Initial commit

This commit is contained in:
llyg777
2026-02-25 14:24:05 +08:00
commit beb8c8f1e6
10 changed files with 738 additions and 0 deletions

112
README.md Normal file
View File

@ -0,0 +1,112 @@
# 木条检测与分类 Python 接口示例
本项目提供完整的 Python 示例,用于图像中木条数量检测、存在性判定以及 NG 木条异常分类。
它支持:
- 基于 RKNNLite 的木条检测
- NG/OK 木条判定
- NG 木条异常类型分类
- 简单接口调用,支持本地图片推理
---
## 目录结构
wood_detection/
├── wood_detect/
│ ├── wood_detect.py # 木条数量检测接口
│ └── wood_detect.rknn # RKNN模型文件
├── wood_exist/
│ ├── wood_exist.py # 木条存在性判定接口
│ └── wood_exist_cls.rknn # RKNN模型文件
├── wood_ng/
│ ├── wood_ng.py # NG木条异常分类接口
│ └── wood_ng_cls.rknn # RKNN模型文件
└── README.md # 说明文档
---
## 配置
### 安装依赖
```bash
pip install opencv-python numpy rknnlite
```
## 接口说明
### 1. 木条数量检测
函数detect_wood(img: np.ndarray) -> int
参数:
imgBGR格式图像 (np.ndarray)
返回值:
检测到的木条数量 (int)
示例:
#### 函数调用
```python
import cv2
from wood_detect.wood_detect import detect_wood
img = cv2.imread("1.jpg")
result = detect_wood(img)
print(f"检测到木条数量: {result}")
```
### 2. 木条存在性判定
函数classify_wood_exist(img: np.ndarray) -> int
参数:
imgBGR格式图像 (np.ndarray)
返回值:
整数结果对应木条状态int: 存在结果0 / 1
示例:
```python
import cv2
from wood_exist.wood_exist import classify_wood_exist, CLASS_NAMES
img = cv2.imread("1.png")
result = classify_wood_exist(img)
print(f"木条存在性判定: {result}")
```
### 3. NG 木条异常分类
函数classify_wood_ng(img: np.ndarray) -> int
参数:
imgBGR格式图像 (np.ndarray)
返回值:
整数结果,对应 NG木条int: NG结果0 / 1
示例:
```python
import cv2
from wood_ng.wood_ng import classify_wood_ng, CLASS_NAMES
img = cv2.imread("1.png")
result = classify_wood_ng(img)
print(f"NG 木条: {result}")
```

BIN
wood_detect/1.jpg Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 333 KiB

