Ruoyu Yang | Machine Vision | Young Researcher Award

Published on by Cognitive Scientist Awards

Ms. Ruoyu Yang | Machine Vision | Young Researcher Award

University of Electronic Science and Technology of China | China

Yang Ruoyu is an emerging researcher specializing in computer vision, image enhancement, and deep learning algorithms, particularly for nighttime road scenarios. Currently pursuing a master’s degree in Big Data Technology and Engineering at the University of Electronic Science and Technology of China, Yang holds a bachelor’s degree in Information and Computing Science from Harbin University of Science and Technology. His research is driven by a passion for improving image quality in challenging conditions, leading to impactful publications in journals like Displays and Applied Sciences. He has contributed to algorithmic advancements for electronic rearview mirrors, addressing low-light, glare, and illumination issues through novel deep learning architectures such as DELIA-Net and NRGS-Net. Yang’s work spans academic papers, conference presentations, patents, and practical engineering projects. Recognized with multiple academic awards, including the National Encouragement Scholarship, he is steadily building a profile as a promising innovator in intelligent transportation imaging technologies

Profile

ORCID

Education

Yang Ruoyu’s academic journey began at Harbin University of Science and Technology, where he pursued a bachelor’s degree in Information and Computing Science. This period provided him with a strong grounding in mathematics, data analysis, and computational algorithms. His early academic success was marked by multiple academic prizes and a national scholarship, highlighting his commitment to excellence. Building on this foundation, Yang advanced to the University of Electronic Science and Technology of China to undertake a master’s degree in Big Data Technology and Engineering. Here, he has deepened his expertise in data-driven problem-solving, computer vision, and artificial intelligence applications. His master’s research focuses on enhancing image processing algorithms to tackle low-light and glare issues in automotive imaging systems. Combining theoretical understanding with hands-on project experience, Yang has cultivated a skill set that bridges mathematical rigor with cutting-edge AI methodologies, positioning him for significant contributions in the field of intelligent transportation technologies.

Experience

Yang Ruoyu has gained valuable research and project experience in image processing, with a primary emphasis on nighttime driving scenarios. His most notable project involves developing a high-dynamic-range imaging algorithm for electronic rearview mirror systems, designed to perform reliably under strong lighting contrasts, low-light environments, and glare interference. Leveraging deep learning architectures such as GANs and Uformer, Yang created innovative frameworks for nighttime road image enhancement and glare suppression. Beyond theoretical design, he has tested and refined these models for real-world automotive applications. As first author, Yang has published in peer-reviewed journals like Displays and Applied Sciences, and has contributed to international conferences with impactful presentations. His work demonstrates a rare blend of academic precision and practical applicability, making him a valuable contributor to AI-powered vision systems. In addition, his patented inventions highlight his ability to move from concept to implementation, driving innovation in both academic and industrial contexts

Awards and Honors

Yang Ruoyu’s academic excellence has been recognized through a series of prestigious awards and honors. He was the recipient of the National Encouragement Scholarship, a testament to his outstanding academic performance and research potential. His consistent achievement earned him multiple Academic Third Prizes from Harbin University of Science and Technology, reflecting his high standing among peers. Beyond academic accolades, Yang’s skill in language proficiency is marked by his commendable CET-4 and CET-6 scores, which strengthen his capacity for international collaboration and research communication. His inventive spirit has been officially recognized through granted Chinese invention patents in nighttime image enhancement and glare suppression technologies. These honors collectively underscore his dedication, intellectual capability, and innovative mindset. Each award not only validates his past accomplishments but also positions him as a promising researcher with the drive and expertise to tackle complex challenges in AI-based image processing and intelligent automotive systems

Research Focus

Yang Ruoyu’s research centers on developing advanced imaging algorithms for nighttime driving assistance systems, with a focus on electronic rearview mirrors. His work tackles the twin challenges of low-light visibility and glare interference, which are critical safety concerns in real-world driving conditions. Drawing on deep learning models such as generative adversarial networks (GANs) and lightweight Uformer architectures, Yang has proposed novel solutions like DELIA-Net for detail enhancement and local illumination adjustment, as well as NRGS-Net for glare suppression. These methods improve image clarity, contrast, and reliability under extreme lighting variations. His research bridges theoretical advancements in AI with direct automotive applications, aiming to enhance driver safety and situational awareness. By integrating machine learning, computer vision, and practical engineering, Yang’s work represents a significant contribution to the future of intelligent transportation, ensuring that image-based systems perform optimally in challenging environmental conditions both in research and industrial deployment

 

Publications

 

Title: NRGS-Net: A Lightweight Uformer with Gated Positional and Local Context Attention for Nighttime Road Glare Suppression

Year:2025

Conclusion

Yang Ruoyu is a dedicated and innovative researcher whose expertise in AI-driven image processing, particularly for nighttime road enhancement and glare suppression, combines strong academic foundations, practical project execution, patented technologies, and internationally recognized publications to deliver impactful solutions for intelligent automotive systems.

