheds light on the impact of ecological awareness among Chinese consumers within the fast-fashion industry. Given China’s substantial role in shaping global fast-fashion production and its evolving environmental policies, this focus adds significant depth to our understanding of sustainability claims’ influence within this crucial consumer base.

The purpose of this study is to analyze the horizontal expansion of Burayu Town between 1990 and 2020. The study typically acts as a baseline for integrated spatial planning in small- and medium-sized towns, which will help to plan sustainable utilization of land.

Landsat5-TM, Landsat7 ETM+, Landsat5 TM and Landsat8 OLI were used in the study, along with other auxiliary data. The LULC map classifications were generated using the Random Forest Package from the Comprehensive R Archive Network. Post-classification, spatial metrics, and per capita land consumption rate were used to understand the manner and rate of expansion of Burayu Town. Focus group discussions and key informant interviews were also used to validate land use classes through triangulation.

The study found that the built-up area was the most dynamic LULC category (85.1%) as it increased by over 4,000 ha between 1990 and 2020. Furthermore, population increase did not result in density increase as per capita land consumption increased from 0.024 to 0.040 during the same period.

As a result of financial limitations, there were no high-resolution satellite images available, making it challenging to pinpoint the truth as it is on the ground. Including senior citizens in the study region allowed this study to overcome these restrictions and detect every type of land use and cover.

Data on urban growth are useful for planning land uses, estimating growth rates and advising the government on how best to use land. This can be achieved by monitoring and reviewing development plans using satellite imaging data and GIS tools.

The use of Random Forest for image classification and the employment of local knowledge to validate the accuracy of land cover classification is a novel approach to properly customize remote sensing applications.