Solution OverviewFirst, I want to thank the Barbados Lands and Surveys Department for this incredible real-world challenge, Zindi Africa for hosting the competi... See more

Hello. It was an interesting competition. I took the most interesting 11th place. Given the story with the alleged disqualifications, I am waiting for confirmat... See more

Barbados Land Detection and OCR Project - Solution SummaryCode: https://github.com/josephgitau/Barbados-Lands-and-Surveys-Plot-Automation-Challenge/tree/mainPla... See more

.

I recently observed that leaderboard is mostly dominated by Kenyans. Yall have crazy talent.

I've tried mean, max ensembling of masks. For some reason, performance is worse

Greetings Zindians;I hope all is well with you all. I just needed help to see a sample bounding box.

Just wondering which yolo segmentation models produce the best results

After nearly three months of hard work, experimenting with different algorithms, testing model variations, and carefully examining every aspect of the dataset,... See more

It seems that some teams have started using manual labeling. Starting from this competition, there is an additional clause: “All data manipulation must be done... See more

Hey everyone, I’m kind of a latecomer to this challenge, and I honestly can’t figure out how you guys are using the geometry column.The given masks don’t overla... See more

Well as you can see, if you try to do any form of inferencing, it brings out this error. After a day of debugging and tears😭, I realized the bug is from unslot... See more

For: "Unit of Measurement' eaxtraction. Is it a must that we normalize all the extractions back to "sq m" or "ha" or we extract exact unit in each image ? Cheer... See more

96.2% IOU for Polygons. Hmmm my morale is gone😔. Let me leave it to Central Park and Joseph.

Honestly speaking, I'm a little disappointed. I was looking foward to chaos on LB since the OCR post.

I am wondering if I can annotate the data

We’ve seen the OCR part shake up the leaderboard... now it’s the segmentation teams holding the fort at the top 😎🔥So... any chance the best top 3 segmentation... See more

What’s the point of calling it a competition if originality doesn’t matter anymore? Some of us have spent weeks experimenting, building, and refining our own id... See more

The best segmentation model could secure victory in this challenge! 🚀

Hi all, if you want to achieve a Word Error Rate (WER) similar to mine, this pipeline should get you there. I used these exact notebooks for my best submission.... See more

I am wondering if parish values are always st. philip ie. the area the data was collected from. If not, how do we identify the parish value from the image(It is... See more

Are you lookingf or digital map digitization into vector shape files like shown in the video below: https://youtu.be/kDCJ9gafOYEor i tried to visualize the give... See more

Dear @Amy_Bray and Competition Organizers,I'm writing to raise a concern regarding the integrity of the provided training dataset, which appears to contain seve... See more

when i manually check my model prediction the surveyor , surveyed for and address all accurate same as on the image and i got high WER please we need clarificat... See more

Hi Everyone,As this competition is nearing the end, I'm curiouis to see who really took part to the competition with all the requirements.As for, I honestly did... See more