aminebdj

3D-OWIS

[NeurIPS2023] 3D-OWIS is capable of detecting unknown instances in inference, and progressively learning novel classes in the process of training.

OpenYOLO3D

Our OpenYOLO3D model achieves state-of-the-art performance in Open Vocabulary 3D Instance Segmentation on ScanNet200 and Replica datasets with up ∼16x speedup compared to the best existing method in literature.

mask3d_cs

aminebdj.github.io

Autonomous_robot_with_Arduino

An autonomous robot with PID controllers, navigation system and obstacle avoidance algorithm.

FCD

human-pose-estimation

We represent our modification of Stacked Hourglass Networks, which significantly increases performance by 13% regarding model speed with an increase in accuracy by around 0.7%

Non-Linear-obsever-for-SLAM

This code contains a python based simulation of a non linear observer to estimate the global pose of a UAV and the absolute locations of some surrounding landmarks, using some relative measurements taken from a camera and an IMU.

pert_ssl

prob

segmformer-deeplabv3p-analysis

In this project, we conducted a comparative analysis of Segformer, a ViT-based semantic segmentation model, and DeeplabV3+, a CNN-based semantic segmentation model, using various image perturbations (e.g., image patch shuffling and removal) and noise addition (e.g., salt and pepper noise).

Sequence_robot

This code is for a robot constructed using an ARDUINO MEGA, H bridge,2 DC motors (CQROBOT), and an ultrasonic sensor. it follows a given sequence of premade states. inside the code, you will find several states that you can edit as you like, including a rotation state for a 45 degrees rotation and other states for linear translation

video-preprocessing