增加说明

.gitignore

@@ -178,7 +178,7 @@ cython_debug/
 # ---> JetBrains
 # Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio, WebStorm and Rider
 # Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
-
+.idea/
 # User-specific stuff
 .idea/**/workspace.xml
 .idea/**/tasks.xml
@@ -275,7 +275,8 @@ fabric.properties
 .LSOverride
 
 # Icon must end with two \r
-Icon
+Icon
+
 
 # Thumbnails
 ._*
@@ -296,3 +297,10 @@ Network Trash Folder
 Temporary Items
 .apdisk
 
+# project files
+/whl_packages/
+runs/
+*.pt
+*.cache
+.vscode/
+*.json

README.md

@@ -1,3 +1,35 @@
 # Graduation-Project
 
-毕业设计：基于YOLO和图像融合技术的无人机检测系统及安全性研究
+毕业设计：基于YOLO和图像融合技术的无人机检测系统及安全性研究
+
+Linux 运行联邦训练
+```bash
+cd federated_learning
+```
+
+```bash
+nohup python -u yolov8_fed.py > runtime.log 2>&1 &
+```
+
+Linux 运行集中训练
+```bash
+cd yolov8
+```
+
+```bash
+nohup python -u yolov8_train.py > runtime.log 2>&1 &
+```
+
+实时监控日志文件
+```bash
+tail -f runtime.log
+```
+
+运行图像融合配准代码
+```bash
+cd image_fusion
+```
+
+```bash
+python Image_Registration_test.py
+```

dataset/train1/labels/6.txt

@@ -0,0 +1,2 @@
+0 0.5375 0.37395833333333334 0.253125 0.16458333333333333
+0 0.2890625 0.5833333333333334 0.196875 0.1125

dataset/train1/labels/7.txt

@@ -0,0 +1 @@
+0 0.36328125 0.525 0.7109375 0.8083333333333333

dataset/train1/train1.yaml

@@ -0,0 +1,4 @@
+train: ./images
+val:   ../val
+nc:    1
+names: ['uav']

dataset/train2/labels/000007.txt

@@ -0,0 +1 @@
+0 0.6934895833333333 0.6527777777777778 0.008854166666666666 0.018518518518518517

dataset/train2/labels/02.txt

@@ -0,0 +1 @@
+0 0.423698 0.593519 0.061979 0.029630

dataset/train2/train2.yaml

@@ -0,0 +1,4 @@
+train: ./images
+val:   ../val
+nc:    1
+names: ['uav']

dataset/val/labels/VS_P65.txt

@@ -0,0 +1 @@
+0 0.5109375 0.5322916666666667 0.125 0.13958333333333334

dataset/val/labels/VS_P66.txt

@@ -0,0 +1 @@
+0 0.55078125 0.296875 0.0890625 0.08958333333333333

federated_learning/GenerateTestdata.sh

@@ -0,0 +1,16 @@
+# 创建测试目录结构
+mkdir -p ./test_data/{client1,client2}/{train,val}/images
+mkdir -p ./test_data/{client1,client2}/{train,val}/labels
+
+# 生成虚拟数据（各客户端仅需2张图片）
+for client in client1 client2; do
+  for split in train val; do
+    # 创建空图片（128x128 RGB）
+    magick -size 128x128 xc:white test_data/${client}/${split}/images/img1.jpg
+    magick -size 128x128 xc:black test_data/${client}/${split}/images/img2.jpg
+
+    # 创建示例标签文件
+    echo "0 0.5 0.5 0.2 0.2" > test_data/${client}/${split}/labels/img1.txt
+    echo "1 0.3 0.3 0.4 0.4" > test_data/${client}/${split}/labels/img2.txt
+  done
+done

federated_learning/config/client1_data.yaml

@@ -0,0 +1,4 @@
+train: ../test_data/client1/train/images
+val: ../test_data/client1/val/images
+nc: 2
+names: [ 'class0', 'class1' ]

federated_learning/config/client2_data.yaml

@@ -0,0 +1,4 @@
+train: ../test_data/client2/train/images
+val: ../test_data/client2/val/images
+nc: 2
+names: [ 'class0', 'class1' ]

federated_learning/yolov8.yaml

@@ -0,0 +1,49 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# Ultralytics YOLOv8 object detection model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolov8
+# Task docs: https://docs.ultralytics.com/tasks/detect
+
+# Parameters
+nc: 1 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.33, 0.25, 1024] # YOLOv8n summary: 129 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPS
+  s: [0.33, 0.50, 1024] # YOLOv8s summary: 129 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPS
+  m: [0.67, 0.75, 768] # YOLOv8m summary: 169 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPS
+  l: [1.00, 1.00, 512] # YOLOv8l summary: 209 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPS
+  x: [1.00, 1.25, 512] # YOLOv8x summary: 209 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPS
+
+# YOLOv8.0n backbone
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
+  - [-1, 3, C2f, [128, True]]
+  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
+  - [-1, 6, C2f, [256, True]]
+  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
+  - [-1, 6, C2f, [512, True]]
+  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
+  - [-1, 3, C2f, [1024, True]]
+  - [-1, 1, SPPF, [1024, 5]] # 9
+
+# YOLOv8.0n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 3, C2f, [512]] # 12
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 3, C2f, [256]] # 15 (P3/8-small)
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 12], 1, Concat, [1]] # cat head P4
+  - [-1, 3, C2f, [512]] # 18 (P4/16-medium)
+
+  - [-1, 1, Conv, [512, 3, 2]]
+  - [[-1, 9], 1, Concat, [1]] # cat head P5
+  - [-1, 3, C2f, [1024]] # 21 (P5/32-large)
+
+  - [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)

