Giter VIP home page Giter VIP logo

Alexandre Gas's Projects

assembly_routing_generator icon assembly_routing_generator

This project consists in the design and implementation of a python program, which describes a new assembled manufactured product, its components, relations and technical solutions used to maintain them together, and the function/role each component carries. Once the product is described, ideally, the program must be able to automatically compute a functional assembly routing.

coding-deep-neural-networks-from-scratch icon coding-deep-neural-networks-from-scratch

In this project, I coded Deep Neural Networks from scratch: using only Numpy. I implemented different layers: Fully Connected, Convolutional, Dropout. I also implemented Batch Normalization. I vectorized the entire process to reduce computational time.

computational_robotics icon computational_robotics

The workspace for our computational robotics class. I explored different techniques such as Bayesian filtering in a Gridworld environment, Graph Based Motion Planning on a chess board, Kalman Filtering... Work in progress !

covid-diagnosis-from-chest-xrays icon covid-diagnosis-from-chest-xrays

In this project, I implemented a framework to try and infer COVID diagnosis from chest X-rays. I first trained a specific U-net to generate masks to segment specific areas of chest x-rays, and CNNs to infer Covid-19 diagnosis on the segmented areas of the lungs.

data_science icon data_science

Contains all the files linked with my Data_Science project

lane-lines-detection---udacity icon lane-lines-detection---udacity

In this project, I use classical computer vision techniques to detect lane lines on road recordings. After applying color filters to outline the road markings, I use Gaussian smoothing and Canny Edge detection to extract points belonging to the lane lines. I extract the lines using the Hough transform.

path-planning-in-a-dynamic-environment icon path-planning-in-a-dynamic-environment

A cool project in which we do path planning in an environment with moving obstacles and large scale fixed obstacles. We use two different representations of the world to handle the fixed and moving obstacles.

pedestrian-intention-prediction icon pedestrian-intention-prediction

In this project, I use convolutional and LSTM neural networks to predict pedestrian intention (crossing the road or staying still). The dataset used is the JAAD dataset, which provides clips of pedestrians crossing the street, as well as useful metadata. I built a complete pipeline to process this dataset and make it suitable for neural networks.

softmax_classifier_and_knn_from_scratch icon softmax_classifier_and_knn_from_scratch

In this project, I implement a softmax classifier and a K-nearest-neighbor algorithm from scratch and train them. I do not use any DL library, only classic math libraries are required (numpy, math, mathplotlib...).

subspace-sparse-clustering---lidar-data icon subspace-sparse-clustering---lidar-data

In this project, I applied robust spectral clustering techniques to LiDAR scans to outline lines in the environment. After matching the lines across different scans, I can deduce the rotation and translation of the robot between each LiDAR scan.

visual-odometry---trajectory-tracking_matlab icon visual-odometry---trajectory-tracking_matlab

In this project, I computed the trajectory of an object from a sequence of images by extracting and tracking specific features of the object. I eliminated matches violating the epipolar constraint to improve accuracy.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.