请用vscode中的 opencv库编写python代码,实现对图片中的交通灯进行颜色识别的功能。使用opencv自带的cv2.inrange,并输出识别后的图片的结果。
时间: 2024-11-03 11:13:15 浏览: 29
要在Visual Studio Code (VSCode) 中使用 OpenCV 库来识别图片中交通灯的颜色,首先需要安装必要的库和环境。以下是步骤以及简单的Python代码示例:
1. 安装所需库:
如果尚未安装`opencv-python`和`numpy`库,可以使用pip命令:
```
pip install opencv-python numpy
```
2. 导入所需的模块:
```python
import cv2
import numpy as np
```
3. 加载图像并转换为HSV色彩空间:
```python
img = cv2.imread('traffic_light.jpg') # 替换为你实际的图片路径
hsv_image = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
```
4. 确定交通信号灯的颜色范围(这里假设红绿黄三色):
```python
red_lower = np.array([0, 50, 50]) # 红色下限
red_upper = np.array([10, 255, 255]) # 红色上限
green_lower = np.array([40, 50, 50]) # 绿色下限
green_upper = np.array([70, 255, 255]) # 绿色上限
yellow_lower = np.array([20, 50, 50]) # 黄色下限
yellow_upper = np.array([40, 255, 255]) # 黄色上限
```
5. 对每个颜色区间应用`inRange`函数:
```python
mask_red = cv2.inRange(hsv_image, red_lower, red_upper)
mask_green = cv2.inRange(hsv_image, green_lower, green_upper)
mask_yellow = cv2.inRange(hsv_image, yellow_lower, yellow_upper)
# 使用位运算合并所有颜色通道的掩码
combined_mask = mask_red | mask_green | mask_yellow
```
6. 提取目标区域(这一步可以根据实际需求调整,例如通过膨胀、腐蚀等操作):
```python
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5))
dilated_mask = cv2.dilate(combined_mask, kernel)
contours, _ = cv2.findContours(dilated_mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
```
7. 绘制识别结果到原图上:
```python
for contour in contours:
x, y, w, h = cv2.boundingRect(contour)
img = cv2.rectangle(img, (x, y), (x+w, y+h), (0, 255, 0), 2)
# 获取并显示每个目标区域的颜色
roi_color = hsv_image[y:y+h, x:x+w]
color_name = "Red" if 'red' in combined_mask[y:y+h, x:x+w].shape else ("Green" if 'green' in ... else "Yellow")
cv2.putText(img, color_name, (x, y-10), cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 0, 255), 2)
```
8. 最后保存处理后的图片:
```python
output_img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) # 转换为RGB格式以便显示
cv2.imwrite("recognized_traffic_lights.jpg", output_img)
```
阅读全文