KAUST's Visual Computing Center (VCC) hosted an Open House event on March 28, showcasing its interdisciplinary research in visual computing. Demonstrations included a virtual reality driving simulator by FalconViz, intended for driver education in Saudi Arabia. Researchers also presented a drone trained to autonomously navigate race courses and a neural network for autonomous driving using image-based technology without GPS. Why it matters: The VCC's work highlights KAUST's role in advancing visual computing applications relevant to Saudi Arabia, from driver training to autonomous systems.
The National Center for Vegetation Cover Development and Combating Desertification (NCVC) and KAUST have launched the SAUDINet initiative. The initiative aims to advance terrestrial ecology research in Saudi Arabia, focusing on restoring degraded lands, enhancing carbon sequestration and preserving biodiversity. NCVC’s workforce will receive specialized training in biodiversity monitoring and ecological sampling, with samples analyzed in KAUST’s labs. Why it matters: The partnership aims to establish Saudi Arabia as a global leader in the study of arid ecosystems and address the lack of data from hyper-arid lands in climate models.
KAUST and The National Center for Vegetation Cover Development and Combating Desertification (NCVC) have launched an Experimental Station and Ecological Observatory in Wadi Qudaid National Park. The station aims to test environmental improvement interventions and desert afforestation methods, supporting the Saudi Green Initiative through research on the local plant environment via the KSA native genome project. KAUST Professor Rod Wing has led the project since 2022, hoping the station will contribute to the national revegetation project. Why it matters: The station represents a significant collaboration to address environmental challenges and promote sustainable practices in line with Saudi Arabia's green initiatives.
KAUST's Visual Computing Center (VCC) is researching computer vision, image processing, and machine learning, with applications in self-driving cars, surveillance, and security. Professor Bernard Ghanem is working on teaching machines to understand visual data semantically, similar to how humans perceive the world. Self-driving cars use visual sensors to interpret traffic signals and detect obstacles, while computer vision also assists governments and corporations with security applications like facial recognition and detecting unattended luggage. Why it matters: Advancements in computer vision at KAUST can contribute to innovations in autonomous vehicles and enhance security measures in the region.
KAUST and the National Center for Wildlife (NCW) are collaborating on research to protect Saudi Arabia's coastal ecosystems and marine economy from invasive species. They are conducting biodiversity surveys along the Red Sea and Arabian Gulf coasts, having surveyed 34 sites and collected over 10,000 samples. So far, 200 species with potential marine invasive traits have been identified, expanding the national knowledge base of marine life. Why it matters: The partnership aims to develop early detection and monitoring systems, fortifying Saudi Arabia's marine biosecurity efforts and supporting its Vision 2030 blue economy goals.
Researchers are exploring computer vision models to mitigate Camel-Vehicle Collisions (CVC) in Saudi Arabia, which have a high fatality rate. They tested CenterNet, EfficientDet, Faster R-CNN, and SSD for camel detection, finding CenterNet to be the most accurate and efficient. Future work involves developing a comprehensive system to enhance road safety in rural areas.
KAUST and the National Center for Wildlife (NCW) have signed an MoU to collaborate on research and environmental initiatives. The collaboration aims to protect ecosystems, preserve biodiversity, and enhance community awareness, formalized at the UNCCD COP16 in Riyadh. The MoU includes joint scientific research, genetic diversity projects, databases, community awareness campaigns, volunteer programs, and ecosystem monitoring. Why it matters: The partnership demonstrates Saudi Arabia's commitment to environmental sustainability and aligns with Vision 2030 and the Green Saudi Initiative.
Video-ChatGPT is a new multimodal model that combines a video-adapted visual encoder with a large language model (LLM) to enable detailed video understanding and conversation. The authors introduce a new dataset of 100,000 video-instruction pairs for training the model. They also develop a quantitative evaluation framework for video-based dialogue models.