MaybeShewill-CV/sky-detector

Stars
128
Rank 281,044 (Top 6 %)
Language
C++
Created over 6 years ago
Updated over 1 year ago

MaybeShewill-CV/sky-detector

MaybeShewill-CV

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Sky area detection without deep neural networks https://maybeshewill-cv.github.io/sky-detector/

Sky-Area-Detector

sky area detection without deep neural networks. A c++ implemention of the algorithm mentioned in paper "Sky Region Detection in a Single Image for Autonomous Ground Robot Navigation". A fast and robust method to extract the sky area of an image.

Installation

This implementation need opencv library. Since the project is static compiled for conveniently transplanting you need static opencv library linked to this project. If static compilation is not necessary for you feel free to modify the CMakeList to dynamic compile the project.

This software has only been tested on ubuntu 16.04(x64), opencv3.4. To install this package your compiler need to support C++11.

git clone https://github.com/MaybeShewill-CV/sky-detector.git

Build

cd ROOT_FOLDER_DIR
mkdir build
cd build
cmake ..
make -j

The project will generate a static binary file which can be used on other platform without any dynamic library. The binary file built on Ubuntu 16.04LTS was tested on CentOS 6 and worked correctly.

Usage

cd build_dir
./detect input_image_file_path output_image_file_path

结果示意图如下

Test input image with full sky

Test input image with ful sky result

Test input image with part sky

Test input image with part sky result

TODO

Accelerate the calculation process

lanenet-lane-detection

Unofficial implemention of lanenet model for real time lane detection

CRNN_Tensorflow

Convolutional Recurrent Neural Networks(CRNN) for Scene Text Recognition

attentive-gan-derainnet

Unofficial tensorflow implemention of "Attentive Generative Adversarial Network for Raindrop Removal from A Single Image (CVPR 2018) " model https://maybeshewill-cv.github.io/attentive-gan-derainnet/

bisenetv2-tensorflow

Unofficial tensorflow implementation of real-time scene image segmentation model "BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation"

Easy-Ipm-Client

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 Generation with SLAM"

nsfw-classification-tensorflow

NSFW classify model implemented with tensorflow.

MNN-LaneNet

Lane detection model for mobile device via MNN project

segment-anything-u-specify

using clip and sam to segment any instance you specify with text prompt of any instance names

DVCNN_Lane_Detection

Accurate and Robust Lane Detection based on Dual-View Convolutional Neutral Network

mortred_model_server

High Performan Ai Model Web Server. Mainly support computer vision model. Quickly establish your own ai-model server. https://github.com/MaybeShewill-CV/mortred_model_server

MaybeShewill-CV.github.io

image-classification-tensorflow

cnn models used for image classification

sfnet-tensorflow

cppn-tensorflow

Tensorflow implemention of "Compositional Pattern Producing Networks: A Novel Abstraction of Development" model"

machine-learning-package

machine learning method implemention

MaybeShewill-CV