Displays最新文献

Underwater target detection technology holds significant importance in both military and civilian applications of ocean exploration. However, due to the complex underwater environment, most targets are small and often obscured, leading to low detection accuracy and missed detections in existing target detection algorithms. To address these issues, we propose an underwater target detection algorithm that balances accuracy and speed. Specifically, we first propose the Differentiable Routing Assistance Sampling Network named (DRASN), where differentiable routing participates in training the sampling network but not in the inference process. It replaces the down-sampling network composed of Maxpool and convolution fusion in the backbone network, reducing the feature loss of small and occluded targets. Secondly, we proposed the Bilateral Attention Synergistic Network (BASN), which establishes connections between the backbone and neck with fine-grained information from both channel and spatial perspectives, thereby further enhancing the detection capability of targets in complex backgrounds. Finally, considering the characteristics of real frames, we proposed a scale approximation auxiliary loss function named (Aux-Loss) and modify the allocation strategy of positive and negative samples to enable the network to selectively learn high-quality anchors, thereby improving the convergence capability of the network. Compared with mainstream algorithms, our detection network achieves 82.9% in [email protected] on the URPC2021 dataset, which is 9.5%, 5.7%, and 2.8% higher than YOLOv8s, RT-DETR, and SDBB respectively. The speed reaches 75 FPS and meets the requirements for real-time performance.

The purpose of this study was to evaluate the ability of SeeColors filters to enhance color vision test results using the electronic version of the Farnsworth D-15 (E-D15) and Ishihara tests on a Samsung TV, and to compare their effectiveness with EnChroma glasses. Sixty-six subjects with congenital red–green color vision deficiency were tested. For both protan and deutan groups, the confusion angle shifted to negative values, with SeeColors filters exhibiting a greater effect than EnChroma glasses. In the deutan group, the TES, S-index, and C-index of the E-D15 test decreased, with the SeeColors D30 filter having a more pronounced effect than EnChroma deutan glasses. In the protan group, while EnChroma protan glasses tended to decrease the TES, S-index, and C-index, the SeeColors P30 filter increased them. For both groups, TS and TN of the Ishihara tests improved, with the SeeColors D30 filter demonstrating a stronger effect than EnChroma deutan glasses. The study concluded that both the SeeColors D30 filter and EnChroma deutan glasses were beneficial for deutans, albeit the SeeColors D30 filter was superior. In protans, neither the SeeColors P30 filter nor EnChroma protan glasses showed significant effectiveness, but the SeeColors P30 filter did improve performance in the pseudoisochromatic task.

With the gradual maturity of computer vision technology, using intersection surveillance videos for vehicle trajectory extraction has become a popular method to analyze vehicle conflicts and safety in urban intersection. However, many intersection surveillance videos have blind spots, failing to fully cover the entire intersection. Vehicles may also obstruct each other, resulting in incomplete vehicle trajectories. The angle of surveillance videos can also lead to inaccurate trajectory extraction. In response to these challenges, this study proposes an vehicle trajectory extraction and integration framework using surveillance videos collected from four entrance of urban intersection. The framework first employs the improved YOLOv5s model to detect the positions of vehicles. Then, we proposed an object tracking model MS-SORT to extract the trajectories in each surveillance video. Subsequently, the trajectories of each surveillance video are mapped into the same coordinate system. Then the integration of trajectories is achieved using space–time information and re-identification (ReID) methods. The framework extracts and integrates trajectories from four intersection surveillance videos, obtaining trajectories with significantly broader temporal and spatial coverage compared to those obtained from any single direction of surveillance video. Our detection model improved mAP by 1.3 percentage points compared to the basic YOLOv5s, and our object tracking model improved MOTA and IDF1 by 2.6 and 2.1 percentage points compared to DeepSORT. The trojectory integration method achieved 94.7 % of F1-Score and RMSE of 0.51 m. The average length and number of the extracted trajectories has increased by at least 47.6 % and 24.2 % respectively compared to trajectories extracted from a single video.