federated_learning/yolov8_fed.py

@@ -0,0 +1,252 @@
+import glob
+import os
+from pathlib import Path
+import json
+from pydoc import cli
+from threading import local
+
+import yaml
+from ultralytics import YOLO
+import copy
+import torch
+
+
+# ------------ 新增联邦学习工具函数 ------------
+def federated_avg(global_model, client_weights):
+    """联邦平均核心算法"""
+    # 计算总样本数
+    total_samples = sum(n for _, n in client_weights)
+    if total_samples == 0:
+        raise ValueError("Total number of samples must be positive.")
+
+    # DEBUG: global_dict
+    # print(global_model)
+
+    # 获取YOLO底层PyTorch模型参数
+    global_dict = global_model.model.state_dict()
+    # 提取所有客户端的 state_dict 和对应样本数
+    state_dicts, sample_counts = zip(*client_weights)
+
+    # 克隆参数并脱离计算图
+    global_dict_copy = {
+        k: v.clone().detach().requires_grad_(False) for k, v in global_dict.items()
+    }
+
+    # 聚合可训练且存在的参数
+    for key in global_dict_copy:
+        # if global_dict_copy[key].dtype != torch.float32:
+        #     continue
+        # if any(
+        #     x in key for x in ["running_mean", "running_var", "num_batches_tracked"]
+        # ):
+        #     continue
+        # 检查所有客户端是否包含当前键
+        all_clients_have_key = all(key in sd for sd in state_dicts)
+        if all_clients_have_key:
+            # 计算每个客户端的加权张量
+            # weighted_tensors = [
+            #     client_state[key].float() * (sample_count / total_samples)
+            #     for client_state, sample_count in zip(state_dicts, sample_counts)
+            # ]
+            weighted_tensors = []
+            for client_state, sample_count in zip(state_dicts, sample_counts):
+                weight = sample_count / total_samples  # 计算权重
+                weighted_tensor = client_state[key].float() * weight  # 加权张量
+                weighted_tensors.append(weighted_tensor)
+            # 聚合加权张量并更新全局参数
+            global_dict_copy[key] = torch.stack(weighted_tensors, dim=0).sum(dim=0)
+
+        # else:
+        #     print(f"错误: 键 {key} 在部分客户端缺失，已保留全局参数")
+        # 终止训练或记录日志
+        # raise KeyError(f"键 {key} 缺失")
+
+    # 加载回YOLO模型
+    global_model.model.load_state_dict(global_dict_copy, strict=True)
+
+    # global_model.model.train()
+    # with torch.no_grad():
+    #     global_model.model.load_state_dict(global_dict_copy, strict=True)
+
+    # 定义多个关键层
+    MONITOR_KEYS = [
+        "model.0.conv.weight",
+        "model.1.conv.weight",
+        "model.3.conv.weight",
+        "model.5.conv.weight",
+        "model.7.conv.weight",
+        "model.9.cv1.conv.weight",
+        "model.12.cv1.conv.weight",
+        "model.15.cv1.conv.weight",
+        "model.18.cv1.conv.weight",
+        "model.21.cv1.conv.weight",
+        "model.22.dfl.conv.weight",
+    ]
+
+    with open("aggregation_check.txt", "a") as f:
+        f.write("\n=== 参数聚合检查 ===\n")
+    for key in MONITOR_KEYS:
+        # if key not in global_dict:
+        #     continue
+        # if not all(key in sd for sd in state_dicts):
+        #     continue
+
+        # 计算聚合后均值
+        aggregated_mean = global_dict[key].mean().item()
+
+        # 计算各客户端均值
+        client_means = [sd[key].float().mean().item() for sd in state_dicts]
+        with open("aggregation_check.txt", "a") as f:
+            f.write(f"层 '{key}' 聚合后均值: {aggregated_mean:.6f}\n")
+            f.write(f"各客户端该层均值差异: {[f'{cm:.6f}' for cm in client_means]}\n")
+            f.write(f"客户端最大差异: {max(client_means) - min(client_means):.6f}\n\n")
+
+    return global_model
+
+
+# ------------ 修改训练流程 ------------
+def federated_train(num_rounds, clients_data):
+    # ========== 初始化指标记录 ==========
+    metrics = {
+        "round": [],
+        "val_mAP": [],  # 每轮验证集mAP
+        # "train_loss": [],  # 每轮平均训练损失
+        "client_mAPs": [],  # 各客户端本地模型在验证集上的mAP
+        "communication_cost": [],  # 每轮通信开销（MB）
+    }
+    # 初始化全局模型
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    global_model = (
+        YOLO("/home/image1325/DATA/Graduation-Project/federated_learning/yolov8n.yaml")
+        .load("/home/image1325/DATA/Graduation-Project/federated_learning/yolov8n.pt")
+        .to(device)
+    )
+    global_model.model.model[-1].nc = 1  # 设置检测类别数为1
+    # global_model.model.train.ema.enabled = False
+
