# E_CEM-for-Hyperspectral-Target-Detection
Python implementation for Ensemble-Based Cascaded Constrained Energy Minimization (E-CEM) algorithm.
For more information of this project, please refer to our paper: [R Zhao, Z Shi, Z Zou, Z Zhang, Ensemble-Based Cascaded Constrained Energy Minimization for Hyperspectral Target Detection. Remote Sensing 2019.](https://www.mdpi.com/472682)
## Prerequisites
- python 3.5
- anaconda>=4.6
## Files
- [demo.py](demo.py): Shows how to run the E-CEM detector.
- [exp.py](exp.py): Reproduces the experiments in the paper.
- [e-cem.py](e-cem.py): Implementation of the E-CEM detector.
- [detector_zoo.py](detector_zoo.py): Implementation of some classical detectors.
- [utils.py](utils.py): Some useful tools.
- [hyperspectral_data](hyperspectral_data.py): Data used in our experiments.
## Usage
To run the E-CEM detector:
```
python demo.py
```
To reproduce our experiments:
```
python exp.py
```
## Citation
```
@article{zhao2019ensemble,
title={Ensemble-Based Cascaded Constrained Energy Minimization for Hyperspectral Target Detection},
author={Zhao, Rui and Shi, Zhenwei and Zou, Zhengxia and Zhang, Zhou},
journal={Remote Sensing},
volume={11},
number={11},
pages={1310},
year={2019},
publisher={Multidisciplinary Digital Publishing Institute}
}
```
## Overview
Ensemble learning is an important group of machine learning techniques that aim to enhance the nonlinearity and generalization ability of a learning system by aggregating multiple learners. We found that ensemble techniques show great potential for improving the performance of traditional hyperspectral target detection algorithms, while at present, there are few previous works have been done on this topic. To this end, we propose an Ensemble based Constrained Energy Minimization (E-CEM) detector for hyperspectral image target detection. Classical hyperspectral image target detection algorithms like Constrained Energy Minimization (CEM), matched filter (MF)
and adaptive coherence/cosine estimator (ACE) are usually designed based on constrained least square regression methods or hypothesis testing methods with Gaussian distribution assumption. However, remote sensing hyperspectral data captured in a real-world environment usually shows strong nonlinearity and non-Gaussianity, which will lead to performance degradation of these classical detection algorithms. Although some hierarchical detection models are able to learn strong nonlinear discrimination of spectral data, due to the spectrum changes, these models usually suffer from the instability in detection tasks. The proposed E-CEM is designed based on the classical CEM detection algorithm. To improve both of the detection nonlinearity and generalization ability, the strategies of “cascaded detection”, “random averaging” and “multi-scale scanning” are specifically designed. Experiments on one synthetic hyperspectral image and two real hyperspectral images demonstrate the effectiveness of our method. E-CEM outperforms the traditional CEM detector and other state-of-the-art detection algorithms.
E-CEM detector consists of two stages, (1) “multi-scale scanning” stage and (2) “cascaded detection” stage. In the first stage, the input is a spectral vector while the output is a feature vector containing multi-scale spectral information, which aims to extract the features of the spectrum and to enhance the robustness to spectrum changes. In the second stage, the input is the feature vector produced by the multi-scale scanning stage, while the output is the final detection score, where the higher the score, the more likely the current spectrum is a target. In this stage, we use a cascaded detection structure with sigmoid nonlinear transformation to enhance the nonlinear discrimination ability of the detector. Besides, we also use multiple CEM detectors in each layer to further improve
the robustness to spectral changes. Figure 1 shows an illustration of the E-CEM detector.