212
wood_detect/wood_detect.py Normal file
View File

@ -0,0 +1,212 @@
# -*- coding: utf-8 -*-
"""
木条检测模块基于RKNNLite + ROI + 单类别NMS
功能:
- 检测ROI区域内木条数量
- 输出实际木条数量
"""
import os
from typing import Optional
import cv2
import numpy as np
from rknnlite.api import RKNNLite
# =====================================================
# 常量配置
# =====================================================
RKNN_MODEL_PATH: str = "wood_detect.rknn"
ROI: tuple[int, int, int, int] = (1, 1, 1000, 1000) # ROI 坐标(x1, y1, x2, y2)
IMG_SIZE: tuple[int, int] = (640, 640) # 模型输入大小
OBJ_THRESH: float = 0.25 # 置信度阈值
NMS_THRESH: float = 0.45 # NMS阈值
CLASS_NAME: list[str] = ["bag"] # 单类别名称后续改成wood
# =====================================================
# 私有工具函数
# =====================================================
def _softmax(x: np.ndarray, axis: int = -1) -> np.ndarray:
"""计算softmax概率"""
x = x - np.max(x, axis=axis, keepdims=True)
exp_x = np.exp(x)
return exp_x / np.sum(exp_x, axis=axis, keepdims=True)
def _letterbox_resize(image: np.ndarray,
size: tuple[int, int],
bg_color: int = 114) -> tuple[np.ndarray, float, int, int]:
"""保持长宽比缩放并填充到目标尺寸"""
target_w, target_h = size
h, w = image.shape[:2]
scale = min(target_w / w, target_h / h)
new_w, new_h = int(w * scale), int(h * scale)
resized = cv2.resize(image, (new_w, new_h))
canvas = np.full((target_h, target_w, 3), bg_color, dtype=np.uint8)
dx = (target_w - new_w) // 2
dy = (target_h - new_h) // 2
canvas[dy:dy + new_h, dx:dx + new_w] = resized
return canvas, scale, dx, dy
def _nms(boxes: np.ndarray, scores: np.ndarray, thresh: float) -> list[int]:
"""非极大值抑制"""
x1, y1, x2, y2 = boxes.T
areas = (x2 - x1) * (y2 - y1)
order = scores.argsort()[::-1]
keep: list[int] = []
while order.size > 0:
i = order[0]
keep.append(i)
xx1 = np.maximum(x1[i], x1[order[1:]])
yy1 = np.maximum(y1[i], y1[order[1:]])
xx2 = np.minimum(x2[i], x2[order[1:]])
yy2 = np.minimum(y2[i], y2[order[1:]])
inter = np.maximum(0, xx2 - xx1) * np.maximum(0, yy2 - yy1)
iou = inter / (areas[i] + areas[order[1:]] - inter)
order = order[1:][iou <= thresh]
return keep
def _post_process(outputs: list[np.ndarray],
scale: float,
dx: int,
dy: int) -> Optional[np.ndarray]:
"""RKNN模型输出后处理解码坐标 + NMS返回有效boxes"""
boxes_list, scores_list = [], []
strides = [8, 16, 32]
for i, stride in enumerate(strides):
reg = outputs[i * 3 + 0][0]
cls = outputs[i * 3 + 1][0]
obj = outputs[i * 3 + 2][0]
num_classes, H, W = cls.shape
reg_max = reg.shape[0] // 4
grid_y, grid_x = np.meshgrid(np.arange(H), np.arange(W), indexing="ij")
grid_x = grid_x.astype(np.float32).ravel()
grid_y = grid_y.astype(np.float32).ravel()
cls_flat = cls.reshape(num_classes, -1).T
obj_flat = obj.ravel()
max_cls_score = np.max(cls_flat, axis=1)
scores = max_cls_score * obj_flat
