Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions

liuwenyu

Last update: Dec 16, 2022

Related tags

Deep Learning Image-Adaptive-YOLO

Overview

Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions

Accepted by AAAI 2022 [arxiv]

Wenyu Liu, Gaofeng Ren, Runsheng Yu, Shi Guo, Jianke Zhu, Lei Zhang

Installation

git clone https://github.com/wenyyu/Image-Adaptive-YOLO.git  
cd Image-Adaptive-YOLO  
# Require python3 and tensorflow
pip install -r ./docs/requirements.txt

Datasets and Models

PSCAL VOC RTTS ExDark Voc_foggy_test & Voc_dark_test & Models (key: iayl)

Quick test

# put checkpoint model in the corresponding directory 
# change the data and model paths in core/config.py
python evaluate.py

Train and Evaluate on the datasets

Prepare the training and testing datasets, edit core/config.py to configure

python train.py # we trained our model from scratch.  
python evaluate.py   
cd mAP & python main.py

Train with your own dataset
reference the implementation tensorflow-yolov3 to prepare the files.

Acknowledgments

The code is based on tensorflow-yolov3, exposure.

Citation

@inproceedings{liu2022imageadaptive,
  title={Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions},
  author={Liu, Wenyu and Ren, Gaofeng and Yu, Runsheng and Guo, Shi and Zhu, Jianke and Zhang, Lei},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  year={2022}
}

You might also like...

Face and other object detection using OpenCV and ML Yolo

Object-and-Face-Detection-Using-Yolo- Opencv and YOLO object and face detection is implemented. You only look once (YOLO) is a state-of-the-art, real-

3 Feb 15, 2022

Real Time Object Detection and Classification using Yolo Algorithm.

Real time Object detection & Classification using YOLO algorithm. Real Time Object Detection and Classification using Yolo Algorithm. What is Object D

1 Apr 17, 2022

Real-time multi-object tracker using YOLO v5 and deep sort

This repository contains a two-stage-tracker. The detections generated by YOLOv5, a family of object detection architectures and models pretrained on the COCO dataset, are passed to a Deep Sort algorithm which tracks the objects. It can track any object that your Yolov5 model was trained to detect.

3.6k Jan 5, 2023

Object tracking using YOLO and a tracker(KCF, MOSSE, CSRT) in openCV

Object tracking using YOLO and a tracker(KCF, MOSSE, CSRT) in openCV File YOLOv3 weight can be downloaded

2 Mar 27, 2022

pytorch, hand(object) detect ,yolo v5，手检测

YOLO V5 物体检测，包括手部检测。项目介绍手部检测手部检测示例如下：视频示例：项目配置作者开发环境： Python 3.7 PyTorch = 1.5.1 数据集手部检测数据集该项目数据集采用 TV-Hand 和 COCO-Hand (COCO-Hand-Big 部分) 进

11 Dec 20, 2022

A object detecting neural network powered by the yolo architecture and leveraging the PyTorch framework and associated libraries.

Yolo-Powered-Detector A object detecting neural network powered by the yolo architecture and leveraging the PyTorch framework and associated libraries

1 Dec 3, 2021

A new data augmentation method for extreme lighting conditions.

Comments

从某个epoch开始接着往后训练

您好，请问如果我想从某个epoch开始接着往后训练的话，应该如何修改呢？（比如说，已经训练了40个epoch，但是训练停止了，然后想从第41个epoch开始接着再往后训练20个epoch。）我的想法是：修改config.py，将第40个epoch所得到的权重作为initial_weight读入，将epoch_first_stage设为0，epoch_second_stage设为20。请问这样可以吗

opened by pumpkin29 2
> 81110多张train,27340张val

81110多张train,27340张val

你的python版本和conda环境能截个图吗，我这边包有冲突，也不知道是哪里问题。

Originally posted by @XuKer in https://github.com/wenyyu/Image-Adaptive-YOLO/issues/28#issuecomment-1075799117

opened by TDlemon-1900 1
VOC peoblem

When I run this code<scripts/voc_annotation.py>. Always display this trouble Traceback (most recent call last): File"scripts/voc_annotation.py", line 51, in <module> if os.path.exists(flags.val_annotation):os.remove(flags.val_annotation). What should I do?

opened by lizhiying-2019 1
论文中的雾天图像

关于雾天图像的定义是论文中的（10），（11）公式，即

但是在代码中的定义为: self.input_data: np.power(train_data[0], lowlight_param),# train_data[0]*np.exp(lowlight_param*np.log(2)), 请问为什么这样去实现

opened by WhXl 1