Zahra Alharz

تخصص الذكاء الاصطناعي · دفعة 2025

Automatic Soccer Penalty Detection (Trajectory of Ball and Goalkeeper)

Detecting the trajectory of the soccer ball and goal keeper with their pose to predict whether the shot would cause a goal. From the collected data we can get statistics such as “Expected Goal on Target (xGOT)”. Furthermore, you can use similarity search from the detections to find similar penalty shots.

اقرأ التقرير النهائي (PDF)

اطّلع عليه في تقرير البرنامج (PDF)

تخصص الذكاء الاصطناعي · دفعة 2024

Beneath the Waves: Leveraging Sam for Coral Reef Dataset Generation & Advanced Vision Models

Inspired by the KAUST-Neom coral restoration project in the Red Sea, our work leverages advanced computer vision and deep learning to protect one of the most vital ecosystems on Earth. Coral reefs, essential to marine biodiversity but under threat from climate change and human activity, require innovative monitoring solutions. We developed an automated tool that uses precise segmentation to efficiently monitor coral health and support large-scale restoration. This technology aims to enhance global conservation efforts, providing real-time insights to help safeguard the future of our oceans.

اطّلع عليه في تقرير البرنامج (PDF)

تخصص الذكاء الاصطناعي · دفعة 2023

Sarid: Arabic Storyteller Using a Fine-Tuned LLM and Text-to-Image Generation

Sarid is an Arabic children’s story generator that combines AI-powered text and image generation. Through the utilization of OpenAl and Midjourney, we created a fine-tuned large language model that generates Arabic stories customized for the user. On the website, the user provides a description and selects the character, age, word count, tone, and theme of their story, which will be sent to the fine-tuned model and text-to-image generator. Sarid aims to fill the gap in Arabic storytelling and provides an interactive and immersive experience for young readers.

اطّلع عليه في تقرير البرنامج (PDF)