Stars
This is the third party implementation of the paper Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.
[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
Converting JSON of COCO dataset into XML of PASCAL VOC
Simple implementation of augmentation for small object detection
AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversaries
Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models
Crowd counting Code for IEEE Access paper "DA-Net: Learning the fine-grained density distribution with deformation aggregation network"
This project is an implementation of the crowd counting model proposed in our CVPR 2017 paper - Switching Convolutional Neural Network(SCNN) for Crowd Counting. SCNN is an adaptation of the fully-c…
Crowd Density Estimation Using - DeepLearning
a survey for CNN-based crowd counting and density estimation
Project at #sg_wonder_vision study group of the Facebook Secure and Private AI Scholarship Challenge 2019
A program, detecting water level from image based on OpenCV
Single Image Crowd Counting (CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting)
Number and the density map of crowd in a picture can be generated by the Multi-scale Convolution Neural Networks model.
Density-aware Curriculum Learning for Crowd Counting
Project to determine the position of a person / to find the density of crowd in the room using image processing.
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
Eye-to-Hand Calibration，摄像机固定，与机器人基坐标系相对位置不变。且机器人末端在固定平面移动，即只需要求一个单应性矩阵的变换关系就行。
Easy to use and accurate hand eye calibration which has been working reliably for years (2016-present) with kinect, kinectv2, rgbd cameras, optical trackers, and several robots including the ur5 an…
A cmake project for robot eye hand calibration (eye in hand and eye to hand).
A Fast and Easy to use microframework for the web.
深度学习入门教程, 优秀文章, Deep Learning Tutorial
AiLearning：数据分析+机器学习实战+线性代数+PyTorch+NLTK+TF2
深度学习面试宝典（含数学、机器学习、深度学习、计算机视觉、自然语言处理和SLAM等方向）