+    # 克隆全局模型
+    local_model = copy.deepcopy(global_model)
+
+    for _ in range(num_rounds):
+        client_weights = []
+        # 各客户端的训练损失
+        # client_losses = []
+
+        # DEBUG: 检查全局模型参数
+        # global_dict = global_model.model.state_dict()
+        # print(global_dict.keys())
+
+        # 每个客户端本地训练
+        for data_path in clients_data:
+            # 统计本地训练样本数
+            with open(data_path, "r") as f:
+                config = yaml.safe_load(f)
+            #  Resolve img_dir relative to the YAML file's location
+            yaml_dir = os.path.dirname(data_path)
+            img_dir = os.path.join(
+                yaml_dir, config.get("train", data_path)
+            )  # 从配置文件中获取图像目录
+
+            # print(f"Image directory: {img_dir}")
+            num_samples = (
+                len(glob.glob(os.path.join(img_dir, "*.jpg")))
+                + len(glob.glob(os.path.join(img_dir, "*.png")))
+                + len(glob.glob(os.path.join(img_dir, "*.jpeg")))
+            )
+            # print(f"Number of images: {num_samples}")
+
+            local_model.model.load_state_dict(
+                global_model.model.state_dict(), strict=True
+            )
+
+            # 本地训练（保持你的原有参数设置）
+            local_model.train(
+                name=f"train{_ + 1}",  # 当前轮次
+                data=data_path,
+                # model=local_model,
+                epochs=16,  # 每轮本地训练多少个epoch
+                # save_period=16,
+                imgsz=768,  # 图像大小
+                verbose=False,  # 关闭冗余输出
+                batch=-1,  # 批大小
+                workers=6,  # 工作线程数
+            )
+
+            # 记录客户端训练损失
+            # client_loss = results.results_dict['train_loss']
+            # client_losses.append(client_loss)
+
+            # 收集模型参数及样本数
+            client_weights.append((local_model.model.state_dict(), num_samples))
+
+        # 聚合参数更新全局模型
+        global_model = federated_avg(global_model, client_weights)
+
+        # DEBUG: 检查全局模型参数
+        # keys = global_model.model.state_dict().keys()
+
+        # ========== 评估全局模型 ==========
+        # 复制全局模型以避免在评估时修改参数
+        val_model = copy.deepcopy(global_model)
+        # 评估全局模型在验证集上的性能
+        with torch.no_grad():
+            val_results = val_model.val(
+                data="/mnt/DATA/uav_dataset_old/UAVdataset/fed_data.yaml",  # 指定验证集配置文件
+                imgsz=768,  # 图像大小
+                batch=16,  # 批大小
+                verbose=False,  # 关闭冗余输出
+            )
+        # 丢弃评估模型
+        del val_model
+
+        # DEBUG: 检查全局模型参数
+        # if keys != global_model.model.state_dict().keys():
+        #     print("模型参数不一致！")
+
+        val_mAP = val_results.box.map  # 获取mAP@0.5
+
+        # 计算平均训练损失
+        # avg_train_loss = sum(client_losses) / len(client_losses)
+
+        # 计算通信开销（假设传输全部模型参数）
+        model_size = sum(p.numel() * 4 for p in global_model.model.parameters()) / (
+            1024**2
+        )  # MB
+
+        # 记录到指标容器
+        metrics["round"].append(_ + 1)
+        metrics["val_mAP"].append(val_mAP)
+        # metrics['train_loss'].append(avg_train_loss)
+        metrics["communication_cost"].append(model_size)
+        # 打印当前轮次结果
+        with open("aggregation_check.txt", "a") as f:
+            f.write(f"\n[Round {_ + 1}/{num_rounds}]\n")
+            f.write(f"Validation mAP@0.5: {val_mAP:.4f}\n")
+            # f.write(f"Average Train Loss: {avg_train_loss:.4f}")
+            f.write(f"Communication Cost: {model_size:.2f} MB\n\n")
+
+    return global_model, metrics
+
+
+if __name__ == "__main__":
+    # 联邦训练配置
+    clients_config = [
+        "/mnt/DATA/uav_fed/train1/train1.yaml",  # 客户端1数据路径
+        "/mnt/DATA/uav_fed/train2/train2.yaml",  # 客户端2数据路径
+    ]
+
+    # 使用本地数据集进行测试
+    # clients_config = [
+    #     "/home/image1325/DATA/Graduation-Project/dataset/train1/train1.yaml",
+    #     "/home/image1325/DATA/Graduation-Project/dataset/train2/train2.yaml",
+    # ]
+
+    # 运行联邦训练
+    final_model, metrics = federated_train(num_rounds=10, clients_data=clients_config)
+
+    # 保存最终模型
+    final_model.save("yolov8n_federated.pt")
+    # final_model.export(format="onnx")  # 导出为ONNX格式
+
+    with open("metrics.json", "w") as f:
+        json.dump(metrics, f, indent=4)

