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.

Although numerous signal modalities are available for emotion recognition, audio and visual modalities are the most common and predominant forms for human beings to express their emotional states in daily communication. Therefore, how to achieve automatic and accurate audiovisual emotion recognition is significantly important for developing engaging and empathetic human–computer interaction environment. However, two major challenges exist in the field of audiovisual emotion recognition: (1) how to effectively capture representations of each single modality and eliminate redundant features and (2) how to efficiently integrate information from these two modalities to generate discriminative representations.

A novel key-frame extraction-based attention fusion network (KE-AFN) is proposed for audiovisual emotion recognition. KE-AFN attempts to integrate key-frame extraction with multimodal interaction and fusion to enhance audiovisual representations and reduce redundant computation, filling the research gaps of existing approaches. Specifically, the local maximum–based content analysis is designed to extract key-frames from videos for the purpose of eliminating data redundancy. Two modules, including “Multi-head Attention-based Intra-modality Interaction Module” and “Multi-head Attention-based Cross-modality Interaction Module”, are proposed to mine and capture intra- and cross-modality interactions for further reducing data redundancy and producing more powerful multimodal representations.

Extensive experiments on two benchmark datasets (i.e. RAVDESS and CMU-MOSEI) demonstrate the effectiveness and rationality of KE-AFN. Specifically, (1) KE-AFN is superior to state-of-the-art baselines for audiovisual emotion recognition. (2) Exploring the supplementary and complementary information of different modalities can provide more emotional clues for better emotion recognition. (3) The proposed key-frame extraction strategy can enhance the performance by more than 2.79 per cent on accuracy. (4) Both exploring intra- and cross-modality interactions and employing attention-based audiovisual fusion can lead to better prediction performance.

The proposed KE-AFN can support the development of engaging and empathetic human–computer interaction environment.

High-resolution remote sensing images possess a wealth of semantic information. However, these images often contain objects of different sizes and distributions, which make the semantic segmentation task challenging. In this paper, a bidirectional feature fusion network (BFFNet) is designed to address this challenge, which aims at increasing the accurate recognition of surface objects in order to effectively classify special features.

There are two main crucial elements in BFFNet. Firstly, the mean-weighted module (MWM) is used to obtain the key features in the main network. Secondly, the proposed polarization enhanced branch network performs feature extraction simultaneously with the main network to obtain different feature information. The authors then fuse these two features in both directions while applying a cross-entropy loss function to monitor the network training process. Finally, BFFNet is validated on two publicly available datasets, Potsdam and Vaihingen.

In this paper, a quantitative analysis method is used to illustrate that the proposed network achieves superior performance of 2–6%, respectively, compared to other mainstream segmentation networks from experimental results on two datasets. Complete ablation experiments are also conducted to demonstrate the effectiveness of the elements in the network. In summary, BFFNet has proven to be effective in achieving accurate identification of small objects and in reducing the effect of shadows on the segmentation process.

The originality of the paper is the proposal of a BFFNet based on multi-scale and multi-attention strategies to improve the ability to accurately segment high-resolution and complex remote sensing images, especially for small objects and shadow-obscured objects.

Classification of remote sensing images (RSI) is a challenging task in computer vision. Recently, researchers have proposed a variety of creative methods for automatic recognition of RSI, and feature fusion is a research hotspot for its great potential to boost performance. However, RSI has a unique imaging condition and cluttered scenes with complicated backgrounds. This larger difference from nature images has made the previous feature fusion methods present insignificant performance improvements.

This work proposed a two-convolutional neural network (CNN) fusion method named main and branch CNN fusion network (MBC-Net) as an improved solution for classifying RSI. In detail, the MBC-Net employs an EfficientNet-B3 as its main CNN stream and an EfficientNet-B0 as a branch, named MC-B3 and BC-B0, respectively. In particular, MBC-Net includes a long-range derivation (LRD) module, which is specially designed to learn the dependence of different features. Meanwhile, MBC-Net also uses some unique ideas to tackle the problems coming from the two-CNN fusion and the inherent nature of RSI.

Extensive experiments on three RSI sets prove that MBC-Net outperforms the other 38 state-of-the-art (STOA) methods published from 2020 to 2023, with a noticeable increase in overall accuracy (OA) values. MBC-Net not only presents a 0.7% increased OA value on the most confusing NWPU set but also has 62% fewer parameters compared to the leading approach that ranks first in the literature.

