A5090815285- Advanced Neural Network Applications
- Infrastructure Maintenance and Monitoring
- Face recognition and analysis
- Maritime Navigation and Safety
- Vehicle License Plate Recognition
- Anomaly Detection Techniques and Applications
- Asphalt Pavement Performance Evaluation
- Advanced Image Processing Techniques
- Image Enhancement Techniques
- COVID-19 diagnosis using AI
- Advanced Vision and Imaging
- Automated Road and Building Extraction
- Artificial Intelligence in Healthcare and Education
- Industrial Vision Systems and Defect Detection
- Data Mining Algorithms and Applications
- Leaf Properties and Growth Measurement
- Smart Agriculture and AI
- Fault Detection and Control Systems
- Industrial Technology and Control Systems
- Plant Disease Management Techniques
- EEG and Brain-Computer Interfaces
- Gaze Tracking and Assistive Technology
- Tunneling and Rock Mechanics
- ECG Monitoring and Analysis
- Time Series Analysis and Forecasting
University of Antwerp
2023-2024
VinUniversity
2022-2023
Advances in AI are transforming scientific discovery, yet spatial biology, a field that deciphers the molecular organization within tissues, remains constrained by labor-intensive workflows. Here, we present SpatialAgent, fully autonomous agent dedicated for spatial-biology research. SpatialAgent integrates large language models with dynamic tool execution and adaptive reasoning. spans entire research pipeline, from experimental design to multimodal data analysis hypothesis generation....
Massive data collected on public roads for autonomous driving has become more popular in many locations the world. More leads to concerns about privacy, including but not limited pedestrian faces and surrounding vehicle license plates, which urges robust solutions detecting anonymizing them realistic road-driving scenarios. Existing datasets both face plate detection are either focused or only parking lots. In this paper, we introduce a challenging dataset domain. The is aggregated from...
Recently, there has been an upsurge in the research on maritime vision, where a lot of works are influenced by application computer vision for Unmanned Surface Ve-hicles (USVs). Various sensor modalities such as camera, radar, and lidar have used to perform tasks object detection, segmentation, tracking, motion planning. A large subset this is focused video analysis, since most current vessel fleets con-tain camera's onboard various surveillance tasks. Due vast abundance data, scene change...
This paper discusses the results for second edition of Monocular Depth Estimation Challenge (MDEC). was open to methods using any form supervision, including fully-supervised, self-supervised, multi-task or proxy depth. The challenge based around SYNS-Patches dataset, which features a wide diversity environments with high-quality dense ground-truth. includes complex natural environments, e.g. forests fields, are greatly underrepresented in current benchmarks.The received eight unique...
In many parts of the world, use vast amounts data collected on public roadways for autonomous driving has increased. order to detect and anonymize pedestrian faces nearby car license plates in actual road-driving scenarios, there is an urgent need effective solutions. As more collected, privacy concerns regarding it increase, including but not limited surrounding vehicle plates. Normal fisheye cameras are two common camera types that typically mounted collection vehicles. With complex...
Today, the COVID-19 epidemic has become extremely widespread. The first step in combating is identifying cases of infection. Real-time reverse transcriptase polymerase chain reaction most common method for COVID (RT-PCR). This method, however, been compromised by a time-consuming, laborious, and complex manual process. In addition to RT-PCR test, screening computed tomography scan (CT) or X-ray images may be used identify positive results, which could aid detection COVID-19. Because...
Roads are an essential mode of transportation, and maintaining them is critical to economic growth citizen well-being. With the continued advancement AI, road surface inspection based on camera images has recently been extensively researched can be performed automatically. However, because almost all deep learning methods for detecting defects were optimized a specific dataset, they difficult apply new, previously unseen dataset. Furthermore, there lack research training efficient model...
As the popularity of autonomous vehicles has grown, many standards and regulators, such as ISO, NHTSA, Euro NCAP, require safety validation to ensure a sufficient level before deploying them in real world. Manufacturers gather large amount public road data for this purpose. However, majority these activities are done manually by humans. Furthermore, used validate each driving feature may differ. result, it is essential have an efficient selection method that can be flexibly dynamically...
Maintaining roads is crucial to economic growth and citizen well-being because are a vital means of transportation. In various countries, the inspection road surfaces still done manually, however, automate it, research interest now focused on detecting surface defects via visual data. While, previous has been deep learning methods which tend process entire image leads heavy computational cost. this study, we focus our attention improving classification performance while keeping cost solution...
This paper discusses the results for second edition of Monocular Depth Estimation Challenge (MDEC). was open to methods using any form supervision, including fully-supervised, self-supervised, multi-task or proxy depth. The challenge based around SYNS-Patches dataset, which features a wide diversity environments with high-quality dense ground-truth. includes complex natural environments, e.g. forests fields, are greatly underrepresented in current benchmarks. received eight unique...
In many parts of the world, use vast amounts data collected on public roadways for autonomous driving has increased. order to detect and anonymize pedestrian faces nearby car license plates in actual road-driving scenarios, there is an urgent need effective solutions. As more collected, privacy concerns regarding it increase, including but not limited surrounding vehicle plates. Normal fisheye cameras are two common camera types that typically mounted collection vehicles. With complex...
Plant diseases can cause up to 50% crop yield loss for the popular tomato plant. Successful disease management requires precise and timely identification methods, but slow inconsistent diagnoses from human experts or laboratory testing prevents farmers applying appropriate treatments before takes its toll. As an alternative diagnostic method, a mobile device-based method identify photos of symptomatic leaves via computer vision be more effective due convenience accessibility. Previous...
Recently, there has been an upsurge in the research on maritime vision, where a lot of works are influenced by application computer vision for Unmanned Surface Vehicles (USVs). Various sensor modalities such as camera, radar, and lidar have used to perform tasks object detection, segmentation, tracking, motion planning. A large subset this is focused video analysis, since most current vessel fleets contain camera's onboard various surveillance tasks. Due vast abundance data, scene change...
The use of sensors for human activity recognition (HAR) is one the most active research fields. Several machine learning techniques classifying actions have been proposed in HAR. However, because they rely so heavily on quality handcrafted features, these demand extensive feature engineering. Recent approaches to deep attempted provide comprehensive training. In this paper, we present a temporal convolutional neural network with Hidden Markov Chain HAR post-processing. Our method comprises...