Roboflow

A Roboflow é uma plataforma de visão computacional que permite organizar bases de imagens, anotar objetos, treinar modelos e realizar deploy de inferência via API ou edge. Quero compartilhar nosso artigo publicado no blog da Roboflow, que apresenta um case real de automação da contagem de conídios com o uso de visão computacional. No artigo, mostramos como uma atividade manual, repetitiva e sujeita a variações foi transformada em um processo digital, padronizado e muito mais escalável, com o apoio do Roboflow e do Lovable para otimizar a rotina laboratorial e tornar a tomada de decisão mais ágil. Os resultados vão além da eficiência operacional. O case destaca ganhos em padronização, rastreabilidade, redução da subjetividade e liberação das equipes para atividades de maior valor agregado. Para profissionais que atuam com qualidade, laboratório, indústria, inovação, dados ou inteligência artificial aplicada aos negócios, a leitura é bastante recomendada. https://lnkd.in/dEwYBZFk

Next week, join me and Vishrut Kaushik of Peer Robotics for a live conversation about integrating computer vision with industrial robots. We'll check out their automated movement systems, how visual intelligence unlocks additional capabilities for them, and lessons learned by Vishrut's team along the way. Register here: https://luma.com/kj3h0mwv

Could you win the World Cup with one kick? Fabrizio Guccione Guccione and I will help you find out! Thank you to Roboflow and Michael Culleton for your help with Computer Vision and TouchDesigner!

Human motion tracking systems typically follow a top-down pipeline (detect → crop → estimate). In practice, especially in lab setups or tools like #freemocap and #pose2sim, this means a person detector runs independently, and the pose model operates on fixed-resolution crops. There is a licensing problem here. Since YOLOv5, Ultralytics models use AGPL-3.0. If you build proprietary commercial software (e.g., motion tracking SaaS), you must either open-source your system or purchase an enterprise license. For that reason, many open-source pipelines (#rtmlib, #sports2d, #pose2sim) still rely on YOLOX (2021), the last Apache-2.0 YOLO variant. After ~1.5 years of using YOLOX in motion tracking setups, I’ve found it poorly suited for high-quality lab tracking. It is highly sensitive to object orientation and produces significant frame-to-frame box jitter, even for nearly static subjects. That instability propagates to pose outputs. You can smooth it offline or add causal filters online, but then you introduce lag. For real-time use cases (e.g., VR animation), that trade-off is undesirable. A better alternative is now available: RF-DETR (ICLR 2026, Apache-2.0) by Roboflow. In my side-by-side comparisons against YOLOX, it is noticeably more stable in low-motion scenes, with far less bounding box wobble. It also avoids NMS, eliminating manual tuning and associated false positives. While YOLOX can be faster, detector stability often matters more for downstream pose quality than raw FPS. To make adoption easier, I built #OpenDetect: a minimal wrapper around RF-DETR (and YOLOX) using ONNX Runtime, with CUDA, TensorRT, and Apple acceleration supported out of the box. While I focus on person class for pose estimation, detection for all COCO classes is supported. Apache-2.0 license, free for commerical use. No obligation to make your code public. 🚀 GitHub: https://lnkd.in/dFwwg4e5 🤓 Docs: https://lnkd.in/d67qCQKj If your subject is mostly static and your keypoints still jitter, improve the detector first. A stable detector can clean up your entire pose pipeline without modifying the pose model. #computervision #poseestimation #opensource

Traffic flow analytics from 20-pixel objects. In this clip the vehicles are roughly 10–20 pixels wide in a 1080p frame. At that scale, small misses in detection quickly turn into broken tracks and noisy analytics. I ran RF-DETR for detection, added SAHI tiling to recover small objects, then used ByteTrack for ID consistency. The heatmap is built from aggregated trajectories over time. The interesting part was how image tiling affected downstream tracking stability/heatmap accuracy. Fewer missed detections -> fewer "broken tracks" -> traffic flow heatmap noticeably cleaner. Built inside Roboflow 's Workflows. The compute overhead is the main downside. Anyone testing higher-res models for real-time detections? #ComputerVision #ObjectDetection #MachineLearning #VideoAnalytics #DeepLearning

RF-DETR Segmentation + ByteTrack 🔥 🔥 🔥 Last week we released RF-DETR 1.4.0 with segmentation support. New state-of-the-art pre-trained checkpoints: N, S, M, L, XL, and 2XL. RF-DETR Segmentation beat the recently released YOLO26. Today we released Trackers 2.1.0 with ByteTrack support. A fast tracking-by-detection algorithm focused on stable identities under occlusion. All of this fully open-source, under Apache 2.0 license. Check out this demo combining both models. And leave a GitHub star under both projects! 🙏🏻 - RF-DETR: https://lnkd.in/dVQRpvWU - Trackers: https://lnkd.in/dy6tSiS8 Big thanks to the Roboflow models and open-source team, in particular Peter Robicheaux, Isaac Robinson and Matvei Popov who gave us RF-DETR Segmentation, Tomasz Stańczyk and Alexander Bodner who gave us ByteTrack and Jiri Borovec, who together with me pushes everything forward! Thanks also to the remaining contributors Kai Christensen, Anuj Khandelwal, Bruno Cardoso and James G, who delivered other features included in these releases. #opensource #programming #objectdetection #instancesegmentation #tracking