Estimating the metric distance between persons from a single video..
- Our work has been accepted to the DiffCVGP workshop @ NeurIPS 2020!
- I am excited to join the computer vision lab at UBC as a research assistant!
- Happy to have been involved at the following conferences; CVPR, ICML, and MLSS in 2020.
- Very excited to be a part of ICLR 2020 conference, as a volunteer !
My work has largely focused on solving problems in deep learning, visual understanding, 2D & 3D vision, Image & Video processing
3D Human Pose Estimation from Single Videos
An End-End integral pose regression for 2D and 3D Human pose estimation.
Instance segmentation was carried out on a nuts custom dataset that was trained on an object detection library (Detectron2).
A simple object tracking system that detects objects on all video frames using predictions from a detectron model and links these detections across the temporal domain.
Estimating the location of 68 distinguishing keypoints on human faces.
Automatically generating captions that describe the content in images.
Implementing a real-time object detection with Tensorflow and OpenCV.
Implementing SLAM (Simultaneous Localization and Mapping) for a 2 dimensional world!.
- Ajisafe D., Domguia J., Tang J., Ellenberger L., Spörri J. and Rhodin H. (2020) Towards end-to-end training of proposal-based 3D human pose estimation. (Accepted to DiffCVGP Workshop at Neurips 2020) Paper
- It was such an honor to speak on the “The Future of Artificial Intelligence in Africa and in the Diaspora” at Kampala International University.
Get In Touch
Would you like say hi, I would be glad to hear from you.