MBC-Net is a more effective and efficient feature fusion approach compared to other STOA methods in the literature. Given the visualizations of grad class activation mapping (Grad-CAM), it reveals that MBC-Net can learn the long-range dependence of features that a single CNN cannot. Based on the tendency stochastic neighbor embedding (t-SNE) results, it demonstrates that the feature representation of MBC-Net is more effective than other methods. In addition, the ablation tests indicate that MBC-Net is effective and efficient for fusing features from two CNNs.

COVID-19 continues to spread, and cause increasing deaths. Physicians diagnose COVID-19 using not only real-time polymerase chain reaction but also the computed tomography (CT) and chest x-ray (CXR) modalities, depending on the stage of infection. However, with so many patients and so few doctors, it has become difficult to keep abreast of the disease. Deep learning models have been developed in order to assist in this respect, and vision transformers are currently state-of-the-art methods, but most techniques currently focus only on one modality (CXR).

This work aims to leverage the benefits of both CT and CXR to improve COVID-19 diagnosis. This paper studies the differences between using convolutional MobileNetV2, ViT DeiT and Swin Transformer models when training from scratch and pretraining on the MedNIST medical dataset rather than the ImageNet dataset of natural images. The comparison is made by reporting six performance metrics, the Scott–Knott Effect Size Difference, Wilcoxon statistical test and the Borda Count method. We also use the Grad-CAM algorithm to study the model's interpretability. Finally, the model's robustness is tested by evaluating it on Gaussian noised images.

Although pretrained MobileNetV2 was the best model in terms of performance, the best model in terms of performance, interpretability, and robustness to noise is the trained from scratch Swin Transformer using the CXR (accuracy = 93.21 per cent) and CT (accuracy = 94.14 per cent) modalities.

Models compared are pretrained on MedNIST and leverage both the CT and CXR modalities.

Existing Simultaneous Localization and Mapping (SLAM) algorithms have been relatively well developed. However, when in complex dynamic environments, the movement of the dynamic points on the dynamic objects in the image in the mapping can have an impact on the observation of the system, and thus there will be biases and errors in the position estimation and the creation of map points. The aim of this paper is to achieve more accurate accuracy in SLAM algorithms compared to traditional methods through semantic approaches.

In this paper, the semantic segmentation of dynamic objects is realized based on U-Net semantic segmentation network, followed by motion consistency detection through motion detection method to determine whether the segmented objects are moving in the current scene or not, and combined with the motion compensation method to eliminate dynamic points and compensate for the current local image, so as to make the system robust.

Experiments comparing the effect of detecting dynamic points and removing outliers are conducted on a dynamic data set of Technische Universität München, and the results show that the absolute trajectory accuracy of this paper's method is significantly improved compared with ORB-SLAM3 and DS-SLAM.

In this paper, in the semantic segmentation network part, the segmentation mask is combined with the method of dynamic point detection, elimination and compensation, which reduces the influence of dynamic objects, thus effectively improving the accuracy of localization in dynamic environments.

Monitoring of the quality of precast concrete (PC) components is crucial for the success of prefabricated construction projects. Currently, quality monitoring of PC components during the construction phase is predominantly done manually, resulting in low efficiency and hindering the progress of intelligent construction. This paper presents an intelligent inspection method for assessing the appearance quality of PC components, utilizing an enhanced you look only once (YOLO) model and multi-source data. The aim of this research is to achieve automated management of the appearance quality of precast components in the prefabricated construction process through digital means.

The paper begins by establishing an improved YOLO model and an image dataset for evaluating appearance quality. Through object detection in the images, a preliminary and efficient assessment of the precast components' appearance quality is achieved. Moreover, the detection results are mapped onto the point cloud for high-precision quality inspection. In the case of precast components with quality defects, precise quality inspection is conducted by combining the three-dimensional model data obtained from forward design conversion with the captured point cloud data through registration. Additionally, the paper proposes a framework for an automated inspection platform dedicated to assessing appearance quality in prefabricated buildings, encompassing the platform's hardware network.

The improved YOLO model achieved a best mean average precision of 85.02% on the VOC2007 dataset, surpassing the performance of most similar models. After targeted training, the model exhibits excellent recognition capabilities for the four common appearance quality defects. When mapped onto the point cloud, the accuracy of quality inspection based on point cloud data and forward design is within 0.1 mm. The appearance quality inspection platform enables feedback and optimization of quality issues.

The proposed method in this study enables high-precision, visualized and automated detection of the appearance quality of PC components. It effectively meets the demand for quality inspection of precast components on construction sites of prefabricated buildings, providing technological support for the development of intelligent construction. The design of the appearance quality inspection platform's logic and framework facilitates the integration of the method, laying the foundation for efficient quality management in the future.