Most blind watermarking methods adopt the Encode-Noiselayer-Decoder network architecture, called END. However, there are issues that impact the imperceptibility and robustness of the watermarking, such as the encoder blindly embedding redundant features, adversarial training failing to simulate unknown noise effectively, and the limited capability of single-scale feature extraction. To address these challenges, we propose a new Noiselayer-Decoder-driven blind watermarking network, called ND-END, which leverages prior knowledge of the noise layer and features extracted by the decoder to guide the encoder for generating images with fewer redundant modifications, enhancing the imperceptibility. To effectively simulate the unknown noise caused during adversarial training, we introduce an unknown noise layer based on the guided denoising diffusion probabilistic model, which gradually modifies the mean value of the predicted noise during the image generation process. It produces unknown noise images that closely resemble the encoded images but can mislead the decoder. Moreover, we propose a multi-scale spatial-channel feature extraction method for extracting multi-scale message features from the noised image, which aids in message extraction. Experimental results demonstrate the effectiveness of our model, ND-END achieves a lower bit error rate while improving the peak signal-to-noise ratio by approximately 6 dB (from about 33.5 dB to 39.5 dB).

Breech face impressions are an essential type of physical evidence in forensic investigations. However, their surface morphology is complex and varies based on the machining method used on the gun’s breech face, making traditional handcrafted local feature-based methods exhibit high false rates and are unsuitable for striated impressions. We proposed a deep local feature-based method for firearm identification utilizing Detector-Free Local Feature Matching with Transformers (LoFTR). This method removes the module of feature point detection and directly utilizes self and cross-attention layers in the Transformer to transform the convolved coarse-level feature maps into a series of dense feature descriptors. Subsequently, matches with high confidence scores are filtered based on the score matrix calculated from the dense descriptors. Finally, the screened initial matches are refined into the convolved fine-level features, and a correlation-based approach is used to obtain the exact location of the match. Validation tests were conducted using three authoritative sets of the breech face impressions datasets provided by the National Institute of Standards and Technology (NIST). The validation results show that, compared with the traditional handcrafted local-feature based methods, the proposed method in this paper yields a lower identification error rate. Notably, the method can not only deal with granular impressions, but can also be applied to the striated impressions. The results indicate that the method proposed in this paper can be utilized for comparative analysis of breech face impressions, and provide a new automatic identification method for forensic investigations.

The real-time and accurate detection of three-dimensional (3D) objects based on LiDAR is a focal problem in the field of autonomous driving environment perception. Compared to two-stage and anchor-based 3D object detection methods that suffer from inference latency challenges, single-stage anchor-free 3D object detection approaches are more suitable for deployment in autonomous driving vehicles with the strict real-time requirement. However, they face the issue of insufficient spatial awareness, which can result in detection errors such as false positives and false negatives, thereby increasing the potential risks of autonomous driving. In response to this, we focus on enhancing the spatial awareness of CenterPoint, a widely used single-stage anchor-free 3D object detector in the industry. Considering the limited allocation of computational resources and the performance bottleneck caused by pillar encoder, we propose an efficient SSDCM backbone to strengthen feature representation and extraction. Furthermore, a simple BGC neck is devised to weight and exchange contextual information in order to deeply fuse multi-scale features. Combining improved backbone and neck networks, we construct a single-stage anchor-free 3D object detection model with spatial awareness enhancement, named CenterPoint-Spatial Awareness Enhancement (CenterPoint-SAE). We evaluate CenterPoint-SAE on two large-scale and challenging autonomous driving datasets, nuScenes and Waymo. It achieves 53.3% mAP and 62.5% NDS on nuScenes detection benchmark, and runs inference at a speed of 11.1 FPS. Compared to the baseline, the upgraded networks deliver a performance improvement of 1.6% mAP and 1.2% NDS at minor cost. Notably, on Waymo dataset, our method achieves competitive detection performance compared to two-stage and point-based methods.