image_fusion/Image_Registration_test.py

@@ -0,0 +1,354 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+import time
+import argparse
+
+import cv2
+import numpy as np
+
+from ultralytics import YOLO
+from skimage.metrics import structural_similarity as ssim
+
+# 添加YOLOv8模型初始化
+yolo_model = YOLO("best.pt")  # 可替换为yolov8s/m/l等
+yolo_model.to('cuda')  # 启用GPU加速
+
+
+def calculate_en(img):
+    """计算信息熵（处理灰度图）"""
+    hist = cv2.calcHist([img], [0], None, [256], [0, 256])
+    hist = hist / hist.sum()
+    return -np.sum(hist * np.log2(hist + 1e-10))
+
+
+def calculate_sf(img):
+    """计算空间频率（处理灰度图）"""
+    rf = np.sqrt(np.mean(np.square(np.diff(img, axis=0))))
+    cf = np.sqrt(np.mean(np.square(np.diff(img, axis=1))))
+    return np.sqrt(rf ** 2 + cf ** 2)
+
+
+def calculate_mi(img1, img2):
+    """计算互信息（处理灰度图）"""
+    hist_2d = np.histogram2d(img1.ravel(), img2.ravel(), 256)[0]
+    pxy = hist_2d / hist_2d.sum()
+    px = np.sum(pxy, axis=1)
+    py = np.sum(pxy, axis=0)
+    return np.sum(pxy * np.log2(pxy / (px[:, None] * py[None, :] + 1e-10) + 1e-10))
+
+
+def calculate_ssim(img1, img2):
+    """计算SSIM（处理灰度图）"""
+    return ssim(img1, img2, data_range=255)
+
+
+# 裁剪线性RGB对比度拉伸：（去掉2%百分位以下的数，去掉98%百分位以上的数，上下百分位数一般相同，并设置输出上下限）
+def truncated_linear_stretch(image, truncated_value=2, maxout=255, min_out=0):
+    """
+    :param image:
+    :param truncated_value:
+    :param maxout:
+    :param min_out:
+    :return:
+    """
+    
+    def gray_process(gray, maxout=maxout, minout=min_out):
+        truncated_down = np.percentile(gray, truncated_value)
+        truncated_up = np.percentile(gray, 100 - truncated_value)
+        gray_new = ((maxout - minout) / (truncated_up - truncated_down)) * gray
+        gray_new[gray_new < minout] = minout
+        gray_new[gray_new > maxout] = maxout
+        return np.uint8(gray_new)
+    
+    (b, g, r) = cv2.split(image)
+    b = gray_process(b)
+    g = gray_process(g)
+    r = gray_process(r)
+    result = cv2.merge((b, g, r))  # 合并每一个通道
+    return result
+
+
+# RGB图片配准函数，采用白天的可见光与红外灰度图，计算两者Surf共同特征点，之间的仿射矩阵。
+def Images_matching(img_base, img_target):
+    """
+    :param img_base:
+    :param img_target:匹配图像
+    :return: 返回仿射矩阵
+    """
+    start = time.time()
+    orb = cv2.ORB_create()
+    
+    # 对可见光图像进行对比度拉伸
+    # img_base = truncated_linear_stretch(img_base)
+    
+    img_base = cv2.cvtColor(img_base, cv2.COLOR_BGR2GRAY)
+    sift = cv2.SIFT_create()
+    # 使用sift算子计算特征点和特征点周围的特征向量
+    st1 = time.time()
+    kp1, des1 = sift.detectAndCompute(img_base, None)  # 1136    1136, 64
+    kp2, des2 = sift.detectAndCompute(img_target, None)
+    en1 = time.time()
+    
+    # print(en1 - st1, "特征提取")
+    
+    # 进行KNN特征匹配
+    # FLANN_INDEX_KDTREE = 0  # 建立FLANN匹配器的参数
+    # indexParams = dict(algorithm=FLANN_INDEX_KDTREE, trees=5)  # 配置索引，密度树的数量为5
+    # searchParams = dict(checks=50)  # 指定递归次数
+    # flann = cv2.FlannBasedMatcher(indexParams, searchParams)  # 建立匹配器
+    # matches = flann.knnMatch(des1, des2, k=2)  # 得出匹配的关键点  list: 1136
+    # FLANN_INDEX_KDTREE = 1
+    # index_params = dict(algorithm=FLANN_INDEX_KDTREE, trees=5)
+    # search_params = dict(checks=50)
+    # flann = cv2.FlannBasedMatcher(index_params, search_params)
+    # matches = flann.knnMatch(des1, des2, k=2)
+    
+    st2 = time.time()
+    matcher = cv2.BFMatcher()
+    matches = matcher.knnMatch(des1, des2, k=2)
+    de2 = time.time()
+    # print(de2 - st2, "特征匹配")
+    good = []
+    # 提取优秀的特征点
+    for m, n in matches:
+        if m.distance < 0.75 * n.distance:  # 如果第一个邻近距离比第二个邻近距离的0.7倍小，则保留
+            good.append(m)  # 134
+    src_pts = np.array([kp1[m.queryIdx].pt for m in good])  # 查询图像的特征描述子索引  # 134, 2
+    dst_pts = np.array([kp2[m.trainIdx].pt for m in good])  # 训练(模板)图像的特征描述子索引
+    if len(src_pts) <= 4:
+        print("Not enough matches are found - {}/{}".format(len(good), 4))
+        return 0, None, 0
+    else:
+        print(len(dst_pts), len(src_pts), "配准坐标点")
+        H = cv2.findHomography(dst_pts, src_pts, cv2.RANSAC, 4)  # 生成变换矩阵  H[0]: 3, 3  H[1]: 134, 1
+        end = time.time()
