Manlio Barajas, PhD

Applied computer vision

Showcase demo

Superpixel Mesh / Aligning a mesh to any image

About me

Computer vision engineer working on 3D reconstruction with some fullstack dev skills. I have worked mostly for US startups solving challenges for which computer vision has a solution.

My value proposition:

Production grade code.  You don't need to refactor everything upon completion. Research, code and productionize as it makes sense.

Computer vision + full stack.  If your project has the right time-to-market but some budget constraints at the same time, I can take on fullstack duties.

Culture and communication.  I have worked for 6 years for US based companies. My main timezone is CST, yet it is flexible.

Complexity not a problem.  I have architected and implemented year long projects smoothly. Comfortable coaching.

Code I have written is running in production in the 5 continents

Experience

Computer vision

  • Structure from motion
  • SLAM using GPS, IMU, LiDAR and vision
  • Multiview stereo
  • Photogrammetry
  • Surface reconstruction
  • Pointcloud processing
  • Calibration
  • Spatial reference transforms (GIS)

Computer vision libraries

  • OpenCV, PointcloudLibray (PCL)
  • SfM VLFeat, FLANN, OpenMVG
  • Multiview stereo PMVS, SMVS
  • Computational geometry PoissonRecon, CGAL
  • Math Eigen, ceres-solver
  • Visualization VTK
  • Parallelization OpenMP, CUDA (beginner)

Software engineering

  • Languages C++, Javascript, Python, Bash, C#, PHP
  • Cloud (AWS): EC2, Lightsail, Elastic Beanstalk, S3, Lambda, API Gateway, Cloudfront, Route53. (GCP): AppEngine
  • Databases MySQL, MS-SQL Server, MongoDB
  • Tools Docker, CMake, Make, GTest, GPerfTools, Protobuf, emscripten
  • Frameworks Qt, Node.JS, React, tensorflow (beginner)