no code implementations • 11 Mar 2024 • Bianca-Cerasela-Zelia Blaga, Sergiu Nedevschi
Humans use UAVs to monitor changes in forest environments since they are lightweight and provide a large variety of surveillance data.
no code implementations • 14 Oct 2022 • Andra Petrovai, Sergiu Nedevschi
Depth-aware video panoptic segmentation tackles the inverse projection problem of restoring panoptic 3D point clouds from video sequences, where the 3D points are augmented with semantic classes and temporally consistent instance identifiers.
no code implementations • 7 Oct 2022 • Andra Petrovai, Sergiu Nedevschi
We propose a novel solution for the task of video panoptic segmentation, that simultaneously predicts pixel-level semantic and instance segmentation and generates clip-level instance tracks.
no code implementations • CVPR 2022 • Andra Petrovai, Sergiu Nedevschi
To improve the performance of our estimates, in the second step, we re-train the network with the scale invariant logarithmic loss supervised by pseudo labels.
no code implementations • CVPR 2017 • Arthur Daniel Costea, Robert Varga, Sergiu Nedevschi
In this paper we propose a novel boosting-based sliding window solution for object detection which can keep up with the precision of the state-of-the art deep learning approaches, while being 10 to 100 times faster.
no code implementations • CVPR 2016 • Arthur Daniel Costea, Sergiu Nedevschi
However most of the top performing approaches provide state of art results at high computational costs.
no code implementations • CVPR 2014 • Arthur Daniel Costea, Sergiu Nedevschi
By using a GPU implementation we achieve a classification rate of over 10 million bounding boxes per second and a 16 FPS rate for multiscale detection in a 640×480 image.