Wildlife Protection System for Train Safety
--
https://github.com/Vinonsan/Srilankan-Railway-Safety-system <-- shared GitHub repository
--
#GIS #spatial #mapping #TechForGood #WildlifeConservation #AI #MachineLearning #ObjectDetection #ReactJS #NodeJS #Innovation #Sustainability #ConservationTech #AIForConservation #srilanka #risk #hazard #safety #model #modeling #mitigation #elephant #bull #wildlife #livestock #protection #realtime #detection #weather #safety #railroad #train #transportation #infrastructure #spatialanalysis #conservation #railway #railroad #economics

Roboflow has launched RF-DETR, a real-time object detection model..

#AI #MachineLearning #ComputerVision #VisionAI #ObjectDetection #Roboflow #RFDETR #EdgeAI #DeepLearning #RealTimeAI #AIModels

https://winbuzzer.com/2025/03/24/roboflows-rf-detr-real-time-object-detection-model-redefines-vision-ai-raising-ethical-questions-xcxwbn/

Comparing YOLOv11 and YOLOv12: A Deep Dive into the Next-Generation Object Detection Models

This in-depth comparison explores the key differences between YOLOv11 and YOLOv12, analyzing their technical advancements, performance metrics, and applications across industries.

https://so-development.org/comparing-yolov11-and-yolov12-a-deep-dive-into-the-next-generation-object-detection-models/

Mielenkiintoinen tämä #norppalive n norppien tunnistus "tietokonenäön" avulla. Kiitos @Dilaz kun jaat näitä videoita! Aina oppii uutta, kuinka "näkö" toimii konkreettisesti. Video löytyy linkin takaa Blueskystä.

https://bsky.app/profile/dilaz.bsky.social/post/3lh53haumrc2b

OpenCVのInpaintingでオクルージョン画像の物体検出精度向上
https://qiita.com/Kazuhito/items/87b41542f71abd89cf62?utm_campaign=popular_items&utm_medium=feed&utm_source=popular_items

In this tutorial in Python and OpenCV, we'll explore how to find differences in similar images.

You can find more similar tutorials in my blog posts page here : https://eranfeit.net/blog/

check out our video here : https://youtu.be/03tY_OF0_Jg&list=UULFTiWJJhaH6BviSWKLJUM9sg

Enjoy,
Eran

Meta Doesn’t Allow Camera Access on VR Headsets, So Here’s a Workaround - The cameras at the front of Meta’s Quest VR headsets are off-limits to developers,... - https://hackaday.com/2024/08/18/meta-doesnt-allow-camera-access-on-vr-headsets-so-heres-a-workaround/ #objectdetection #virtualreality #softwarehacks #mobilenet #quest #vr

"Introduction to Object Detection Model Evaluation"

Déborah Mesquita

https://towardsdatascience.com/introduction-to-object-detection-model-evaluation-3a789220a9bf?source=rss-dd9e06a0a640------2

Follow this 10 minutes tutorial , for detecting text on images !

My blog posts page : https://eranfeit.net/blog/

check out our tutorial here : https://youtu.be/DycbnT_pWKw&list=UULFTiWJJhaH6BviSWKLJUM9sg

Enjoy,
Eran

"AutoML for Object Detection: How to Train a Model to Identify Potholes"

Déborah Mesquita

https://towardsdatascience.com/automl-for-object-detection-how-to-train-a-model-to-identify-potholes-e22c3f4b774?source=rss-dd9e06a0a640------2

Distracted.

Instead of working on the Darknet configuration code I meant to work on today, I modified the support discord server, and implemented a bunch of new functionality in the Darknet/YOLO Bot.

See the results here: https://discord.gg/zSq8rtW

Interact with the bot by typing commands such as "help", "repo", "faq", and "kick me".

I've been facing many issues with using #Poetry (#pythonpoetry) with my #Python based #objectdetection project. I love Poetry for publishing packages, but think that #conda would be better since I have to deal with #CUDA and whatnot. Anyone familiar with a way to use `pyproject.toml` for publishing and building packages, even if Poetry isn't being used for dependency management?

For context, here's the project I'm working on: https://github.com/slashtechno/wyzely-detect

"AutoML for Object Detection: How to Train a Model to Identify Potholes"

Déborah Mesquita

https://towardsdatascience.com/automl-for-object-detection-how-to-train-a-model-to-identify-potholes-e22c3f4b774?source=rss-dd9e06a0a640------2

Need To Pick Objects Out Of Images? Segment Anything Does Exactly That - Segment Anything, recently released by Facebook Research, does something that most... - https://hackaday.com/2023/04/14/need-to-pick-objects-out-of-images-segment-anything-does-exactly-that/ #artificialintelligence #machinelearning #objectdetection #machinevision #segment #ai

Adversarial attacks as a way of understanding differences in #human and #machine "#perception"

Sorry for tired and dishevelled late night recording, but some parts are, even 3 yrs (and many models&methods) later, relevant to the current discourse

https://vimeo.com/475121381/4f7255ada3

Hey #DH #CSS ppl! What is your favorite platform/method of generating labeled training data from images? Have about ten categories that I need to annotate and hoping to have at least 100 examples for each category. Also the dataset is historic Newspaper indices (so lots of weird tables and numbers)

I've known ppl who have used Makesense https://www.makesense.ai/ previously and also very much considering taking the plunge and buying a Prodigy https://prodi.gy/ license. So any advice would be appreciated!

Some exciting tests with #yolov8 #AI #objectdetection for mapping #beaver dams and lodges in #Alaska on #aerial #imagery with ~5-10 cm GSD.

Quite promising results for now.

Labelling and data preparation with #roboflow
#deeplearning

Diffusion meets Object Detection

DiffusionDet: Diffusion Model for Object Detection

• It formulates object detection as a denoising diffusion process
from noisy boxes to object boxes

• At training, object boxes diffuse from ground-truth boxes to random distribution

• The model learns to reverse this noising process

• During inference, the model gradually refines a set of randomly generated boxes to refine the results

https://detector.uber.space/demo/ This is a demo of a detector for #farright symbols like swastika, ss skull and the SS Insignia. it' using #tensorflowjs so everything happens in the browser. I'll gladly share the data-sets, just reach out #datascience #ml #objectdetection #sociology