Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
dronefreak 
posted an update 14 days ago
Post
3083
Excited to open-source the VisDrone Aerial Object Detection Model Zoo on Hugging Face.

The collection includes multiple YOLO variants trained and evaluated on the VisDrone benchmark for aerial object detection, with accompanying documentation and performance metrics.

If you're working on drones, aerial surveillance, robotics, or small-object detection, I hope these models save you some time.

Model Zoo: https://huggingface.co/collections/dronefreak/visdrone-detection-model-zoo

Feedback, issues, and contributions are welcome.
ArslanMehmood

Hi,
whats the difference between pedestrian and people?

·
dronefreak

Hi,

So what I understood from the paper is that pedestrian is classified as a type of person without any accessory like a bike or a scooter etc. Person/people according to the dataset are the ones on the roads on sidewalks on some kind of transport vehicles. Even though the authors did not specify this distinction, its what I understood.
warfazeee

Dear Mr. Saksena, I am a CSE student from Bangladesh, deeply inspired by your research in Computer Vision and Healthcare AI. I am currently working on deep learning projects and would be honored to connect and explore any future research collaboration opportunities with you. Respectfully, Md Masud Rana.

·
dronefreak

Hi Masud,

Thank you for your kind words. I will shortly start working on DOTA Aerial Detection Benchmark to evaluate the YOLO variants on this aerial dataset. We can collaborate on the development part if you want (although I might be able to work on this only on the weekends).
ara-25

I have tested your yolov26 models on a drone video I had (which was really low-quality) and they are giving good results. Was especially impressed by your yolov26-nano model which gave better detections than some of the other larger open-source models I tried, though those were trained on coco.

I would also suggest you to look into finetuning and experimenting with the yolo-master model too. Results from that one were closer to yours and they have an experimental sparse sahi implementation which may be useful.

Also, I have noticed that most of your models on huggingface are labeled with Apache 2.0 license. Maybe you should revisit that as both the VisDrone dataset and the Ultralytics models which you have trained on have different and more restrictive licenses.

·
dronefreak

Thanks for your kind words, and I am glad you found the models useful. You are right to remark about the yolo26-nano performance. I will be starting shortly trying to distill a yolov8s from yolo26-x, in the hopes of further improving the performance.

Also, thanks for your licensing remarks, I will update the licenses of the model cards to AGPL to follow the upstream model licenses.
In this post