Stars
Pytorch and ncnn implementation of PPYOLOE、YOLOX、PPYOLO、PPYOLOv2、PicoDet and so on.
Pytorch implementation of "Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN"
🏁 More robust checkerboard detection, similar algorithm to libcbdetect
A tool for generating Chinese license plate dataset for plate detecting
D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement [ICLR 2025 Spotlight]
A database of all 8,291 license plates available in the U.S. (50 states + D.C.) as of July 2023.
⚡ Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+
⚡ A newly designed ultra lightweight anchor free target detection algorithm， weight only 250K parameters， reduces the time consumption by 10% compared with yolo-fastest, and the post-processing is …
⚡ Based on yolo's ultra-lightweight universal target detection algorithm, the calculation amount is only 250mflops, the ncnn model size is only 666kb, the Raspberry Pi 3b can run up to 15fps+, and …
🚀🚀🚀YOLOC is Combining different modules to build an different Object detection model.Including YOLOv3、YOLOv4、Scaled_YOLOv4、YOLOv5、YOLOv6、YOLOv7、YOLOX、YOLOR、PPYOLO、PPYOLOE
NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥
🔥🔥🔥 专注于YOLO改进模型，Support to improve backbone, neck, head, loss, IoU, NMS and other modules🚀
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
Data for automatic license plate character recognition and detection algorithms
China-Balanced-License-Plate-Recognition-Dataset-330k:A balanced dataset of 330,000 images featuring various types of Chinese license plates for recognition tasks, ideal for training and evaluating…
数学建模数码相机定位 使用opencv完成轮廓提取与椭圆拟合
FEEDS: Detection dataset designed for Integrated Detection Method of Pedestrian and Face
These datasets are used for machine-learning research
chess board corner extraction and chess board recovery "Automatic Camera and Range Sensor Calibration using a single Shot"
Weakly Supervised Extrinsics Self-Calibration of SVS
Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model