13 results for “topic:rgb-images”
A tool that can convert your rgb images to nordtheme palette
We present MocapNET, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance
Code for the ICPR 2020 paper: "CURL: Neural Curve Layers for Image Enhancement"
A tool that can convert your rgb images to nordtheme palette
3D facial reconstruction, expression recognition and transfer from monocular RGB images with a deep convolutional auto-encoding neural network
A curated collection of 45 high-quality RGB image datasets for computer vision in agriculture. Features datasets for weed detection, disease identification, and crop monitoring, focusing on natural field scenes. Part of our GIL 2025 survey paper.
The code implemented in ROS projects a point cloud obtained by a Velodyne VLP16 3D-Lidar sensor on an image from an RGB camera.
CoFly-WeedDB dataset: 201 aerial RGB images for weed detection.
BaleUAVision: High-resolution UAV dataset for automated hay bale detection and counting. Includes 2,599 annotated images, flight metadata, orthomosaics, segmentation formats (COCO, YOLO, CSV, masks) and YOLOv11 benchmark.
A lightweight, educational Python tool that demonstrates how to hide secret text inside RGB images using XOR encryption and ASCII encoding. This project showcases basic steganography principles by embedding encrypted messages directly into pixel color values.
No description provided.
No description provided.
Development of exercises related to image processing such as: fast Fourier transform (FFT), convolutional filters, morphology process, among others.