valid_mask = scores >= OBJ_THRESH
if not np.any(valid_mask):
continue
valid_idx = np.where(valid_mask)[0]
scores_v = scores[valid_idx]
gx = grid_x[valid_idx]
gy = grid_y[valid_idx]
reg_valid = reg.reshape(4, reg_max, -1)[:, :, valid_idx]
reg_softmax = _softmax(reg_valid, axis=1)
acc = np.arange(reg_max, dtype=np.float32).reshape(1, -1, 1)
distance = np.sum(reg_softmax * acc, axis=1)
cx = (gx + 0.5) * stride
cy = (gy + 0.5) * stride
l, t, r, b = distance[0], distance[1], distance[2], distance[3]
x1 = cx - l * stride
y1 = cy - t * stride
x2 = cx + r * stride
y2 = cy + b * stride
boxes = np.stack([x1, y1, x2, y2], axis=1)
boxes[:, [0, 2]] = (boxes[:, [0, 2]] - dx) / scale
boxes[:, [1, 3]] = (boxes[:, [1, 3]] - dy) / scale
boxes_list.append(boxes)
scores_list.append(scores_v)
if not boxes_list:
return None
boxes_all = np.concatenate(boxes_list, axis=0)
scores_all = np.concatenate(scores_list, axis=0)
keep_idx = _nms(boxes_all, scores_all, NMS_THRESH)
return boxes_all[keep_idx]
# =====================================================
# RKNN模型全局初始化
# =====================================================
_global_rknn = RKNNLite()
_global_rknn.load_rknn(RKNN_MODEL_PATH)
_global_rknn.init_runtime()
# =====================================================
# 木条检测类
# =====================================================
class WoodDetectorRKNN:
"""基于RKNN的木条检测器"""
def __init__(self):
"""初始化木条检测器"""
self.rknn = _global_rknn
def detect(self, img_np: np.ndarray) -> int:
"""
检测木条数量
Args:
img_np (np.ndarray): 原始BGR图像
Returns:
int: 检测到的木条数量
"""
# ROI裁剪
h, w = img_np.shape[:2]
x1, y1, x2, y2 = ROI
x1 = max(0, min(x1, w - 1))
x2 = max(0, min(x2, w))
y1 = max(0, min(y1, h - 1))
y2 = max(0, min(y2, h))
roi_img = img_np[y1:y2, x1:x2]
# letterbox resize
resized_img, scale, dx, dy = _letterbox_resize(roi_img, IMG_SIZE)
# 推理
input_tensor = np.expand_dims(resized_img.astype(np.float32), axis=0)
outputs = self.rknn.inference([input_tensor])
boxes = _post_process(outputs, scale, dx, dy)
if boxes is None:
return 0
return len(boxes)
# =====================================================
# 对外统一接口
# =====================================================
_detector = WoodDetectorRKNN()
def detect_wood(img_np: np.ndarray) -> int:
"""
对外木条检测接口(返回木条数量)
Args:
img_np (np.ndarray): 原始BGR图像
Returns:
int: 检测到的木条数量
"""
return _detector.detect(img_np)
# =====================================================
# 主程序入口
# =====================================================
if __name__ == "__main__":
img_path = "1.jpg"
if not os.path.exists(img_path):
raise FileNotFoundError(f"图片不存在: {img_path}")
img = cv2.imread(img_path)
if img is None:
raise ValueError("图像加载失败")
total_count = detect_wood(img)
print(f"检测到木条数量: {total_count}")

