Multispectral-Object-Detection

Intro

Official Code for Cross-Modality Fusion Transformer for Multispectral Object Detection.

Multispectral Object Detection with Transformer and Yolov5

Abstract

Multispectral image pairs can provide the combined information, making object detection applications more reliable and robust in the open world. To fully exploit the different modalities, we present a simple yet effective cross-modality feature fusion approach, named Cross-Modality Fusion Transformer (CFT) in this paper. Unlike prior CNNs-based works, guided by the Transformer scheme, our network learns long-range dependencies and integrates global contextual information in the feature extraction stage. More importantly, by leveraging the self attention of the Transformer, the network can naturally carry out simultaneous intra-modality and inter-modality fusion, and robustly capture the latent interactions between RGB and Thermal domains, thereby significantly improving the performance of multispectral object detection. Extensive experiments and ablation studies on multiple datasets demonstrate that our approach is effective and achieves state-of-the-art detection performance.

Demo

Night Scene

Day Scene

Overview

Citation

If you use this repo for your research, please cite our paper:

@article{fang2021cross,
  title={Cross-Modality Fusion Transformer for Multispectral Object Detection},
  author={Fang Qingyun and Han Dapeng and Wang Zhaokui},
  journal={arXiv preprint arXiv:2111.00273},
  year={2021}
}

Installation

Python>=3.6.0 is required with all requirements.txt installed including PyTorch>=1.7 (The same as yolov5 https://github.com/ultralytics/yolov5 ).

Clone the repo

git clone https://github.com/DocF/multispectral-object-detection

Install requirements

$ cd  multispectral-object-detection
$ pip install -r requirements.txt

Dataset

-[FLIR] [Google Drive] [Baidu Drive] extraction code:qwer

A new aligned version.

-[LLVIP] download

-[VEDAI] download

You need to convert all annotations to YOLOv5 format.

Refer: https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data

Run

Download the pretrained weights

yolov5 weights (pre-train)

-[yolov5s] google drive

-[yolov5m] google drive

-[yolov5l] google drive

-[yolov5x] google drive

CFT weights

-[LLVIP] google drive

-[FLIR] google drive

Change the data cfg

some example in data/multispectral/

Change the model cfg

some example in models/transformer/

note!!! we used xxxx_transfomerx3_dataset.yaml in our paper.

Train Test and Detect

train: python train.py

test: python test.py

detect: python detect_twostream.py

Results

LLVIP

Log Average Miss Rate

Miss Rate - FPPI curve

References

https://github.com/ultralytics/yolov5