Visually assistive systems for the visually impaired play a pivotal role in enhancing the quality of life for the visually impaired. Assistive technologies for the visually impaired have undergone a remarkable transformation with the advent of deep learning and sophisticated assistive devices. In particular, the paper utilizes the latest machine translation models and techniques to accomplish the Chinese–Braille translation task, providing convenience for visually impaired individuals. The Traditional end-to-end Chinese–Braille translation approach incorporates Braille dots and Braille word segmentation symbols as tokens within the model’s vocabulary. However, our findings reveal that Braille word segmentation is significantly more complex than Braille dot prediction. The paper proposes a novel Two-Part Loss (TPL) method that treats these tasks distinctly, leading to significant accuracy improvements. To enhance translation performance further, we introduce a BERT-Enhanced Segmentation Transformer (BEST) method. BEST leverages knowledge distillation techniques to transfer knowledge from a pre-trained BERT model to the translate model, mitigating its limitations in word segmentation. Additionally, soft label distillation is employed to improve overall efficacy further. The TPL approach achieves an average BLEU score improvement of 1.16 and 5.42 for Transformer and GPT models on four datasets, respectively. In addition, The work presents a two-stage deep learning-based translation approach that outperforms traditional multi-step and end-to-end methods. The proposed two-stage translation method achieves an average BLEU score improvement of 0.85 across four datasets.

Orthodontic treatment is a subject of prevention, treatment and prognostic care for malocclusion. The complexity and multimodality of orthodontic treatment restrict the development of intelligent orthodontics, due to the different growth and development characteristics of patients with different treatment stages and the different prognosis of treatment at different stages. Digital twin technology can effectively solve the problems of orthodontics ，due to its ability to interpret the deep information of big data. Building upon medical knowledge, this paper succinctly summarizes the application of digital twin technology in key areas of orthodontics, including precision Medicine, personalized orthodontic treatment, prediction of soft and hard tissues before and after orthodontic treatment, and the orthodontic cloud platform. The study provides a feasibility analysis of an intelligent predictive model for orthodontic treatment under multimodal fusion, offering a robust solution for establishing a comprehensive digital twin-assisted diagnostic paradigm.

Learning node representation on heterophilous graphs has been challenging due to nodes with diverse labels/attributes being connected. The main idea is to balance contributions between the center node and neighborhoods. However, existing methods failed to make full use of personalized contributions of different neighborhoods based on whether they own the same label as the center node, making it necessary to explore the distinctive contributions of similar/dissimilar neighborhoods. We reveal that both similar/dissimilar neighborhoods have positive impacts on feature aggregation under different homophily ratios. Especially, dissimilar neighborhoods play a significant role under low homophily ratios. Based on this, we propose LAAH, a label-aware aggregation approach for node representation learning on heterophilous graphs. LAAH separates each center node from its neighborhoods and generates their own node representations. Additionally, for each neighborhood, LAAH records its label information based on whether it belongs to the same class as the center node and then aggregates its effective feature in a weighted manner. Finally, a learnable parameter is used to balance the contributions of each center node and all its neighborhoods, leading to updated representations. Extensive experiments on 8 real-world heterophilous datasets and a synthetic dataset verify that LAAH can achieve competitive or superior accuracy in node classification with lower parameter scale and computational complexity compared with the SOTA methods. The code is released at GitHub: https://github.com/laah123graph/LAAH.

The local scanning orthogonal translation computed laminography (OTCL) has great potential for tiny fault detection of laminated structure thin-plate parts. However, it generates limited-angle and truncated projection data, which result in aliasing and truncation artifacts in the reconstructed images. The directional total variation (DTV) algorithm has been demonstrated to achieve highly accurate reconstructed images in limited-angle computed tomography (CT). However, its application in local scanning OTCL has not been explored. Based on this algorithm, we introduce the $l_p$ norm to better suppress artifacts, and prior information to further constrain the reconstructed image. Thus, we propose a prior information guided directional total p-variation (DTpV) algorithm (Pig-DTpV). The Pig-DTpV model is a constrained non-convex optimization model. The constraint term are the six DTpV terms, whereas the objective term is the data fidelity term. Then, we use the iterative reweighting strategy and the Chambolle–Pock (CP) algorithm to solve the model. The Pig-DTpV reconstruction algorithm’s performance is compared with other algorithms such as simultaneous algebraic reconstruction technique (SART), TV, reweighted anisotropic-TV (RwATV), and DTV in simulation and real data experiments. The experiment results demonstrate that the Pig-DTpV algorithm can reduce truncation and aliasing artifacts and enhance the quality of reconstructed images.