当前位置：首页 > article >正文

YOLO11结合传统图像增强算法 | 让你的模型无惧黑暗 | 包含端到端推理代码 | 低照度图像增强

article 2024/10/30 16:02:41

原图	YOLO11目标检测	传统图像增强 + YOLO11目标检测

一低照度图像增强

二 YOLO11

三 YOLO11结合传统图像增强算法

① 代码

② 效果图

一低照度图像增强

【低照度图像增强系列】使用SSR/MSR/MSRCR/MSRCP/automatedMSRCR算法对低照度图像进行增强处理的实践 - 点击此处即可跳转

二 YOLO11

【YOLOv11】ultralytics最新作品yolov11 AND 模型的训练、推理、验证、导出以及使用 - 点击此处即可跳转

安装 YOLO11：

# Clone the ultralytics repository
git clone https://github.com/ultralytics/ultralytics.git

# 创建conda 环境yolov11
conda create -n yolov11 python=3.9
conda activate yolov11

# Navigate to the cloned directory
cd ultralytics
# Install the package in editable mode for development
pip install -e . -i https://pypi.tuna.tsinghua.edu.cn/simple

pip install onnx -i  https://pypi.tuna.tsinghua.edu.cn/simple
pip install onnxslim -i  https://pypi.tuna.tsinghua.edu.cn/simple
pip install onnxruntime -i  https://pypi.tuna.tsinghua.edu.cn/simple

# opencv
pip install opencv-python -i  https://pypi.tuna.tsinghua.edu.cn/simple
pip install opencv-contrib-python -i  https://pypi.tuna.tsinghua.edu.cn/simple

三 YOLO11结合传统图像增强算法

YOLO11结合传统图像增强算法，让你的模型无惧黑暗。

① 代码

from ultralytics import YOLO
import cv2
import numpy as np


def singleScaleRetinex(img, sigma):
    # cv2.GaussianBlur（ SRC，ksize，sigmaX [，DST [，sigmaY [，borderType ] ] ] ） → DST
    # ksize为高斯核大小。 width、height 可以不同，但必须是正数和奇数。它们可以为零，此时会根据给定的sigma大小自动计算一个尺寸。
    # 参数sigmaX是必填参数，x方向的标准差，决定了卷积核x方向高斯分布的形状。这个sigmaX值越小，则核中心值越大，周围值下降的越快（表现为高瘦）；
    # 相反，这个值越大，则核中心值越小，周围值下降的越慢（表现为矮胖）。
    retinex = np.log10(img) - np.log10(cv2.GaussianBlur(img, (0, 0), sigma))
    return retinex


def multiScaleRetinex(img, sigma_list):
    retinex = np.zeros_like(img)
    for sigma in sigma_list:
        retinex += singleScaleRetinex(img, sigma)
    retinex = retinex / len(sigma_list)
    return retinex


def colorRestoration(img, alpha, beta):
    img_sum = np.sum(img, axis=2, keepdims=True)
    color_restoration = beta * (np.log10(alpha * img) - np.log10(img_sum))
    return color_restoration


def simplestColorBalance(img, low_clip, high_clip):
    total = img.shape[0] * img.shape[1]
    for i in range(img.shape[2]):
        # # np.unique对数据去重后从小到大排序
        unique, counts = np.unique(img[:, :, i], return_counts=True)
        current = 0
        for u, c in zip(unique, counts):
            if float(current) / total < low_clip:
                low_val = u
            if float(current) / total < high_clip:
                high_val = u
            current += c
        img[:, :, i] = np.maximum(np.minimum(img[:, :, i], high_val), low_val)
    return img


def MSRCP(img, sigma_list, low_clip, high_clip):
    img = np.float64(img) + 1.0
    intensity = np.sum(img, axis=2) / img.shape[2]
    retinex = multiScaleRetinex(intensity, sigma_list)
    intensity = np.expand_dims(intensity, 2)
    retinex = np.expand_dims(retinex, 2)
    intensity1 = simplestColorBalance(retinex, low_clip, high_clip)
    intensity1 = (intensity1 - np.min(intensity1)) / (np.max(intensity1) - np.min(intensity1)) * 255.0 + 1.0
    img_msrcp = np.zeros_like(img)
    for y in range(img_msrcp.shape[0]):
        for x in range(img_msrcp.shape[1]):
            B = np.max(img[y, x])
            A = np.minimum(256.0 / B, intensity1[y, x, 0] / intensity[y, x, 0])
            img_msrcp[y, x, 0] = A * img[y, x, 0]
            img_msrcp[y, x, 1] = A * img[y, x, 1]
            img_msrcp[y, x, 2] = A * img[y, x, 2]
    img_msrcp = np.uint8(img_msrcp - 1.0)
    return img_msrcp


def deal_img_Result(imgpath):
    # 加载图像
    im = cv2.imread(imgpath)
    MSRCP_Result = MSRCP(im, [15, 80, 100], 0.01, 0.99)
    cv2.imwrite("tmp.jpg", MSRCP_Result)
    pass


def imgEnhanceYolo(model_path, img_path):
    deal_img_Result(img_path)
    model = YOLO(model_path)  # load a custom model
    # Predict with the model
    results = model("tmp.jpg", conf=0.3)
    for result in results:
        # boxes = result.boxes  # Boxes object for bounding box outputs
        # masks = result.masks  # Masks object for segmentation masks outputs
        # keypoints = result.keypoints  # Keypoints object for pose outputs
        # probs = result.probs  # Probs object for classification outputs
        # obb = result.obb  # Oriented boxes object for OBB outputs
        result.show(line_width=1, font_size=1, color_mode='class')  # display to screen
        result.save(filename="enhance_result.jpg")  # save to disk
    pass

def Onlyyolo(model_path, img_path):
    # Load a model
    model = YOLO(model_path)  # load a custom model
    # Predict with the model
    results = model.predict(img_path, conf=0.3)
    # Process results list
    for result in results:
        result.show(line_width=1, font_size=1, color_mode='class')  # display to screen
        result.save(filename="result.jpg")  # save to disk
    pass


if __name__ == '__main__':
    Onlyyolo("yolo11s.pt", "data/difficult/test1.jpg")
    imgEnhanceYolo("yolo11s.pt", "data/difficult/test1.jpg")
    pass