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)
RubiCap може змінити навчання ШІ: новий підхід до детального опису зображень
# #AImodels #Apple #AppleAI #Computervision #Denseimagecaptioning #Gemini25Pro #GPT5 #Qwen25 #Reinforcementlearning #RubiCap
https://gizchina.net/2026/03/26/rubicap-ai-dense-image-captioning/
RubiCap може змінити навчання ШІ: новий підхід до детального опису зображень

RubiCap — це новий підхід до навчання моделей штучного інтелекту, який може суттєво покращ

GizChina.net
RubiCap може змінити навчання ШІ: новий підхід до детального опису зображень
# #AImodels #Apple #AppleAI #Computervision #Denseimagecaptioning #Gemini25Pro #GPT5 #Qwen25 #Reinforcementlearning #RubiCap
https://gizchina.net/2026/03/26/rubicap-ai-dense-image-captioning/
RubiCap може змінити навчання ШІ: новий підхід до детального опису зображень

RubiCap — це новий підхід до навчання моделей штучного інтелекту, який може суттєво покращ

GizChina.net

AA (@measure_plan)

이 프로젝트의 코드가 공개되었고, 컴퓨터 비전, three.js, 음악, 게임 등 25개 이상의 실험 예제가 함께 제공된다. 다양한 AI·웹 인터랙티브 실험을 담은 오픈소스 자료로 주목할 만하다.

https://x.com/measure_plan/status/2036912848027213884

#opensource #computervision #threejs #interactive #experiments

AA (@measure_plan) on X

code for this project is available here, along with 25+ experiments in computer vision, threejs, music, games, etc https://t.co/szuzm1c0qf

X (formerly Twitter)

AA (@measure_plan)

three.js, 글로벌 일루미네이션, MediaPipe를 결합한 컴퓨터 비전 데모가 소개되었다. 웹 기반 3D 그래픽과 실시간 비전 기술을 활용한 인터랙티브한 AI/CG 응용 사례로 보인다.

https://x.com/measure_plan/status/2036891647288520789

#threejs #mediapipe #computervision #computergraphics #webgl

AA (@measure_plan) on X

threejs + global illumination + mediapipe: https://t.co/DkRW1jjhBl

X (formerly Twitter)

SEAR, a.k.a "𝐒imple and 𝐄fficient 𝐀daptation of Visual Geometric Transformers for 𝐑GB+Thermal 3D Reconstruction", is now available on arXiv (https://arxiv.org/abs/2603.18774v1).

Multimodal 3D reconstruction—especially combining RGB and thermal data—has long been a challenge due to the difficulty of aligning these distinct modalities. Our work introduces a novel fine-tuning strategy that adapts pretrained visual geometry transformers to handle RGB+Thermal (RGB-T) inputs efficiently. The result? State-of-the-art performance in RGB-T 3D reconstruction and camera pose estimation, even with a (very) small training dataset and under extreme conditions like low light or dense smoke.

Key highlights:
• 29%+ improvement in AUC@30 over existing methods
• Small training times and negligible inference overhead compared to RGB-only models
• New dataset with RGB-T sequences across diverse conditions
• Open-source code & models will be available at GitHub soon (https://github.com/Schindler-EPFL-Lab/SEAR)

If you’re working in computer vision, robotics, or multimodal sensing, SEAR offers a practical, efficient solution for integrating thermal and RGB data—opening doors for applications in search & rescue, industrial inspection, and autonomous navigation.

#computervision #research #machinelearning #preprints #thermal #3d #ai #vggt #vision

Ultralytics (@ultralytics)

Ultralytics Live Session에서 Ultralytics Platform의 전체 워크플로우를 소개한다. 주석, 학습, 배포까지 지원하는 엔드투엔드 비전 AI 플랫폼을 직접 시연하는 내용으로, YOLO 모델 개발자에게 유용한 업데이트다.

https://x.com/ultralytics/status/2036723707561889804

#ultralytics #yolo #platform #computervision #deployment

Ultralytics (@ultralytics) on X

Don't forget to join us today for our Ultralytics Live Session! 📢 Join us for a live walkthrough of Ultralytics Platform - the ultimate end-to-end vision AI platform to annotate, train, and deploy Ultralytics YOLO models. Register now ➡️ https://t.co/IKdanKWOhY

X (formerly Twitter)

Ultralytics (@ultralytics)

Ultralytics가 v8.4.27을 공개했다. 이번 버전은 플랫폼 학습 제어 강화, COCO 변환 안전성 개선, 마스크와 좌표 정렬 품질 향상 등으로 더 안정적인 컴퓨터 비전 워크플로우를 제공한다.

https://x.com/ultralytics/status/2036798324766810182

#ultralytics #yolo #computervision #release #opensource

Ultralytics (@ultralytics) on X

Ultralytics vv8.4.27 is here 🚀 Better Platform training control, safer COCO conversion, and cleaner mask/coord alignment for more reliable workflows ✅ #Ultralytics #AI #ComputerVision https://t.co/vXQKcmcits

X (formerly Twitter)

LooperRobotics Insight 9 standalone spatial AI camera features D-Robotics RDK X5 SoC, supports ROS 2 (Crowdfunding)

https://fed.brid.gy/r/https://www.cnx-software.com/2026/03/25/looperrobotics-insight-9-standalone-spatial-ai-camera-features-d-robotics-rdk-x5-soc-supports-ros-2/

LooperRobotics Insight 9 standalone spatial AI camera features D-Robotics RDK X5 SoC, supports ROS 2 (Crowdfunding)

LooperRobotics Insight 9 is an autonomous plug-and-play spatial AI camera designed for embodied intelligence, quadruped robots, and dynamic mobile platforms. Compared to typical USB depth cameras like Intel RealSense D435i or Luxonis OAK-D, which rely on a host PC for processing, the Insight 9 integrates a D-Robotics RDK X5 octa-core Cortex-A55 processor with a 10 TOPS AI accelerator, allowing it to run Visual SLAM (V-SLAM) and depth mapping entirely on-device. The camera features a "Tri-Eye Perception Matrix," which includes an 8.4MP Sony Starvis IMX415 RGB sensor with an ultra-wide 188° field of view, and two SmartSens SG0132 global shutter sensors for stereoscopic depth. Encased in a passively cooled CNC aluminum chassis, it is also equipped with an automotive-grade Bosch BMI088 IMU capable of 24g high-G tracking, making it suitable for the heavy vibrations of legged locomotion. LooperRobotics Insight 9 specifications: SoC – D-Robotics RDK X5 octa-core Arm Cortex-A55 processor @ 1.5 GHz;

CNX Software - Embedded Systems News