+        times = end - start
+        # print("配准时间", times)
+        return 1, H[0], len(dst_pts)
+
+
+def fusions(img_vl, img_inf):
+    """
+    :param img_vl: 原图像
+    :param img_inf: 红外图像
+    :return:
+    """
+    img_YUV = cv2.cvtColor(img_vl, cv2.COLOR_BGR2YUV)  # 如果输入是BGR，需转换
+    # img_YUV = cv2.cvtColor(img_vl, cv2.COLOR_RGB2YUV)
+    y, u, v = cv2.split(img_YUV)  # 分离通道,获取Y通道
+    Yf = y * 0.5 + img_inf * 0.5
+    Yf = Yf.astype(np.uint8)
+    fusion = cv2.cvtColor(cv2.merge((Yf, u, v)), cv2.COLOR_YUV2RGB)
+    return fusion
+
+
+def removeBlackBorder(gray):
+    """
+    移除缝合后的图像的多余黑边
+    输入：
+        image：三维numpy矩阵，待处理图像
+    输出：
+        裁剪后的图像
+    """
+    threshold = 40  # 阈值
+    nrow = gray.shape[0]  # 获取图片尺寸
+    ncol = gray.shape[1]
+    rowc = gray[:, int(1 / 2 * nrow)]  # 无法区分黑色区域超过一半的情况
+    colc = gray[int(1 / 2 * ncol), :]
+    rowflag = np.argwhere(rowc > threshold)
+    colflag = np.argwhere(colc > threshold)
+    left, bottom, right, top = rowflag[0, 0], colflag[-1, 0], rowflag[-1, 0], colflag[0, 0]
+    # cv2.imshow('name', gray[left:right, top:bottom])  # 效果展示
+    cv2.waitKey(1)
+    return gray[left:right, top:bottom], left, right, top, bottom
+
+
+def main(matchimg_vi, matchimg_in):
+    """
+    :param matchimg_vi: 可见光图像
+    :param matchimg_in: 红外图像
+    :return: 融合好的图像（带检测结果）
+    """
+    try:
+        orimg_vi = matchimg_vi
+        orimg_in = matchimg_in
+        h, w = orimg_vi.shape[:2]  # 480 640
+        # (3, 3)//获取对应的配准坐标点
+        flag, H, dot = Images_matching(matchimg_vi, matchimg_in)
+        if flag == 0:
+            return 0, None, 0, 0.0, 0.0, 0.0, 0.0
+        else:
+            # 配准处理
+            matched_ni = cv2.warpPerspective(orimg_in, H, (w, h))
+            matched_ni, left, right, top, bottom = removeBlackBorder(matched_ni)
+            
+            # 裁剪可见光图像
+            # fusion = fusions(orimg_vi[left:right, top:bottom], matched_ni)
+            
+            # 不裁剪可见光图像
+            fusion = fusions(orimg_vi, matched_ni)
+            
+            # 转换为灰度计算指标
+            fusion_gray = cv2.cvtColor(fusion, cv2.COLOR_RGB2GRAY)
+            cropped_vi_gray = cv2.cvtColor(orimg_vi, cv2.COLOR_BGR2GRAY)
+            matched_ni_gray = matched_ni  # 红外图已经是灰度
+            
+            # 计算指标
+            en = calculate_en(fusion_gray)
+            sf = calculate_sf(fusion_gray)
+            mi_visible = calculate_mi(fusion_gray, cropped_vi_gray)
+            mi_infrared = calculate_mi(fusion_gray, matched_ni_gray)
+            mi_total = mi_visible + mi_infrared
+            
+            # 添加SSIM容错处理
+            try:
+                ssim_visible = calculate_ssim(fusion_gray, cropped_vi_gray)
+                ssim_infrared = calculate_ssim(fusion_gray, matched_ni_gray)
+                ssim_avg = (ssim_visible + ssim_infrared) / 2
+            except Exception as ssim_error:
+                print(f"SSIM计算错误: {ssim_error}")
+                ssim_avg = -1  # 用-1表示计算失败
+            
+            # YOLOv8目标检测
+            results = yolo_model(fusion)  # 输入融合后的图像
+            annotated_image = results[0].plot()  # 绘制检测框
+            
+            # 返回带检测结果的图像
+            return 1, annotated_image, dot, en, sf, mi_total, ssim_avg
+    except Exception as e:
+        print(f"Error in fusion/detection: {e}")
+        return 0, None, 0, 0.0, 0.0, 0.0, 0.0
+
+
+def parse_args():
+    # 输入可见光和红外图像路径
+    visible_image_path = "./test/visible/visibleI0195.jpg"  # 可见光图片路径
+    infrared_image_path = "./test/infrared/infraredI0195.jpg"  # 红外图片路径
+    # 输入可见光和红外视频路径
+    visible_video_path = "./test/visible.mp4"  # 可见光视频路径
+    infrared_video_path = "./test/infrared.mp4"  # 红外视频路径
+    
+    """解析命令行参数"""
+    parser = argparse.ArgumentParser(description='图像融合与目标检测')
+    
+    parser.add_argument('--mode', type=str, choices=['video', 'image'], default='image',
+                        help='输入模式：video（视频流） 或 image（静态图片）')
+    
+    # 区分摄像头或视频文件
+    parser.add_argument('--source', type=str, choices=['camera', 'file'],
+                        help='视频输入类型：camera（摄像头）或 file（视频文件）')
+    
+    # 视频模式参数