Binary file not shown.

BIN
wood_exist/1.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 394 KiB

207
wood_exist/wood_exist.py Normal file
View File

@ -0,0 +1,207 @@
# -*- coding: utf-8 -*-
"""
ROI RKNN 图像分类模块
基于 RKNNLite 对输入图像的指定 ROI 区域进行分类,
输出类别 ID0: 异常1: 正常)。
支持:
- RKNN 模型单例加载
- ROI 裁剪与缩放
- BGR → RGB 预处理
- 主程序测试入口
"""
import os
from typing import Dict
import cv2
import numpy as np
from rknnlite.api import RKNNLite
# =====================================================
# 全局配置(常量)
# =====================================================
RKNN_MODEL_PATH: str = "wood_exist_cls.rknn"
# ROI 坐标x1, y1, x2, y2像素坐标
ROI: tuple[int, int, int, int] = (3, 0, 694, 182)
CLASS_NAMES: Dict[int, str] = {
0: "异常",
1: "正常",
}
# =====================================================
# 全局 RKNN 实例(单例)
# =====================================================
_global_rknn: RKNNLite | None = None
def _init_rknn_model(model_path: str) -> RKNNLite:
"""
初始化并返回 RKNN 模型(单例模式)。
Args:
model_path (str): RKNN 模型路径
Returns:
RKNNLite: 已初始化的 RKNNLite 实例
Raises:
FileNotFoundError: 模型文件不存在
RuntimeError: RKNN 加载或运行时初始化失败
"""
global _global_rknn
if _global_rknn is not None:
return _global_rknn
if not os.path.exists(model_path):
raise FileNotFoundError(f"RKNN 模型不存在: {model_path}")
rknn = RKNNLite(verbose=False)
ret = rknn.load_rknn(model_path)
if ret != 0:
raise RuntimeError(f"Load RKNN failed: {ret}")
ret = rknn.init_runtime(core_mask=RKNNLite.NPU_CORE_0)
if ret != 0:
raise RuntimeError(f"Init runtime failed: {ret}")
_global_rknn = rknn
print(f"[INFO] RKNN 模型加载成功: {model_path}")
return rknn
# =====================================================
# 预处理函数
# =====================================================
def _preprocess_input(img: np.ndarray) -> np.ndarray:
"""
对 ROI 图像进行模型输入预处理。
Args:
img (np.ndarray): BGR 格式图像shape=(640, 640, 3)
Returns:
np.ndarray: NHWC 格式 float32 输入张量shape=(1, 640, 640, 3)
Raises:
ValueError: 输入图像尺寸不符合要求
"""
if img.shape[:2] != (640, 640):
raise ValueError("输入图像必须是 640x640")
img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
input_tensor = np.expand_dims(img_rgb.astype(np.float32), axis=0)
return np.ascontiguousarray(input_tensor)
# =====================================================
# ROI + RKNN 分类器
# =====================================================
class ROIClassifierRKNN:
"""
基于 RKNN 的 ROI 区域分类器。
功能:
- 加载 RKNN 分类模型
- 从原始图像中裁剪 ROI
- 执行分类推理并返回类别 ID
"""
def __init__(self, model_path: str) -> None:
"""
初始化分类器。
Args:
model_path (str): RKNN 模型路径
"""
self.rknn = _init_rknn_model(model_path)
def classify(self, img_np: np.ndarray) -> int:
"""
对输入图像进行 ROI 分类。
Args:
img_np (np.ndarray): 原始 BGR 图像
Returns:
int: 分类结果0: 异常1: 正常)
Raises:
ValueError: ROI 坐标非法
"""
height, width = img_np.shape[:2]
x1, y1, x2, y2 = ROI
# -------- ROI 边界保护 --------
x1 = max(0, min(x1, width - 1))
x2 = max(0, min(x2, width))
y1 = max(0, min(y1, height - 1))
y2 = max(0, min(y2, height))
if x2 <= x1 or y2 <= y1:
raise ValueError(f"ROI 坐标无效: {(x1, y1, x2, y2)}")
# -------- 1. 裁剪 ROI --------
roi_img = img_np[y1:y2, x1:x2]
# -------- 2. resize 到 640×640 --------
roi_img = cv2.resize(roi_img, (640, 640))
# -------- 3. 预处理 --------
input_tensor = _preprocess_input(roi_img)
# -------- 4. RKNN 推理 --------
outputs = self.rknn.inference([input_tensor])
logits = outputs[0].reshape(-1).astype(float)
return int(np.argmax(logits))
# =====================================================
# 对外接口
# =====================================================
_classifier = ROIClassifierRKNN(RKNN_MODEL_PATH)
def classify_wood_exist(img_np: np.ndarray) -> int:
"""
线条是否存在图像分类接口函数。
Args:
img_np (np.ndarray): 原始 BGR 图像
Returns:
int: 分类结果0 / 1
"""
return _classifier.classify(img_np)
# =====================================================
# 测试入口
# =====================================================
if __name__ == "__main__":
img_path = "1.png"
if not os.path.exists(img_path):
raise FileNotFoundError(f"图片不存在: {img_path}")
img = cv2.imread(img_path)
if img is None:
raise ValueError("图像加载失败")
result = classify_wood_exist(img)
print(
f"NG料结果{result} "
f"({CLASS_NAMES[result]})"
)

Binary file not shown.

