Register now After registration you will be able to apply for this opportunity online.
Low Latency Occlusion-aware Object Tracking
Low Latency Occlusion-aware Object Tracking
Keywords: Object Tracking; Event Cameras
In this project, we will develop a low-latency, robust to occlusion, object tracker. Three main paradigms exist in the literature to perform object tracking: Tracking-by-detection, Tracking-by-regression, and Tracking-by-attention. We will start with a deep literature review to evaluate the current solutions to our end goal of being fast and robust to occlusion. Starting from the conclusions of this study, we will design a novel tracker that can achieve our goal. In addition to RGB images, we will investigate other sensor modalities such as inertial measurement units and event cameras. We will use the Meta Aria smart glasses (Meta Aria Project: https://www.projectaria.com/).
In this project, we will develop a low-latency, robust to occlusion, object tracker. Three main paradigms exist in the literature to perform object tracking: Tracking-by-detection, Tracking-by-regression, and Tracking-by-attention. We will start with a deep literature review to evaluate the current solutions to our end goal of being fast and robust to occlusion. Starting from the conclusions of this study, we will design a novel tracker that can achieve our goal. In addition to RGB images, we will investigate other sensor modalities such as inertial measurement units and event cameras. We will use the Meta Aria smart glasses (Meta Aria Project: https://www.projectaria.com/).
Develop a low-latency object tracker that is robust to occlusions. We look for students with a strong computer vision background and familiar with common software tools used in Deep Learning (for example, PyTorch or TensorFlow).
Develop a low-latency object tracker that is robust to occlusions. We look for students with a strong computer vision background and familiar with common software tools used in Deep Learning (for example, PyTorch or TensorFlow).
