206 lines
6.6 KiB
Python
206 lines
6.6 KiB
Python
import cv2
|
|
import time
|
|
import os
|
|
import numpy as np
|
|
from PIL import Image
|
|
from skimage.metrics import structural_similarity as ssim
|
|
from rknnlite.api import RKNNLite
|
|
|
|
# ================== 配置 ==================
|
|
RTSP_URL = "rtsp://admin:ailaimiye123@192.168.0.234:554/streaming/channels/101"
|
|
RKNN_MODEL = "bag3568.rknn"
|
|
OUTPUT_DIR = "camera_event_capture"
|
|
|
|
CONF_THRESHOLD = 0.5
|
|
SSIM_THRESHOLD = 0.9
|
|
|
|
END_MISS_FRAMES = 30 # 连续多少帧未检测到 → 结束采集
|
|
SAVE_EVERY_N_FRAMES = 1 # 采集中每 N 帧保存一次
|
|
SHOW_WINDOW = False
|
|
|
|
# 灰度判断参数
|
|
GRAY_LOWER = 70
|
|
GRAY_UPPER = 230
|
|
GRAY_RATIO_THRESHOLD = 0.7
|
|
|
|
IMG_SIZE = (640, 640)
|
|
OBJ_THRESH = 0.001
|
|
NMS_THRESH = 0.45
|
|
CLASS_NAME = ["bag"]
|
|
|
|
os.makedirs(OUTPUT_DIR, exist_ok=True)
|
|
|
|
# ================== 灰度判断 ==================
|
|
def is_large_gray(image):
|
|
img = np.array(image)
|
|
if img.ndim != 3 or img.shape[2] != 3:
|
|
return True
|
|
h, w, _ = img.shape
|
|
gray_mask = (
|
|
(img[:, :, 0] >= GRAY_LOWER) & (img[:, :, 0] <= GRAY_UPPER) &
|
|
(img[:, :, 1] >= GRAY_LOWER) & (img[:, :, 1] <= GRAY_UPPER) &
|
|
(img[:, :, 2] >= GRAY_LOWER) & (img[:, :, 2] <= GRAY_UPPER)
|
|
)
|
|
return gray_mask.sum() / (h * w) > GRAY_RATIO_THRESHOLD
|
|
|
|
# ================== RKNN 推理工具 ==================
|
|
def letterbox_resize(image, size, bg_color=114):
|
|
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, dy = (target_w - new_w) // 2, (target_h - new_h) // 2
|
|
canvas[dy:dy + new_h, dx:dx + new_w] = resized
|
|
return canvas, scale, dx, dy
|
|
|
|
def dfl_numpy(position):
|
|
n, c, h, w = position.shape
|
|
p_num = 4
|
|
mc = c // p_num
|
|
y = position.reshape(n, p_num, mc, h, w)
|
|
y = np.exp(y) / np.sum(np.exp(y), axis=2, keepdims=True)
|
|
acc = np.arange(mc).reshape(1,1,mc,1,1)
|
|
return np.sum(y * acc, axis=2)
|
|
|
|
def box_process(position):
|
|
grid_h, grid_w = position.shape[2:4]
|
|
col, row = np.meshgrid(np.arange(grid_w), np.arange(grid_h))
|
|
col = col.reshape(1,1,grid_h,grid_w)
|
|
row = row.reshape(1,1,grid_h,grid_w)
|
|
grid = np.concatenate((col,row), axis=1)
|
|
stride = np.array([IMG_SIZE[1]//grid_h, IMG_SIZE[0]//grid_w]).reshape(1,2,1,1)
|
|
position = dfl_numpy(position)
|
|
box_xy = grid + 0.5 - position[:,0:2,:,:]
|
|
box_xy2 = grid + 0.5 + position[:,2:4,:,:]
|
|
return np.concatenate((box_xy*stride, box_xy2*stride), axis=1)
|
|
|
|
def filter_boxes(boxes, box_confidences, box_class_probs):
|
|
boxes = boxes.reshape(-1,4)
|
|
box_confidences = box_confidences.reshape(-1)
|
|
box_class_probs = np.array(box_class_probs)
|
|
|
|
class_ids = np.argmax(box_class_probs, axis=-1)
|
|
class_scores = box_class_probs[np.arange(len(class_ids)), class_ids]
|
|
scores = box_confidences * class_scores
|
|
|
|
mask = scores >= OBJ_THRESH
|
|
return np.sum(mask) > 0 # True: 有 bag, False: 无 bag
|
|
|
|
def post_process(outputs, scale, dx, dy):
|
|
boxes_list, conf_list, class_list = [], [], []
|
|
for i in range(3):
|
|
