RESUMO
Risky driving is a major factor in traffic incidents, necessitating constant monitoring and prevention through Intelligent Transportation Systems (ITS). Despite recent progress, a lack of suitable data for detecting risky driving in traffic surveillance settings remains a significant challenge. To address this issue, Bayonet-Drivers, a pioneering benchmark for risky driving detection, is proposed. The unique challenge posed by Bayonet-Drivers arises from the nature of the original data obtained from intelligent monitoring and recording systems, rather than in-vehicle cameras. Bayonet-Drivers encompasses a broad spectrum of challenging scenarios, thereby enhancing the resilience and generalizability of algorithms for detecting risky driving. Further, to address the scarcity of labeled data without compromising detection accuracy, a novel semi-supervised network architecture, named DGMB-Net, is proposed. Within DGMB-Net, an enhanced semi-supervised method founded on a teacher-student model is introduced, aiming at bypassing the time-consuming and labor-intensive tasks associated with data labeling. Additionally, DGMB-Net has engineered an Adaptive Perceptual Learning (APL) Module and a Hierarchical Feature Pyramid Network (HFPN) to amplify spatial perception capabilities and amalgamate features at varying scales and levels, thus boosting detection precision. Extensive experiments on widely utilized datasets, including the State Farm dataset and Bayonet-Drivers, demonstrated the remarkable performance of the proposed DGMB-Net.
RESUMO
Groundwater with an excessive level of Arsenic (As) is a threat to human health. In Bangladesh, out of 64 districts, the groundwater of 50 and 59 districts contains As exceeding the Bangladesh (50 µg/L) and WHO (10 µg/L) standards for potable water. This review focuses on the occurrence, origin, plausible sources, and mobilization mechanisms of As in the groundwater of Bangladesh to better understand its environmental as well as public health consequences. High As concentrations mainly was mainly occur from the natural origin of the Himalayan orogenic tract. Consequently, sedimentary processes transport the As-loaded sediments from the orogenic tract to the marginal foreland of Bangladesh, and under the favorable biogeochemical circumstances, As is discharged from the sediment to the groundwater. Rock weathering, regular floods, volcanic movement, deposition of hydrochemical ore, and leaching of geological formations in the Himalayan range cause As occurrence in the groundwater of Bangladesh. Redox and desorption processes along with microbe-related reduction are the key geochemical processes for As enrichment. Under reducing conditions, both reductive dissolution of Fe-oxides and desorption of As are the root causes of As mobilization. A medium alkaline and reductive environment, resulting from biochemical reactions, is the major factor mobilizing As in groundwater. An elevated pH value along with decoupling of As and HCO3- plays a vital role in mobilizing As. The As mobilization process is related to the reductive solution of metal oxides as well as hydroxides that exists in sporadic sediments in Bangladesh. Other mechanisms, such as pyrite oxidation, redox cycling, and competitive ion exchange processes, are also postulated as probable mechanisms of As mobilization. The reductive dissolution of MnOOH adds dissolved As and redox-sensitive components such as SO42- and oxidized pyrite, which act as the major mechanisms to mobilize As. The reductive suspension of Mn(IV)-oxyhydroxides has also accelerated the As mobilization process in the groundwater of Bangladesh. Infiltration from the irrigation return flow and surface-wash water are also potential factors to remobilize As. Over-exploitation of groundwater and the competitive ion exchange process are also responsible for releasing As into the aquifers of Bangladesh.
Assuntos
Arsênio , Água Subterrânea , Poluentes Químicos da Água , Bangladesh , Monitoramento Ambiental , Sedimentos Geológicos , HumanosRESUMO
A reasonable and balanced diet is essential for maintaining good health. With advancements in deep learning, an automated nutrition estimation method based on food images offers a promising solution for monitoring daily nutritional intake and promoting dietary health. While monocular image-based nutrition estimation is convenient, efficient and economical, the challenge of limited accuracy remains a significant concern. To tackle this issue, we proposed DPF-Nutrition, an end-to-end nutrition estimation method using monocular images. In DPF-Nutrition, we introduced a depth prediction module to generate depth maps, thereby improving the accuracy of food portion estimation. Additionally, we designed an RGB-D fusion module that combined monocular images with the predicted depth information, resulting in better performance for nutrition estimation. To the best of our knowledge, this was the pioneering effort that integrated depth prediction and RGB-D fusion techniques in food nutrition estimation. Comprehensive experiments performed on Nutrition5k evaluated the effectiveness and efficiency of DPF-Nutrition.
RESUMO
Brain tumor segmentation is a fundamental task and existing approaches usually rely on multi-modality magnetic resonance imaging (MRI) images for accurate segmentation. However, the common problem of missing/incomplete modalities in clinical practice would severely degrade their segmentation performance, and existing fusion strategies for incomplete multi-modality brain tumor segmentation are far from ideal. In this work, we propose a novel framework named M 2 FTrans to explore and fuse cross-modality features through modality-masked fusion transformers under various incomplete multi-modality settings. Considering vanilla self-attention is sensitive to missing tokens/inputs, both learnable fusion tokens and masked self-attention are introduced to stably build long-range dependency across modalities while being more flexible to learn from incomplete modalities. In addition, to avoid being biased toward certain dominant modalities, modality-specific features are further re-weighted through spatial weight attention and channel- wise fusion transformers for feature redundancy reduction and modality re-balancing. In this way, the fusion strategy in M 2 FTrans is more robust to missing modalities. Experimental results on the widely-used BraTS2018, BraTS2020, and BraTS2021 datasets demonstrate the effectiveness of M 2 FTrans, outperforming the state-of-the-art approaches with large margins under various incomplete modalities for brain tumor segmentation. Code is available at https://github.com/Jun-Jie-Shi/M2FTrans.
RESUMO
In this Letter, the color constancy and its realization were studied and a novel color constancy image enhancement algorithm under poor illumination was presented. The purpose of this algorithm is to maintain the hue of an image during the processing so that the change of saturation can be minimized. The original image was first multiplied by a scale parameter obtained by the adaptive quadratic function to enhance the luminance, and then the edge details were restored by a shifting parameter. Numerical results of the Simon Fraser University (SFU) image database indicated that the proposed algorithm performed much better in preserving the hue and saturation and avoiding color distortion compared with the existing image enhancement algorithms.