sayzard7h ago

Muhammad Rizwan Munawar (@muhammdrizwanmr)

Ultralytics YOLO26을 활용한 개인보호장비(PPE) 탐지 사례를 소개한다. 건설 현장에서 안전장비 착용 여부를 자동으로 식별해 산업 안전과 사고 예방에 활용할 수 있는 AI 비전 응용이다.

https://x.com/muhammdrizwanmr/status/2037021785254769035

#computervision #objectdetection #yolo #safetyai #ultralytics

Muhammad Rizwan Munawar (@muhammdrizwanmr) on X

Personal protective equipment detection with @ultralytics YOLO26 🦺 In the past year, the U.S. construction industry recorded approximately 169,200 nonfatal injuries. This equates to around 1% of construction workers sustaining injuries severe enough to result in missed

X (formerly Twitter)
HitechDigital Solutions3d ago

A closer look at image annotation in AI systems

Machines need labeled data to understand images. image annotation services provide that structure by marking objects and patterns. This helps AI systems process visual information and deliver more accurate and reliable outcomes.

Know more: https://www.hitechdigital.com/image-annotation-services

#ImageAnnotationServices #DataAnnotationServices #ImageLabeling #ComputerVision #AITrainingData #MachineLearning #ObjectDetection

sayzard6d ago

Muhammad Rizwan Munawar (@muhammdrizwanmr)

도로의 포트홀을 @ultralytics의 YOLO26으로 실시간 탐지하는 사례를 소개한다. 수동 도로 점검의 느린 속도와 높은 비용, 확장성 한계를 지적하며, 거리 영상이나 비디오 피드에서 객체 탐지를 활용해 더 빠르고 일관된 도로 유지보수를 가능하게 하는 혁신적 AI 응용이다.

https://x.com/muhammdrizwanmr/status/2034831468787085558

#objectdetection #computervision #yolo #ultralytics #smartcity

Muhammad Rizwan Munawar (@muhammdrizwanmr) on X

Pothole detection on the road in real time using @ultralytics YOLO26! 🕳️ Manual road inspections are slow, costly, and hard to scale. With object detection, potholes can be identified directly from street-level images or video feeds, enabling faster and more consistent road

X (formerly Twitter)
sayzardMar 17

Muhammad Rizwan Munawar (@muhammdrizwanmr)

Ultralytics의 YOLO26을 활용해 음료 캔을 자동으로 세는 비전 AI 사례입니다. 몇 줄의 Python 코드와 object counting 솔루션으로 생산 라인 쪽으로 이동하는 캔을 실시간 집계하는 데모를 구현했다고 소개합니다. 간단한 코드로 산업용 카운팅 워크플로우를 빠르게 구축할 수 있음을 보여주는 실용적 사용 사례입니다.

https://x.com/muhammdrizwanmr/status/2033740239593001347

#ultralytics #yolo #objectdetection #python #computervision

Muhammad Rizwan Munawar (@muhammdrizwanmr) on X

Drink can counting with @Ultralytics YOLO26🚀 Imagine a vision AI system that can automatically count drink cans moving toward the delivery line, all with just a few lines of Python code. I’ve built this use case using the object counting solution. The core logic remains

X (formerly Twitter)
Show threadstrickvlMar 15

That brings panlabel to 13 supported formats with full read, write, and auto-detection. Single binary, no Python dependencies.

This is the kind of project I enjoy just steadily plodding away at — ticking off one format at a time until every common object detection annotation format is covered.

https://github.com/strickvl/panlabel

#ObjectDetection #Rust #MachineLearning #ComputerVision #OpenSource

GitHub - strickvl/panlabel: Universal annotation converter

Universal annotation converter. Contribute to strickvl/panlabel development by creating an account on GitHub.

GitHub
sayzardMar 13

DGX Spark provides a lot of horsepower for really high quality detection + tracking with RF-DETR

@skalskip92 is working on something related to this right now, should be out soon

will help you see how the quality of your detector impacts the quality of tracking

https://x.com/roboflow/status/2032123926399025551

#dgx #rfdetr #objectdetection #objecttracking #deeplearning

Roboflow (@roboflow) on X

DGX Spark provides a lot of horsepower for really high quality detection + tracking with RF-DETR @skalskip92 is working on something related to this right now, should be out soon will help you see how the quality of your detector impacts the quality of tracking

X (formerly Twitter)
sayzardMar 9

merve (@mervenoyann)

Hugging Face Hub의 객체 탐지(object detection) 데이터셋을 다양한 포맷으로 변환하고 다시 Hub에 푸시할 수 있는 'UV scripts'를 배포했다고 알림. 포맷 검증, 바운딩박스 통계 표시, 스트리밍 기반 미리보기(glance) 기능을 제공하며, @strickvl의 panlabel에서 영감을 받았다고 설명함.

https://x.com/mervenoyann/status/2031016273232920880

#huggingface #dataset #objectdetection #opensource

merve (@mervenoyann) on X

shipped: UV scripts to convert a @huggingface Hub object detection datasets to different formats and push back to Hub 🔥 validate formats, show stats of bboxes, glance with streaming 🙌🏻 inspired by panlabel of @strickvl 🤝

X (formerly Twitter)
HitechDigital SolutionsMar 3

AI Image Annotation for Detection Models

Structured polygon annotation, 3D cuboids, landmark detection, and semantic segmentation designed for scalable AI training. An image annotation company delivers datasets for computer vision, medical imaging, and object detection systems.

Know More: https://www.hitechdigital.com/image-annotation-services

#ImageAnnotation #AITrainingData #ObjectDetection #MachineLearning #MedicalImagingAI #DataLabeling

sayzardMar 2

Ultralytics (@ultralytics)

Ultralytics의 YOLO26을 사용해 뇌종양 MRI 데이터셋에서 탐지 모델을 훈련하는 안내입니다. 경량 연구용 데이터셋으로 탐지 파이프라인을 테스트하고 의료 AI 워크플로를 검증하는 데 적합하다고 소개합니다.

https://x.com/ultralytics/status/2028515820683337790

#ultralytics #yolo26 #medicalai #mri #objectdetection

Ultralytics (@ultralytics) on X

Train Ultralytics YOLO26 on the brain tumor dataset! 🧠 Detect tumors in MRI images using this lightweight research dataset, ideal for testing detection pipelines and validating medical AI workflows. Start training ➡️ https://t.co/clSb7BT6YJ #Ultralytics #YOLO26 #AI #MedicalAI

X (formerly Twitter)
sayzardMar 1

Akshay (@akshay_pachaar)

Ultralytics가 발표한 YOLO26은 기존 YOLO 계열에서 사용되던 중복 박스 제거 기법(NMS)을 완전히 생략하고 단일 패스 예측으로 실시간 객체 검출을 가속화한 모델입니다. 최대 300개 검출을 지원하며 더 빠른 추론을 목표로 하고 있고, 모델 다운로드 링크가 제공됩니다. 실시간 객체 검출 성능·파이프라인에 큰 영향이 기대됩니다.

https://x.com/akshay_pachaar/status/2027673683255591252

#yolo26 #yolo #objectdetection #ultralytics #realtime

Akshay 🚀 (@akshay_pachaar) on X

Real-time object detection will never be the same. Traditional YOLO needs NMS to remove duplicate boxes; it's slow and inconsistent. YOLO26 skips it entirely: single-pass predictions, faster inference and up to 300 detections per image. Download model: https://t.co/vI1ZyYyEzM

X (formerly Twitter)