BIN
wood_ng/1.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 394 KiB

207
wood_ng/wood_ng.py Normal file
View File

@ -0,0 +1,207 @@
# -*- coding: utf-8 -*-
"""
ROI RKNN 图像分类模块
基于 RKNNLite 对输入图像的指定 ROI 区域进行分类,
输出类别 ID0: 异常1: 正常)。
支持:
- RKNN 模型单例加载
- ROI 裁剪与缩放
- BGR → RGB 预处理
- 主程序测试入口
"""
import os
from typing import Dict
import cv2
import numpy as np
from rknnlite.api import RKNNLite
# =====================================================
# 全局配置(常量)
# =====================================================
RKNN_MODEL_PATH: str = "wood_ng_cls.rknn"
# ROI 坐标x1, y1, x2, y2像素坐标
ROI: tuple[int, int, int, int] = (3, 0, 694, 182)
CLASS_NAMES: Dict[int, str] = {
0: "异常",
1: "正常",
}
# =====================================================
# 全局 RKNN 实例(单例)
# =====================================================
_global_rknn: RKNNLite | None = None
def _init_rknn_model(model_path: str) -> RKNNLite:
"""
初始化并返回 RKNN 模型(单例模式)。
Args:
model_path (str): RKNN 模型路径
Returns:
RKNNLite: 已初始化的 RKNNLite 实例
Raises:
FileNotFoundError: 模型文件不存在
RuntimeError: RKNN 加载或运行时初始化失败
"""
global _global_rknn
if _global_rknn is not None:
return _global_rknn
if not os.path.exists(model_path):
raise FileNotFoundError(f"RKNN 模型不存在: {model_path}")
rknn = RKNNLite(verbose=False)
ret = rknn.load_rknn(model_path)
if ret != 0:
raise RuntimeError(f"Load RKNN failed: {ret}")
ret = rknn.init_runtime(core_mask=RKNNLite.NPU_CORE_0)
if ret != 0:
raise RuntimeError(f"Init runtime failed: {ret}")
_global_rknn = rknn
print(f"[INFO] RKNN 模型加载成功: {model_path}")
return rknn
# =====================================================
# 预处理函数
# =====================================================
def _preprocess_input(img: np.ndarray) -> np.ndarray:
"""
对 ROI 图像进行模型输入预处理。
Args:
img (np.ndarray): BGR 格式图像shape=(640, 640, 3)
Returns:
np.ndarray: NHWC 格式 float32 输入张量shape=(1, 640, 640, 3)
Raises:
ValueError: 输入图像尺寸不符合要求
"""
if img.shape[:2] != (640, 640):
raise ValueError("输入图像必须是 640x640")
img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
input_tensor = np.expand_dims(img_rgb.astype(np.float32), axis=0)
return np.ascontiguousarray(input_tensor)
# =====================================================
# ROI + RKNN 分类器
# =====================================================
class ROIClassifierRKNN:
"""
基于 RKNN 的 ROI 区域分类器。
功能:
- 加载 RKNN 分类模型
- 从原始图像中裁剪 ROI
- 执行分类推理并返回类别 ID
"""
def __init__(self, model_path: str) -> None:
"""
初始化分类器。
Args:
model_path (str): RKNN 模型路径
"""
self.rknn = _init_rknn_model(model_path)
def classify(self, img_np: np.ndarray) -> int:
"""
对输入图像进行 ROI 分类。
Args:
img_np (np.ndarray): 原始 BGR 图像
Returns:
int: 分类结果0: 异常1: 正常)
Raises:
ValueError: ROI 坐标非法
"""
height, width = img_np.shape[:2]
x1, y1, x2, y2 = ROI
# -------- ROI 边界保护 --------
x1 = max(0, min(x1, width - 1))
x2 = max(0, min(x2, width))
y1 = max(0, min(y1, height - 1))
y2 = max(0, min(y2, height))
if x2 <= x1 or y2 <= y1:
raise ValueError(f"ROI 坐标无效: {(x1, y1, x2, y2)}")
# -------- 1. 裁剪 ROI --------
roi_img = img_np[y1:y2, x1:x2]
# -------- 2. resize 到 640×640 --------
roi_img = cv2.resize(roi_img, (640, 640))
# -------- 3. 预处理 --------
input_tensor = _preprocess_input(roi_img)
# -------- 4. RKNN 推理 --------
outputs = self.rknn.inference([input_tensor])
logits = outputs[0].reshape(-1).astype(float)
return int(np.argmax(logits))
# =====================================================
# 对外接口
# =====================================================
_classifier = ROIClassifierRKNN(RKNN_MODEL_PATH)
def classify_wood_ng(img_np: np.ndarray) -> int:
"""
线条是否为ng料图像分类接口函数。
Args:
img_np (np.ndarray): 原始 BGR 图像
Returns:
int: 分类结果0 / 1
"""
return _classifier.classify(img_np)
# =====================================================
# 测试入口
# =====================================================
if __name__ == "__main__":
img_path = "1.png"
if not os.path.exists(img_path):
raise FileNotFoundError(f"图片不存在: {img_path}")
img = cv2.imread(img_path)
if img is None:
raise ValueError("图像加载失败")
result = classify_wood_ng(img)
print(
f"NG料结果{result} "
f"({CLASS_NAMES[result]})"
)

BIN
wood_ng/wood_ng_cls.rknn Normal file

Binary file not shown.