Prompt Depth Anything

DORA (Dataflow-Oriented Robotic Architecture) is middleware designed to streamline and simplify the creation of AI-based robotic applications. It offers low latency, composable, and distributed dat…

The official VOT Challenge evaluation and analysis toolkit

An easy, interface friendly cross-platform client to generate bird's view images using inverse perspective mapping methods proposed in paper "Adaptive Inverse Perspective Mapping for Lane Map Gener…

"FastSAM_Awsome_Openvino" 项目展示了如何通过 OpenVINO 框架高效部署 FastSAM 模型，实现了令人瞩目的实例分割功能。该项目提供了 C++ 版本和 Python 版本两种实现，为开发者提供了在不同语言环境下使用 FastSAM 模型的选择。

Workflow for generating synthetic data and training CV models.

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

Synthetic Data Generation Examples

Official implementation of the paper "Watermark Anything with Localized Messages"

Universal grid map library for mobile robotic mapping

[ICCV 2023] SurroundOcc: Multi-camera 3D Occupancy Prediction for Autonomous Driving

[CVPR 2022] "MonoScene: Monocular 3D Semantic Scene Completion": 3D Semantic Occupancy Prediction from a single image

[ICRA'2024] MonoOcc: Digging into Monocular Semantic Occupancy Prediction

Simple tutorial on how to apply DQN on cartpole

PCIe GEN1, GEN2 and GEN3 Scrambler, This Scrambler is able to scramble 1,2 and 4 bytes of data in 1 clock cycle in respect to the scrambling rules. Implemented in Verilog, Suitable for PIPE, Suppor…

Repository for the Inzva Deep Learning Study Group Week 6 material

Lightweight models for real-time semantic segmentation(include mobilenetv1-v3, shufflenetv1-v2, igcv3, efficientnet).

try to export sam2 to onnx.

Using OnnxRuntime to inference yolov10,yolov10+SAM ,yolov10+bytetrack and SAM2 by c++ .

Projects and application using computer vision and machine learning

Inverse perspective transform with manual vanishing point aided

Pytorch implementation of ResUnet and ResUnet ++

Gazebo simulation of dynamics environment in warehouses.

A pallet model trained with SDG optimized for NVIDIA Jetson.

TensorFlow Implementation for Computing a Semantically Segmented Bird's Eye View (BEV) Image Given the Images of Multiple Vehicle-Mounted Cameras.

OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.

C++ Kursunda verilen ödevler.

ResUNet, a semantic segmentation model inspired by the deep residual learning and UNet. An architecture that take advantages from both(Residual and UNet) models.