+    parser.add_argument('--video1', type=str, default=visible_video_path,
+                        help='可见光视频路径（仅在source=file时需要）')
+    parser.add_argument('--video2', type=str, default=infrared_video_path,
+                        help='红外视频路径（仅在source=file时需要）')
+    
+    # 摄像头模式参数
+    parser.add_argument('--camera_id1', type=int, default=0,
+                        help='可见光摄像头ID（仅在source=camera时需要，默认0）')
+    parser.add_argument('--camera_id2', type=int, default=1,
+                        help='红外摄像头ID（仅在source=camera时需要，默认1）')
+    parser.add_argument('--output', type=str, default='output.mp4',
+                        help='输出视频路径（仅在video模式需要）')
+    
+    # 图片模式参数
+    parser.add_argument('--visible', type=str, default=visible_image_path,
+                        help='可见光图片路径（仅在image模式需要）')
+    parser.add_argument('--infrared', type=str, default=infrared_image_path,
+                        help='红外图片路径（仅在image模式需要）')
+    
+    return parser.parse_args()
+
+
+if __name__ == '__main__':
+    time_all = 0
+    dots = 0
+    i = 0
+    args = parse_args()
+    
+    if args.mode == 'video':
+        if args.source == 'file':
+            # ========== 视频流处理模式 ==========
+            if not args.video1 or not args.video2:
+                raise ValueError("视频模式需要指定 --video1 和 --video2 参数")
+            capture = cv2.VideoCapture(args.video2)
+            capture2 = cv2.VideoCapture(args.video1)
+        elif args.source == 'camera':
+            # ========== 摄像头处理模式 ==========
+            capture = cv2.VideoCapture(args.camera_id1)
+            capture2 = cv2.VideoCapture(args.camera_id2)
+        else:
+            raise ValueError("必须指定 --source 参数（camera 或 file）")
+        
+        # 公共视频处理逻辑
+        fps = capture.get(cv2.CAP_PROP_FPS) if args.source == 'file' else 30
+        fourcc = cv2.VideoWriter_fourcc(*'XVID')
+        out = cv2.VideoWriter(args.output, fourcc, fps, (640, 480))
+        
+        while True:
+            ret1, frame_vi = capture.read()  # 可见光帧
+            ret2, frame_ir = capture2.read()  # 红外帧
+            if not ret1 or not ret2:
+                break
+            
+            # 红外图像转灰度
+            frame_ir_gray = cv2.cvtColor(frame_ir, cv2.COLOR_BGR2GRAY)
+            
+            # 执行融合与检测
+            flag, fusion, _ = main(frame_vi, frame_ir_gray)
+            
+            if flag == 1:
+                cv2.imshow("Fusion with YOLOv8 Detection", fusion)
+                out.write(fusion)
+            
+            if cv2.waitKey(1) == ord('q'):
+                break
+        
+        # 释放资源
+        capture.release()
+        capture2.release()
+        out.release()
+        cv2.destroyAllWindows()
+    
+    elif args.mode == 'image':
+        # ========= 图片处理模式 ==========
+        if not args.infrared or not args.visible:
+            raise ValueError("图片模式需要指定 --visible 和 --infrared 参数")
+        
+        # 读取图像
+        img_visible = cv2.imread(args.visible)
+        img_infrared = cv2.imread(args.infrared)
+        
+        if img_visible is None or img_infrared is None:
+            print("Error: 图片加载失败，请检查路径！")
+            exit()
+        
+        # 转换为灰度图（红外图像处理）
+        img_inf_gray = cv2.cvtColor(img_infrared, cv2.COLOR_BGR2GRAY)
+        
+        # 执行融合与检测
+        flag, fusion_result, dot, en, sf, mi, ssim_val = main(img_visible, img_inf_gray)
+        
+        if flag == 1:
+            # 展示评价指标
+            print("\n======== 融合质量评价 ========")
+            print(f"信息熵（EN）: {en:.2f}")
+            print(f"空间频率（SF）: {sf:.2f}")
+            print(f"互信息（MI）: {mi:.2f}")
+            
+            # 条件显示SSIM
+            if ssim_val >= 0:
+                print(f"结构相似性（SSIM）: {ssim_val:.4f}")
+            else:
+                print("结构相似性（SSIM）: 计算失败（已跳过）")
+            
+            print(f"配准点数: {dot}")
+            # 显示并保存结果
+            # cv2.imshow("Fusion with Detection", fusion_result)
+            cv2.imwrite("output/fusion_result.jpg", fusion_result)
+            # cv2.waitKey(0)
+            # cv2.destroyAllWindows()
+        else:
+            print("融合失败！")

