I'm going to jump in here as someone who is using object detection, and currently working on getting a Darknet detector in particular up and running, in what I'd like to think is a positive way.
I'm a researcher working on a system for monitoring offshore kelp farms for renewable aquaculture with an autonomous underwater vehicle. I can't use GPS underwater, Dopper velocity logs and sensitive inertial navigation systems are either too expensive and/or export-controlled, and doing manual filtering of visual data is tricky and inconsistent. Adding good object detection for kelp to helps to make that kind of system much more reliable, which can help provide useful metrics to groups working on creating new biofuel sources and marine ecosystem monitoring. I think that's valuable work, and it's enabled by YOLO.
Joe Redmon has paid attention to where and how his work is being used, and I respect him for disengaging with something that he finds not to line up with his values. But it's worth pointing out that there are people (not just me) who are using that work in ways that might be worthwhile.
I appreciate that, I think they have a lot of promise as well! I do think things are probably a bit early to be trying to do an AMA (I feel that they're often as much Q&A as they are a pitch about the topic itself), and both the tech and farm structure at the moment are both up in the air.
For example, the robotics end is currently a human-piloted ROV with data getting obtained in post-processing on dozens of fronds, rather than an AUV doing real-time inference (hopefully to be solved by YOLO) on thousands. However, I recently heard about some tentative plans for a more in-depth pilot-scale effort in Spring/Summer 2021, by which time we'll hopefully have some more interesting results to talk about!
We're still working on the first draft of our results for publication on the subsurface imaging side of things, so there's unfortunately not a paper I can point you to yet, but an overview of the project at a high-level can be seen here [1]. If you're really interested, feel free to reach out to me over email, and I'd be happy to discuss things and learn about what you're doing as well!
You wouldn't happen to have been part of the group that came over to Santa Barbara a while back, were you? I worked with Erin and Sean to get some of the sidescan data on the test lines out here with a REMUS 100 one afternoon.
I'm a researcher working on a system for monitoring offshore kelp farms for renewable aquaculture with an autonomous underwater vehicle. I can't use GPS underwater, Dopper velocity logs and sensitive inertial navigation systems are either too expensive and/or export-controlled, and doing manual filtering of visual data is tricky and inconsistent. Adding good object detection for kelp to helps to make that kind of system much more reliable, which can help provide useful metrics to groups working on creating new biofuel sources and marine ecosystem monitoring. I think that's valuable work, and it's enabled by YOLO.
Joe Redmon has paid attention to where and how his work is being used, and I respect him for disengaging with something that he finds not to line up with his values. But it's worth pointing out that there are people (not just me) who are using that work in ways that might be worthwhile.