Object Detection
Yet another SOTA model from META, meet SAM-3. Learn about what's new and how to implement your own tracking pipeline using SAM-3.
The field of computer vision is fueled by the remarkable progress in self-supervised learning. At the forefront of this revolution is DINOv2, a cutting-edge self-supervised vision transformer developed by Meta
Real-time object detection has become essential for many practical applications, and the YOLO (You Only Look Once) series by Ultralytics has always been a state-of-the-art model series, providing a robust
This blog goes through the architecture of DETR
This article discusses how to use any finetuned yolov8 pytorch model on oak-d-lite device with OpenVINO IR Format.
YOLOv10 introduces a dual-head architecture for NMS-free training and efficiency-accuracy driven model design. It combines one-to-one and one-to-many label assignments to improve performance without extra computation. YOLOv10 uses lightweight classification
This research article discusses about how data preparation matters for Fine-tuning Faster R-CNN on aerial small object detection.
This article will help you to quickly build and showcase your own deep learning models, using Gradio and OpenCV's DNN module.
This article introduces the YOLOv9 model, which addresses the core challenges in object detection through deep learning.
In the preceding article, YOLO Loss Functions Part 1, we focused exclusively on SIoU and Focal Loss as the primary loss functions used in the YOLO series of models. In
The YOLO (You Only Look Once) series of models, renowned for its real-time object detection capabilities, owes much of its effectiveness to its specialized loss functions. In this article, we
This article has provided a brief overview of moving object detection using OpenCV. We've explored the basics of the library's capabilities like Background Subtraction and Contour Detection and explored how