In this study, an indoor sensor information fusion positioning system of the quadrotor unmanned aerial vehicle (UAV) was investigated to solve the problem of unstable indoor flight positioning.

The presented system was built on Light Detection and Ranging (LiDAR), Inertial Measurement Unit (IMU) and LiDAR-Lite devices. Based on this, one can obtain the aircraft's current attitude and the position vector relative to the target and control the attitudes and positions of the UAV to reach the specified target positions. While building a UAV positioning model relative to the target for indoor positioning scenarios under limited Global Navigation Satellite Systems (GNSS), the system detects the environment through the NVIDIA Jetson TX2 (Transmit Data) peripheral sensor, obtains the current attitude and the position vector of the UAV, packs the data in the format and delivers it to the flight controller. Then the flight controller controls the UAV by calculating the posture to reach the specified target position.

The authors used two systems in the experiment. The first is the proposed UAV, and the other is the Vicon system, our reference system for comparison purposes. Vicon positioning error can be considered lower than 2 mm from low to high-speed experiments. After comparison, experimental results demonstrated that the system could fully meet the requirements (less than 50 mm) in real-time positioning of the indoor quadrotor UAV flight. It verifies the accuracy and robustness of the proposed method compared with that of Vicon and achieves the aim of a stable indoor flight preliminarily.

Vicon positioning error can be considered lower than 2 mm from low to high-speed experiments. After comparison, experimental results demonstrated that the system could fully meet the requirements (less than 50 mm) in real-time positioning of the indoor quadrotor UAV flight. It verifies the accuracy and robustness of the proposed method compared with that of Vicon and achieves the aim of a stable indoor flight preliminarily.

This paper presents a survey of research into interactive robotic systems for the purpose of identifying the state of the art capabilities as well as the extant gaps in this emerging field. Communication is multimodal. Multimodality is a representation of many modes chosen from rhetorical aspects for its communication potentials. The author seeks to define the available automation capabilities in communication using multimodalities that will support a proposed Interactive Robot System (IRS) as an AI mounted robotic platform to advance the speed and quality of military operational and tactical decision making.

This review will begin by presenting key developments in the robotic interaction field with the objective of identifying essential technological developments that set conditions for robotic platforms to function autonomously. After surveying the key aspects in Human Robot Interaction (HRI), Unmanned Autonomous System (UAS), visualization, Virtual Environment (VE) and prediction, the paper then proceeds to describe the gaps in the application areas that will require extension and integration to enable the prototyping of the IRS. A brief examination of other work in HRI-related fields concludes with a recapitulation of the IRS challenge that will set conditions for future success.

Using insights from a balanced cross section of sources from the government, academic, and commercial entities that contribute to HRI a multimodal IRS in military communication is introduced. Multimodal IRS (MIRS) in military communication has yet to be deployed.

Multimodal robotic interface for the MIRS is an interdisciplinary endeavour. This is not realistic that one can comprehend all expert and related knowledge and skills to design and develop such multimodal interactive robotic interface. In this brief preliminary survey, the author has discussed extant AI, robotics, NLP, CV, VDM, and VE applications that is directly related to multimodal interaction. Each mode of this multimodal communication is an active research area. Multimodal human/military robot communication is the ultimate goal of this research.

A multimodal autonomous robot in military communication using speech, images, gestures, VST and VE has yet to be deployed. Autonomous multimodal communication is expected to open wider possibilities for all armed forces. Given the density of the land domain, the army is in a position to exploit the opportunities for human–machine teaming (HMT) exposure. Naval and air forces will adopt platform specific suites for specially selected operators to integrate with and leverage this emerging technology. The possession of a flexible communications means that readily adapts to virtual training will enhance planning and mission rehearsals tremendously.

Interaction, perception, cognition and visualization based multimodal communication system is yet missing. Options to communicate, express and convey information in HMT setting with multiple options, suggestions and recommendations will certainly enhance military communication, strength, engagement, security, cognition, perception as well as the ability to act confidently for a successful mission.

The objective is to develop a multimodal autonomous interactive robot for military communications. This survey reports the state of the art, what exists and what is missing, what can be done and possibilities of extension that support the military in maintaining effective communication using multimodalities. There are some separate ongoing progresses, such as in machine-enabled speech, image recognition, tracking, visualizations for situational awareness, and virtual environments. At this time, there is no integrated approach for multimodal human robot interaction that proposes a flexible and agile communication. The report briefly introduces the research proposal about multimodal interactive robot in military communication.