![overview](C:/Users/HP/Desktop/overview.png) **Figure 1.** An overview of the E-CEM detector. </div>
## Experiments
#### Detection Results on Synthetic Data
![syn_scoremaps](imgs/syn_scoremaps.png) **Figure 2.** The first band of the synthetic hyperspectral image (with noise
of 20dB SNR), ground truth location of the target and detection results. </div>
![syn_rocs](imgs/syn_rocs.png) **Figure 3.** ROC curves of different detection algorithms on our synthetic hyperspectral data (with noise
of 20dB SNR). </div>
#### Detection Results on AVIRIS San Diego Data
![sandiego_scoremaps](imgs/sandiego_scoremaps.png) **Figure 4.** The first band of the AVIRIS San Diego hyperspectral image, ground truth location of the target and detection results. </div>
![sandiego_rocs](imgs/sandiego_rocs.png) **Figure 5.** ROC curves of different detection algorithms on AVIRIS San Diego hyperspectral image. </div>
#### Detection Results on AVIRIS Cuprite Data
![cuprite_scoremaps](imgs/cuprite_scoremaps.png) **Figure 6.** The first band of the AVIRIS Cuprite hyperspectral image, ground truth location of the target and detection results. </div>
![cuprite_rocs](imgs/cuprite_rocs.png) **Figure 7.** ROC curves of different detection algorithms on AVIRIS Cuprite hyperspectral image. </div>
没有合适的资源?快使用搜索试试~ 我知道了~
温馨提示
基于Jupyter+python实现高光谱图像目标检测+源码+实验数据报告+项目说明,适合毕业设计、课程设计、项目开发。项目源码已经过严格测试,可以放心参考并在此基础上延申使用~ 基于Jupyter+python实现高光谱图像目标检测+源码+实验数据报告+项目说明,适合毕业设计、课程设计、项目开发。项目源码已经过严格测试,可以放心参考并在此基础上延申使用~ 基于Jupyter+python实现高光谱图像目标检测+源码+实验数据报告+项目说明,适合毕业设计、课程设计、项目开发。项目源码已经过严格测试,可以放心参考并在此基础上延申使用~ 基于Jupyter+python实现高光谱图像目标检测+源码+实验数据报告+项目说明,适合毕业设计、课程设计、项目开发。项目源码已经过严格测试,可以放心参考并在此基础上延申使用~
资源推荐
资源详情
资源评论
收起资源包目录
高光谱图像目标检测.zip (62个子文件)
高光谱图像目标检测
Hyperspectral-Target-Detection-based-on-Target-Spectrum-Analysis-master
高光谱遥感综述.doc 46KB
高光谱图像处理之目标检测技术(CEM算法)(图像处理).docx 305KB
overview.png 111KB
output.png 35KB
data
hyperspectral_data
san.mat 53.01MB
cup.mat 63.3MB
syn.mat 4.3MB
output_san.png 42KB
2014-12-1377.pdf 381KB
高光谱目标检测.xmind 388KB
Pic
SAN_原始算法.png 37KB
SAN——CEM.png 30KB
ecem_san.png 66KB
SAN_ROC_curve_ACE_CEM.svg 38KB
SAN_ACE.png 31KB
CUP.png 71KB
ROC_curve.jpeg 35KB
ROC_curve_SAN.png 19KB
SAN_ROC_curve_CEM_ACE.png 24KB
基于光谱信息判别的高光谱目标检测研究Hyperspectral Target Detection based on Target Spectrum Analysis.pdf 1.27MB
ROC_curve_ECEM.svg 39KB
ROC_curve.svg 32KB
SAN_Data_CEM.png 49KB
CUPROC_curve.svg 25KB
E_CEM-for-Hyperspectral-Target-Detection-master
utils.py 4KB
My___try.ipynb 33KB
My___Item1.ipynb 12KB
e_cem.py 4KB
Mycode
utils.py 3KB
main.py 2KB
e_cem.py 3KB
dectors.py 2KB
__pycache__
dectors.cpython-39.pyc 1KB
utils.cpython-39.pyc 3KB
e_cem.cpython-39.pyc 3KB
My___demo_i.ipynb 56KB
exp.py 4KB
detector_zoo.py 5KB
hyperspectral_data
san.mat 53.01MB
cup.mat 63.3MB
syn.mat 4.3MB
images
overview.png 111KB
__pycache__
utils.cpython-311.pyc 6KB
utils.cpython-39.pyc 3KB
e_cem.cpython-39.pyc 3KB
detector_zoo.cpython-39.pyc 2KB
demo.py 1KB
imgs
syn_scoremaps.png 79KB
overview.png 111KB
sandiego_rocs.png 42KB
sandiego_scoremaps.png 215KB
syn_rocs.png 25KB
cuprite_rocs.png 32KB
cuprite_scoremaps.png 372KB
README.md 5KB
output2.png 43KB
高光谱遥感图像目标检测80页PPT.ppt 8.47MB
专业基础实践报告.zip 58.21MB
~$光谱信息判别的高光谱目标检测研究Hyperspectral Target Detection based on Target Spectrum Analysis.docx 162B
cup.png 76KB
基于光谱信息判别的高光谱目标检测研究Hyperspectral Target Detection based on Target Spectrum Analysis.docx 1.07MB
README.md 130B
共 62 条
- 1
资源评论
- 2301_768073662024-04-17资源很赞,希望多一些这类资源。
梦回阑珊
- 粉丝: 3023
- 资源: 868
下载权益
C知道特权
VIP文章
课程特权
开通VIP
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功