image_fusion/Img_Registration.py

@@ -0,0 +1,147 @@
+# -*- coding: utf-8 -*-
+# @Time :
+# @Author :
+import cv2
+import numpy as np
+
+sift = cv2.SIFT_create()
+
+
+def compuerSift2GetPts(img1, img2):
+    # sift 查找关键点，关键点 And 描述
+    kp1, des1 = sift.detectAndCompute(img1, None)
+    kp2, des2 = sift.detectAndCompute(img2, None)
+    
+    matcher = cv2.BFMatcher()
+    raw_matches = matcher.knnMatch(des1, des2, k=2)
+    good_matches = []
+    ratio = 0.75
+    for m1, m2 in raw_matches:
+        # 如果最接近和次接近的比值大于一个既定的值，那么我们保留这个最接近的值，认为它和其匹配的点为good_match
+        if m1.distance < ratio * m2.distance:
+            good_matches.append([m1])
+    matches = cv2.drawMatchesKnn(img1, kp1, img2, kp2, good_matches, None, flags=2)
+    ptsA = np.float32([kp1[m[0].queryIdx].pt for m in good_matches]).reshape(-1, 1, 2)
+    ptsB = np.float32([kp2[m[0].trainIdx].pt for m in good_matches]).reshape(-1, 1, 2)
+    
+    ransacReprojThreshold = 4
+    #  单应性矩阵可以将一张图通过旋转、变换等方式与另一张图对齐
+    # print(len(ptsA), len(ptsB))
+    if len(ptsA) == 0: return ptsA, ptsB, 0
+    H, status = cv2.findHomography(ptsA, ptsB, cv2.RANSAC, ransacReprojThreshold)
+    cv2.imshow("matcher", matches)
+    cv2.waitKey(100)
+    
+    return ptsA, ptsB, 1
+
+
+def findBestDistanceAndPts(ptsA, ptsB):
+    x_dct = {}
+    y_dct = {}
+    best_x, best_y = int(ptsA[0][0][0] - ptsB[0][0][0]), int(ptsA[0][0][1] - ptsB[0][0][1])
+    x_cnt, y_cnt = 0, 0
+    for i in range(len(ptsA)):
+        # print(ptsA[i], '        ', ptsB[i])
+        x_dis = int(ptsA[i][0][0] - ptsB[i][0][0])
+        y_dis = int(ptsA[i][0][1] - ptsB[i][0][1])
+        # print(x_dis)
+        if x_dis in x_dct:
+            x_dct.update({x_dis: int(x_dct.get(x_dis) + 1)})
+            if x_dct.get(x_dis) > x_cnt:
+                best_x = x_dis
+                x_cnt = x_dct.get(x_dis)
+            # print(x_dct.get(x_dis))
+        else:
+            x_dct.update({x_dis: 1})
+            # print(x_dct.get(x_dis))
+        # print(y_dis)
+        if y_dis in y_dct:
+            y_dct.update({y_dis: int(y_dct.get(y_dis) + 1)})
+            if y_dct.get(y_dis) > y_cnt:
+                best_y = y_dis
+                y_cnt = y_dct.get(y_dis)
+            # print(y_dct.get(y_dis))
+        else:
+            y_dct.update({y_dis: 1})
+            # print(y_dct.get(y_dis))
+    print(best_x, best_y)
+    
+    pt = []
+    ptb = []
+    for i in range(len(ptsA)):
+        x_dis = int(ptsA[i][0][0] - ptsB[i][0][0])
+        y_dis = int(ptsA[i][0][1] - ptsB[i][0][1])
+        if abs(best_x - x_dis) <= 0:
+            pt.append([ptsA[i][0][0], ptsA[i][0][1]])
+    # print(pt)
+    return pt, best_x, best_y
+
+
+def minDistanceHasXy(ptsA, ptsB):
+    dct = {}
+    cnt = 0
+    best = 's'
+    for i in range(len(ptsA)):
+        disx = int(ptsA[i][0][0] - ptsB[i][0][0] + 0.5)
+        disy = int(ptsA[i][0][1] - ptsB[i][0][1] + 0.5)
+        s = str(disx) + ',' + str(disy)
+        # print(s)
+        if s in dct:
+            dct.updata({s: int(dct.get(s) + 1)})
+            if dct.get(s) >= cnt:
+                cnt = dct.get(s)
+                best = s
+                print(s)
+        else:
+            dct.update({s: int(1)})
+    for i, j in dct.items():
+        print(i, j)
+    print(best)
+
+
+def detectImg(img1, img2, pta, best_x, best_y):
+    # print(pta)
+    min_x = int(min(x[0] for x in pta))
+    max_x = int(max(x[0] for x in pta))
+    min_y = int(min(x[1] for x in pta))
+    max_y = int(max(x[1] for x in pta))
+    # print(min_x, max_x)
+    # print(min_x - best_x, max_x - best_x)
+    # print(min_y, max_y)
+    # print(min_y - best_y, max_y - best_y)
+    newimg1 = img1[min_y: max_y, min_x: max_x]
+    newimg2 = img2[min_y - best_y: max_y - best_y, min_x - best_x: max_x - best_x]
+    # cv2.imshow("newimg1", newimg1)
+    # cv2.imshow("newimg2", newimg2)
+    # cv2.waitKey(0)
+    return newimg1, newimg2
+
+
+if __name__ == '__main__':
+    j = 0
+    for i in range(20, 4771, 1):
+        print(i)
+        path1 = './data/907dat/gray/camera1-' + str(i) + '.png'
+        path2 = './data/907dat/color/camera0-' + str(i) + '.png'
+        img1 = cv2.imread(path1)
+        img2 = cv2.imread(path2)
+        if (img1 is None or img2 is None): continue
+        PtsA, PtsB, f = compuerSift2GetPts(img1, img2)
+        if (f == 0): continue
+        pt, best_x, best_y = findBestDistanceAndPts(PtsA, PtsB)
+        newimg1, newimg2 = detectImg(img1, img2, pt, best_x, best_y)
+        if newimg1.shape[0] < 10 or newimg1.shape[1] < 10: continue
+        print(newimg1.shape, newimg2.shape)
+        # newimg1 = cv2.resize(newimg1, (320, 240))
+        # newimg2 = cv2.resize(newimg2, (320, 240))
+        wirtePath1 = './result/dat_result_2/gray/camera1-' + str(j) + '.png'
+        wirtePath2 = './result/dat_result_2/color/camera0-' + str(j) + '.png'
+        if newimg1.shape[0] > 255 and newimg1.shape[1] > 255 and newimg1.shape == newimg2.shape:
+            # cv2.imwrite(wirtePath1, newimg1)
+            # cv2.imwrite(wirtePath2, newimg2)
+            j += 1
+            cv2.imshow("newimg1", newimg1)
+            cv2.imshow("newimg2", newimg2)
+            cv2.waitKey()
+    print(j)
+    pass