boxes_list.append(box_process(outputs[i*3]))
|
|
conf_list.append(outputs[i*3+2])
|
|
class_list.append(outputs[i*3+1])
|
|
|
|
def flatten(x):
|
|
x = x.transpose(0,2,3,1)
|
|
return x.reshape(-1,x.shape[3])
|
|
|
|
boxes = np.concatenate([flatten(b) for b in boxes_list])
|
|
box_conf = np.concatenate([flatten(c) for c in conf_list])
|
|
class_probs = np.concatenate([flatten(c) for c in class_list])
|
|
return filter_boxes(boxes, box_conf, class_probs)
|
|
|
|
# ================== RKNN 初始化 ==================
|
|
rknn = RKNNLite()
|
|
if rknn.load_rknn(RKNN_MODEL) != 0:
|
|
raise RuntimeError("RKNN 模型加载失败")
|
|
if rknn.init_runtime(core_mask=RKNNLite.NPU_CORE_AUTO) != 0:
|
|
raise RuntimeError("RKNN Runtime 初始化失败")
|
|
print("✅ RKNN 初始化完成")
|
|
|
|
# ================== 视频流 ==================
|
|
cap = cv2.VideoCapture(RTSP_URL)
|
|
if not cap.isOpened():
|
|
raise RuntimeError("RTSP 连接失败")
|
|
print("🎥 视频流已连接")
|
|
|
|
# ================== 状态机 ==================
|
|
STATE_IDLE = 0
|
|
STATE_CAPTURING = 1
|
|
|
|
state = STATE_IDLE
|
|
miss_count = 0
|
|
save_idx = 0
|
|
session_dir = None
|
|
session_id = 0
|
|
last_gray = None
|
|
frame_count = 0
|
|
|
|
try:
|
|
while True:
|
|
ret, frame = cap.read()
|
|
if not ret:
|
|
time.sleep(0.5)
|
|
continue
|
|
|
|
frame_count += 1
|
|
|
|
if SHOW_WINDOW:
|
|
cv2.imshow("Camera", frame)
|
|
if cv2.waitKey(1) == ord('q'):
|
|
break
|
|
|
|
# ---------- 灰度过滤 ----------
|
|
pil_image = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
|
|
if is_large_gray(pil_image):
|
|
continue
|
|
|
|
# ---------- SSIM 去重 ----------
|
|
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
|
|
if last_gray is not None and state == STATE_IDLE:
|
|
sim = ssim(gray, last_gray)
|
|
if sim > SSIM_THRESHOLD:
|
|
continue
|
|
last_gray = gray.copy()
|
|
|
|
# ---------- RKNN 推理判断是否有 bag ----------
|
|
img_resized, scale, dx, dy = letterbox_resize(frame, IMG_SIZE)
|
|
input_data = np.expand_dims(img_resized, 0)
|
|
outputs = rknn.inference(inputs=[input_data])
|
|
has_bag = post_process(outputs, scale, dx, dy)
|
|
|
|
# ---------- 状态机 ----------
|
|
if state == STATE_IDLE:
|
|
if has_bag:
|
|
session_id += 1
|
|
ts = time.strftime("%Y%m%d_%H%M%S")
|
|
session_dir = os.path.join(OUTPUT_DIR, f"session_{session_id:04d}_{ts}")
|
|
os.makedirs(session_dir, exist_ok=True)
|
|
print(f"\n🚀 进入采集")
|
|
state = STATE_CAPTURING
|
|
miss_count = 0
|
|
save_idx = 0
|
|
|
|
elif state == STATE_CAPTURING:
|
|
if has_bag:
|
|
miss_count = 0
|
|
else:
|
|
miss_count += 1
|
|
|
|
if save_idx % SAVE_EVERY_N_FRAMES == 0:
|
|
ts = time.strftime("%Y%m%d_%H%M%S")
|
|
ms = int((time.time()%1)*1000)
|
|
fname = f"{save_idx:06d}_{ts}_{ms:03d}.png"
|
|
cv2.imwrite(os.path.join(session_dir, fname), frame) # 保存原图
|
|
save_idx += 1
|
|
|
|
if miss_count >= END_MISS_FRAMES:
|
|
print(f"🛑 退出采集，本次保存 {save_idx} 帧")
|
|
state = STATE_IDLE
|
|
miss_count = 0
|
|
session_dir = None
|
|
|
|
except KeyboardInterrupt:
|
|
print("\n🛑 用户退出")
|
|
|
|
finally:
|
|
cap.release()
|
|
cv2.destroyAllWindows()
|
|
rknn.release()
|
|
print("程序结束")
|
|
|