ChallengeRocket
  • Product
    • Recruitment Challenges
    • Skill Assessment
    • Direct Hire
    • Hackathons
    • Intern Challenges
  • Challenges
  • Case-studies
  • Employers
  • Log in
  • Join talent network
  • Book demo
Menu
  • Home
  • Challenges
  • NVIDIA® Jetson™ Developer Challenge

This Challenge is completed

NVIDIA® Jetson™ Developer Challenge

NVIDIA® Jetson™ Developer Challenge
  • Winners announced
  • Winners announced
prize pool $42,789

SEE RESULTS

SEE RESULTS

Oct 23, 2017 - Feb 18, 2018 23:59 UTC
Voting: Feb 19 - Mar 04, 2018 23:59 UTC
  • Challenge outline
  • Resources
  • Participants
  • Projects
  • FAQ
  • Results
  • Updates
  • Rules
NVIDIA® Jetson™ Developer Challenge
  • Challenge outline
  • Resources
  • Participants
  • Projects
  • FAQ
  • Results
  • Updates
  • Rules

AS

Ayman Saleh

Added: Feb 18, 2018

Khalid Khalil
Ayman Saleh

TAGS

  1. Drones,
  2. Deep Learning,
  3. AI,
  4. Neural Networks,
  5. Python,
  6. C++,
  7. Kalman Filters,
  8. Computer Vision,
  9. ROS

TYPE OF PROJECT

Unmanned Aerial Vehicle

VOTES: 207 LIKES: 45

TITUS

  • play
  • TITUS
  • TITUS

    Project description

    TITUS is an autonomous Unmanned Aerial Vehicle (UAV) focused on inspecting forests to determine areas of possible risk to wildfires. To accomplish this task of classifying the hazardous areas, we focused on developing a UAV that can navigate through a dense forest environment autonomously, classify areas of risk to wildfires, and be cost effective at the same time. The main feature of TITUS that differentiates itself from any other autonomous UAVs is that it only has one camera as its perception sensor for Simultaneous Localization and Mapping (SLAM). This can only be possible with the on board GPU that the Jetson platform provides along with the NVIDIA CUDA API. The next section will explain how we are able to develop real time depth maps with a single monocular camera.


    MonoSLAM:


    We have developed a novel approach to achieving Simultaneous Localization and Mapping (SLAM) from a single moving camera. This approach uses two inputs to an extended Kalman Filter to generate a probabilistic depth measurement on a per-pixel basis. The first input is an implementation of REMODE SLAM developed by Professor Scaramuzza, Christian Forster, and Matia Pizzoli. This approach combines Bayesian Estimation and convex optimization for image processing. Uncertainty is computed to reject erroneous estimations and provide live feedback to the depth map reconstruction. Camera pose estimates are computed in the following sequence of steps, every time step k, the pose of the camera T(k,r) in the depth map reference frame is calculated by utilizing visual based odometry. We build upon this method by extracting the inertial measurement unit navigation messages from our flight controller and publishing those messages as a ROS node. Since visual odometery is the main contributor to the probability of the depth measurement, utilizing ground truth estimates from the Pixhawk (this is the brand of our flight controller) allows our model to tend more towards a deterministic measurement. As the camera pose is updated, the transform of the plane is mapped to depth viewer and checked for error threshold. The other input is the output of a linear regression calculation that is done to predict the depth of a pixel in an image. The regression is trained on a data set of rgb-d data which takes into account the light threshold in the image, the true depth to each pixe,l and the rgb channel values of each pixel. Since our deployment environment is in a forest, we make the assumption that we can ignore drastic changes in light for most conditions. As a result we only weigh the estimation of the regression ⅕ of the REMODE estimation. We have seen great results for areas of low light with this method.


    3D Classification of underbrush:


    In order to classify underbrush from our generated 3D scans, we utilize Point Net. A deep learning framework developed by Stanford University for deep learning on geometric data structures. This includes the segmentation and classification of objects in point cloud data. On the backed for part segmentation of the generated map, a volumetric convolutional neural network is used to detect and segment the part. We collected a medium sized amount of 3D scans utilizing our MonoSlam algorithm to collect data of underbrush to train the network. We also optimized the architecture design to run on the Jetson for classification of underbrush in real time.



    • previous project
    • next project

    Comment


    Please login to leave a comment


    Comments (3)

    1. j

      janajaber4433

      thats Great project! love it

    2. a

      alkuran

      Great project!

    3. v

      vinnysilmi

      That's a great idea hope everything works well and it it becomes a huge success GW


    ChallengeRocket
    Tech talent
    Challenges Blog Find jobs Employers
    Companies
    Business HR Blog Pricing
    Challengerocket
    FAQ EU Join Us Contact Us
    Copyright © 2023 ChallengeRocket. All rights reserved.
    Privacy Terms and Conditions Service status

    Let’s talk

    Proven effectiveness - get up to x3 more candidates and shorter recruitment time.

    In view of your consent, the data you provide will be used by ChallengeRocket Sp. z o.o. based in Rzeszów (address: Pl. Wolności 13/2, 35-073, +48 695 520 111, office@challengerocket.com) to send messages as part of the newsletter subscription. Don't worry, only us and the entities that support us in our activities will have access to data. All information on data processing and your rights can be obtained by contacting us or at www.challengerocket.com in the Privacy Policy tab.

    We will reply within 2 business days.

    Log in


    Forgot your password?

    OR
    Don’t have an account?
    Create a candidate account or a company account

    Log in

    Forgot your password?

    Create a candidate account

    Already have an account?
    Log in
    OR
    • At least 10 characters
    • Uppercase Latin characters
    • Lowercase Latin characters
    • At least one number or symbol

    Not a candidate?  Sign up as an employer

    Reset your password

    Remember your password? Log in Log in for business

    Create an employer account

    Sign up for free.
    Select the best plan to publish job ofers & challenges.

    Company name introduced here will be visible on your job ads.
    • At least 10 characters
    • Uppercase Latin characters
    • Lowercase Latin characters
    • At least one number or symbol

    Not an employer?  Sign up as a candidate