NVIDIA / NVIDIAOpticalFlowSDK
Optical Flow SDK exposes the latest hardware capability of Turing GPUs dedicated to computing the relative motion of pixels between images. The hardware uses sophisticated algorithms to yield highly accurate flow vectors, with robust frame-to-frame intensity variations and tracks the true object motion faster and more accurately.
☆60Updated 3 years ago
Alternatives and similar repositories for NVIDIAOpticalFlowSDK:
Users that are interested in NVIDIAOpticalFlowSDK are comparing it to the libraries listed below
- BriefMatch real-time GPU optical flow☆41Updated 7 years ago
- YOLOv3 Windows and Linux DLL library with CMAKE☆28Updated 5 years ago
- Connected Component Labeling.☆43Updated 4 years ago
- C++ header-only lib for extracting local patches☆15Updated 4 years ago
- The purpose of this project is to apply mediapipe to more AI chips.☆52Updated 3 years ago
- fast guided filter implementation for OpenCV☆72Updated 7 years ago
- Parallel CUDA implementation of NON maximum Suppression☆79Updated 4 years ago
- Simple and Effective Face Detector, based on Progressive Calibration Networks (PCN) which is an accurate rotation-invariant face detector…☆24Updated 4 years ago
- Final project for 15-618 : implement a GPU version of the KCF algorithm☆65Updated 7 years ago
- Real-time visual object tracking using correlations filters and deep learning☆32Updated 6 years ago
- Converts a regular video into Slow Motion video using concepts of Motion Compensated Frame Interpolation. ( C++ / OpenCV)☆19Updated 2 years ago
- ☆25Updated 3 years ago
- JF-Cut: A Parallel Graph Cut Approach for Large Scale Image and Video☆36Updated 9 years ago
- Tengine 管子是用来快速生产 demo 的辅助工具☆13Updated 3 years ago
- fast and energy-efficient computation of HOG features☆17Updated 6 years ago
- Example of using TBB parallel pipeline with OpenCV☆16Updated 7 years ago
- undergraduate work☆21Updated 8 years ago
- C++/Python library for multiple object tracking via min-cost flow algorithms☆57Updated 6 years ago
- Lightweight Mat and imread()/imwrite()/imshow()☆82Updated 9 months ago
- libnms.so for object detection, can be use in libtorch or caffe or nccn or onnx or TensorRT☆17Updated 5 years ago
- Fastest image resizer☆20Updated 5 years ago
- Dolly zoom without a zoom lens☆24Updated 5 years ago
- Using TensorRT to implement and accelerate YOLO v3. Multi-scale and NMS are included. The acceleration ratio reaches 3 compared to the o…☆43Updated 6 years ago
- TensorRT half precision inference routine on a API-based TensorRT model☆13Updated 6 years ago
- Implementation of Non-Maximum Suppression algorithm☆69Updated 3 years ago
- Multiple-Person Multi-Camera Tracker☆13Updated 8 years ago
- The aim of this project is to generate a pointcloud with motion vectors and semantic segmentation of stereoscopic image sequences. Target…☆19Updated 4 years ago
- c++ implementation of tracking algorithm staple☆21Updated 6 years ago
- Implementation of paper "Backtracking Regression Forests for Accurate Camera Relocalization"☆12Updated 7 years ago
- some test to implement cv::Mat conversion to numpy.array☆25Updated 8 years ago