Alvaro Garcia | Computer vision | Best Researcher Award

Published on by Cognitive Scientist Awards

Dr. Alvaro Garcia | Computer vision | Best Researcher Award

Álvaro García Martín es Profesor Titular en la Universidad Autónoma de Madrid, especializado en visión por computadora y análisis de video. 🎓 Obtuvo su título de Ingeniero de Telecomunicación en 2007, su Máster en Ingeniería Informática y Telecomunicaciones en 2009 y su Doctorado en 2013, todos en la Universidad Autónoma de Madrid. 🏫 Ha trabajado en detección de personas, seguimiento de objetos y reconocimiento de eventos, con más de 22 artículos en revistas indexadas y 28 en congresos. 📝 Ha realizado estancias en Carnegie Mellon University, Queen Mary University y Technical University of Berlin. 🌍 Su investigación ha contribuido al desarrollo de sistemas de videovigilancia inteligentes, análisis de secuencias de video y procesamiento de señales multimedia. 📹 Ha sido reconocido con prestigiosos premios y ha participado en múltiples proyectos europeos de innovación tecnológica. 🚀

Profile

Education 🎓

🎓 Ingeniero de Telecomunicación por la Universidad Autónoma de Madrid (2007). 🎓 Máster en Ingeniería Informática y Telecomunicaciones con especialización en Tratamiento de Señales Multimedia en la Universidad Autónoma de Madrid (2009). 🎓 Doctor en Ingeniería Informática y Telecomunicación por la Universidad Autónoma de Madrid (2013). Su formación ha sido complementada con estancias en reconocidas universidades internacionales, incluyendo Carnegie Mellon University (EE.UU.), Queen Mary University (Reino Unido) y la Technical University of Berlin (Alemania). 🌍 Durante su doctorado, recibió la beca FPI-UAM para la realización de su investigación. Su sólida formación académica le ha permitido contribuir significativamente al campo del análisis de video y visión por computadora, consolidándose como un experto en la detección, seguimiento y reconocimiento de eventos en secuencias de video. 📹

Experience 👨‍🏫

🔬 Se unió al grupo VPU-Lab en la Universidad Autónoma de Madrid en 2007. 📡 De 2008 a 2012, fue becario de investigación (FPI-UAM). 🎓 Entre 2012 y 2014, trabajó como Profesor Ayudante. 👨‍🏫 De 2014 a 2019, fue Profesor Ayudante Doctor. 📚 De 2019 a 2023, ocupó el cargo de Profesor Contratado Doctor. 🏛️ Desde septiembre de 2023, es Profesor Titular en la Universidad Autónoma de Madrid. 🏆 Ha participado en múltiples proyectos europeos sobre videovigilancia, transmisión de contenido multimedia y reconocimiento de eventos, incluyendo PROMULTIDIS, ATI@SHIVA, EVENTVIDEO y MobiNetVideo. 🚀 Ha realizado estancias de investigación en Carnegie Mellon University, Queen Mary University y Technical University of Berlin. 🌍 Su experiencia docente abarca asignaturas en Ingeniería de Telecomunicaciones, Ingeniería Informática e Ingeniería Biomédica.

Research Interests 🔬

🎯 Su investigación se centra en la visión por computadora, el análisis de secuencias de video y la inteligencia artificial aplicada a entornos de videovigilancia. 📹 Especialista en detección de personas, seguimiento de objetos y reconocimiento de eventos en video. 🧠 Desarrolla algoritmos de aprendizaje profundo y visión artificial para mejorar la seguridad y automatización en ciudades inteligentes. 🏙️ Ha trabajado en proyectos sobre videovigilancia, transmisión multimedia y detección de anomalías en video. 🔬 Su investigación incluye procesamiento de imágenes, análisis semántico y redes neuronales profundas. 🚀 Participa activamente en proyectos internacionales y colabora con universidades como Carnegie Mellon, Queen Mary y TU Berlin. 🌍 Ha publicado en IEEE Transactions on Intelligent Transportation Systems, Sensors y Pattern Recognition, consolidándose como un referente en el campo de la visión por computadora. 📜