requirements.txt

@@ -0,0 +1,41 @@
+certifi==2025.1.31
+charset-normalizer==3.4.1
+colorama==0.4.6
+contourpy==1.3.2
+cycler==0.12.1
+filelock==3.18.0
+fonttools==4.57.0
+fsspec==2025.3.2
+idna==3.10
+Jinja2==3.1.6
+kiwisolver==1.4.8
+MarkupSafe==3.0.2
+matplotlib==3.10.1
+mpmath==1.3.0
+networkx==3.4.2
+numpy==2.1.1
+opencv-python==4.11.0.86
+packaging==24.2
+pandas==2.2.3
+pillow==11.2.1
+psutil==7.0.0
+py-cpuinfo==9.0.0
+pyparsing==3.2.3
+python-dateutil==2.9.0.post0
+pytz==2025.2
+PyYAML==6.0.2
+requests==2.32.3
+scipy==1.15.2
+seaborn==0.13.2
+setuptools==78.1.0
+six==1.17.0
+sympy==1.13.1
+torch==2.6.0+cu124
+torchaudio==2.6.0+cu124
+torchvision==0.21.0+cu124
+tqdm==4.67.1
+typing_extensions==4.13.2
+tzdata==2025.2
+ultralytics==8.3.111
+ultralytics-thop==2.0.14
+urllib3==2.4.0

yolov8/yolov8.yaml

@@ -0,0 +1,6 @@
+train: /mnt/DATA/dataset/uav_dataset/train/images/
+val:   /mnt/DATA/dataset/uav_dataset/val/images/
+test:  /mnt/DATA/dataset/test2/images/
+# number of classes
+nc:    1
+names: ['uav']

yolov8/yolov8_train.py

@@ -0,0 +1,13 @@
+from ultralytics import YOLO
+
+# 加载预训练模型
+model = YOLO('../yolov8n.pt')
+
+# 开始训练
+model.train(
+    data='./yolov8.yaml',  # 数据配置文件路径
+    epochs=320,                 # 训练轮数
+    batch=-1,                  # 批量大小
+    imgsz=640,                 # 输入图片大小
+    device=0                   # 使用的设备（0 表示 GPU，'cpu' 表示 CPU）
+)