Hacker News new | ask | show | jobs
by Joel_Mckay 118 days ago
Cameras have all the same problems of lidar, and none of the advantages. Show a lidar a 45' mirror/weather-glass to test what your $60k bought.

Monocular feature extraction has been around for decades, but is only reliable for people that never go outside in the sun/dust/rain. =3
1 comments
irishcoffee 116 days ago
The point was how fragmented the "community" has become.

Also, the talk about visual camera point could generation was very impressive.

Lidar also suffers from the environment, and angles, and reflection, and light sources.

link
Joel_Mckay 116 days ago
In general, lidar is used to remove the ambiguity in a local ground scan, and cameras extrapolate overlapping texture gradients to guess distant surface structure ( documented in the old book https://www.amazon.com/Learning-OpenCV-Computer-Vision-Libra... .)

There are some fairly good FOSS tools around like COLMAP, if you want to learn why automatic monocular pose recovery and SfM is hard.

Real autonomous robotics is hard, and people make the same predictable mistakes every 4 years. Retrofitting a consumer Yarbo would be cool though. =3

link
irishcoffee 116 days ago
I'm not sure how you ended up here.

I'm quite familiar with robotics and lidar, and ground planes, and ROS. Not sure what 4-year cycle you're talking about.

link
Joel_Mckay 116 days ago
>Not sure what 4-year cycle you're talking about.

I observe many groups solving platform design issues also eventually move on to other projects or careers. The dozens of documented fools-errands from Academic literature and Commercial sectors are eventually lost again each time. There are various institutional structural reasons this occurs, but the outcome is usually the same.

One must accept many problems are not purely technical in nature, and unfortunately complex Mechatronics often tend to exhibit sustainability problems.

>I'm not sure how you ended up here.

Don't worry about it... =3

link