Awards & Recognitions 🏅

🥇 Medalla “Juan López de Peñalver” 2017, otorgada por la Real Academia de Ingeniería. 📜 Reconocimiento por su contribución a la ingeniería española en el campo de la visión por computadora y análisis de video. 🏛️ Ha recibido financiación para múltiples proyectos de investigación europeos y nacionales. 🔬 Ha participado en iniciativas de innovación en videovigilancia y análisis de video para seguridad. 🚀 Sus contribuciones han sido publicadas en las principales conferencias y revistas científicas del área. 📚 Su trabajo ha sido citado más de 4500 veces y cuenta con un índice h de 16 en Google Scholar. 📊

Publications 

1. Rafael Martín-Nieto, Álvaro García-Martín, Alexander G. Hauptmann, and Jose. M.
Martínez: “Automatic vacant parking places management system using multicamera
vehicle detection”. IEEE Transactions on Intelligent Transportation Systems, Volume 20,
Issue 3, pp. 1069-1080, ISSN 1524-9050, March 2019.

2. Rafael Martín-Nieto, Álvaro García-Martín, Jose. M. Martínez, and Juan C. SanMiguel:
“Enhancing multi-camera people detection by online automatic parametrization using
detection transfer and self-correlation maximization”. Sensors, Volume 18, Issue 12, ISSN
1424-8220, December 2018.

3. Álvaro García-Martín, Juan C. SanMiguel and Jose. M. Martínez: “Coarse-to-fine adaptive
people detection for video sequences by maximizing mutual information”. Sensors,
Volume 19, Issue 4, ISSN 1424-8220, January 2019.

4. Alejandro López-Cifuentes, Marcos Escudero-Viñolo, Jesús Bescós and Álvaro GarcíaMartín: “Semantic-Aware Scene Recognition”. Pattern Recognition. Accepted February
2020.

5. Paula Moral, Álvaro García-Martín, Marcos Escudero Viñolo, Jose M. Martinez, Jesus
Bescós, Jesus Peñuela, Juan Carlos Martinez, Gonzalo Alvis: “Towards automatic waste
containers management in cities via computer vision: containers localization and geopositioning in city maps”. Waste Management, June 2022.

6. Javier Montalvo, Álvaro García-Martín, Jesus Bescós: “Exploiting Semantic Segmentation
to Boost Reinforcement Learning in Video Game Environments”. Multimedia Tools and
Applications. September 2022.

7. Paula Moral, Álvaro García-Martín, Jose M. Martinez, Jesus Bescós: “Enhancing Vehicle
Re-Identification Via Synthetic Training Datasets and Re-ranking Based on Video-Clips
Information”. Multimedia Tools and Applications. February 2023.

8. Roberto Alcover-Couso, Juan C. SanMiguel, Marcos Escudero-Viñolo and Alvaro GarciaMartin: “On exploring weakly supervised domain adaptation strategies for semantic
segmentation using synthetic data”. Multimedia Tools and Applications. February 2023.

9. Juan Ignacio Bravo Pérez-Villar, Álvaro García-Martín, Jesús Bescós, Marcos EscuderoViñolo: “Spacecraft Pose Estimation: Robust 2D and 3D-Structural Losses and
Unsupervised Domain Adaptation by Inter-Model Consensus”. IEEE Transactions on
Aerospace and Electronic Systems. August 2023.

10. Javier Montalvo, Álvaro García-Martín, José M. Martinez. “An Image-Processing Toolkit
for Remote Photoplethysmography”, Multimedia Tools and Applications. July 2024.

11. Juan Ignacio Bravo Pérez-Villar, Álvaro García-Martín, Jesús Bescós, Juan C. SanMiguel:
“Test-Time Adaptation for Keypoint-Based Spacecraft Pose Estimation Based on
Predicted-View Synthesis”. IEEE Transactions on Aerospace and Electronic Systems.
May 2024.

12. Kirill Sirotkin, Marcos Escudero-Viñolo, Pablo Carballeira, Álvaro García-Martín:
“Improved Transferability of Self-Supervised Learning Models Through Batch
Normalization Finetuning”. Applied Intelligence. Aug 2024.

13. Javier Galán, Miguel González, Paula Moral, Álvaro García-Martín, Jose M. Martinez:
“Transforming Urban Waste Collection Inventory: AI-Based Container Classification and
Re-Identification”. Waste Management, Feb 2025.