forked from dsutanto/bytetrack-counter
869 lines
33 KiB
Python
869 lines
33 KiB
Python
"""
|
||
Edge production live counter — RTSP + YOLO RKNN + line crossing.
|
||
Runs on RK3588 hardware with RKNN model (320×320 input).
|
||
Replaces the Jetson/TensorRT variant.
|
||
"""
|
||
import numpy as np
|
||
import cv2
|
||
import csv
|
||
import os
|
||
import signal
|
||
import time
|
||
from datetime import datetime
|
||
from pathlib import Path
|
||
|
||
from dotenv import load_dotenv
|
||
load_dotenv()
|
||
|
||
from rknnlite.api import RKNNLite
|
||
from batch_store import BatchStore
|
||
|
||
# --- config (override via env / .env) ---
|
||
OUTPUT_DIR = os.getenv('OUTPUT_DIR', '/opt/jetson-counter')
|
||
DB_PATH = os.getenv('DB_PATH', f'{OUTPUT_DIR}/jetson_counter.db')
|
||
STATE_FILE = os.getenv('STATE_FILE', f'{OUTPUT_DIR}/current_batch.json')
|
||
SOURCE = os.getenv('SOURCE', 'rtsp://user:pass@192.168.0.100:554/stream1')
|
||
MODEL_PATH = os.getenv('MODEL_PATH', '/opt/jetson-counter/yolo11n.rknn')
|
||
CAMERA_NAME = os.getenv('CAMERA_NAME', 'CC1')
|
||
OBJECT_LABEL = os.getenv('OBJECT_LABEL', 'ayam-potong')
|
||
CLASS_AYAM = os.getenv('CLASS_AYAM', 'ayam')
|
||
CLASS_TALENAN = os.getenv('CLASS_TALENAN', 'talenan')
|
||
|
||
LINE_X = int(os.getenv('LINE_X')) if os.getenv('LINE_X') else None
|
||
LINE_X_FRAC = float(os.getenv('LINE_X_FRAC', '0.5'))
|
||
CROSS_DIRECTION = os.getenv('CROSS_DIRECTION', 'rtl').lower()
|
||
|
||
IMGSZ = int(os.getenv('IMGSZ', '320'))
|
||
HALF = os.getenv('HALF', 'false').lower() == 'true'
|
||
CONF = float(os.getenv('CONF', '0.3'))
|
||
DEVICE = int(os.getenv('DEVICE', '0'))
|
||
|
||
# RKNN-specific — core mask for NPU
|
||
# 1 = core0, 2 = core1, 3 = core0+core1 (dual), 7 = all three
|
||
CORE_MASK = int(os.getenv('CORE_MASK', '1'))
|
||
|
||
# YOLO decoder config
|
||
NUM_CLASSES = int(os.getenv('NUM_CLASSES', '2'))
|
||
SCORE_SIGMOID = os.getenv('SCORE_SIGMOID', 'false').lower() == 'true'
|
||
|
||
DAILY_CUTOFF_TIME = os.getenv('DAILY_CUTOFF_TIME', '20:00')
|
||
BATCH_TIMEOUT_SECONDS = float(os.getenv('BATCH_TIMEOUT_SECONDS', '300'))
|
||
IGNORE_BATCH_LABEL_TIMEOUT = float(os.getenv('IGNORE_BATCH_LABEL_TIMEOUT_SECONDS', '30'))
|
||
MIN_OBJECT_PER_BATCH = int(os.getenv('MIN_OBJECT_PER_BATCH', '60'))
|
||
MIN_DURATION_PER_BATCH = int(os.getenv('MIN_DURATION_PER_BATCH', '60'))
|
||
|
||
EXPORT_CSV = os.getenv('EXPORT_CSV', 'true').lower() == 'true'
|
||
CROSS_CSV = os.getenv('CROSS_CSV', f'{OUTPUT_DIR}/batch_crossings.csv')
|
||
|
||
WARMUP_FRAMES = int(os.getenv('WARMUP_FRAMES', '30'))
|
||
RECONNECT_DELAY_SEC = int(os.getenv('RECONNECT_DELAY_SEC', '3'))
|
||
MAX_RECONNECT_ATTEMPTS = int(os.getenv('MAX_RECONNECT_ATTEMPTS', '0'))
|
||
FLUSH_EVERY_N_FRAMES = int(os.getenv('FLUSH_EVERY_N_FRAMES', '100'))
|
||
TRACKED_PRUNE_SEC = int(os.getenv('TRACKED_PRUNE_SEC', '300'))
|
||
RECORD_VIDEO = os.getenv('RECORD_VIDEO', 'false').lower() == 'true'
|
||
VIDEO_SEGMENT_SEC = int(os.getenv('VIDEO_SEGMENT_SEC', '3600'))
|
||
OUTPUT_FPS = int(os.getenv('OUTPUT_FPS', '15'))
|
||
|
||
LIVE_STREAM_ENABLED = os.getenv('LIVE_STREAM_ENABLED', 'false').lower() == 'true'
|
||
LIVE_STREAM_FRAME_PATH = os.getenv('LIVE_STREAM_FRAME_PATH', '/dev/shm/jetson-counter/live_frame.jpg')
|
||
LIVE_STREAM_QUALITY = int(os.getenv('LIVE_STREAM_QUALITY', '75'))
|
||
LIVE_STREAM_EVERY_N = int(os.getenv('LIVE_STREAM_EVERY_N', '2'))
|
||
|
||
RTSP_FFMPEG_OPTIONS = os.getenv(
|
||
'OPENCV_FFMPEG_CAPTURE_OPTIONS',
|
||
'rtsp_transport;tcp|fflags;nobuffer|flags;low_delay',
|
||
)
|
||
|
||
IS_LIVE = SOURCE.lower().startswith(('rtsp://', 'http://'))
|
||
|
||
CROSS_FLASH_FRAMES = 12
|
||
POPUP_LIFETIME = 20
|
||
LINE_PULSE_FRAMES = 12
|
||
COUNT_PULSE_FRAMES = 15
|
||
BATCH_PULSE_FRAMES = 20
|
||
|
||
SKELETON = [(0, 1), (4, 3), (1, 2), (3, 2), (2, 6), (2, 5), (2, 7), (7, 8)]
|
||
SK_COLORS = [
|
||
(0, 255, 255), (0, 255, 255), (255, 0, 255), (255, 0, 255),
|
||
(0, 255, 0), (255, 255, 0), (0, 0, 255), (200, 200, 0),
|
||
]
|
||
|
||
C_PANEL = (28, 24, 18)
|
||
C_BORDER = (90, 85, 75)
|
||
C_ACCENT = (255, 200, 60)
|
||
C_GREEN = (80, 220, 100)
|
||
C_TEXT = (235, 235, 235)
|
||
C_MUTED = (150, 150, 150)
|
||
C_AYAM_BOX = (0, 165, 255)
|
||
C_TALENAN_BOX = (220, 120, 60)
|
||
C_LINE_CORE = (180, 220, 255)
|
||
C_LINE_GLOW = (100, 160, 220)
|
||
|
||
shutdown_requested = False
|
||
|
||
|
||
def request_shutdown(signum, frame):
|
||
global shutdown_requested
|
||
shutdown_requested = True
|
||
print('\nShutdown requested — finishing current frame...')
|
||
|
||
|
||
signal.signal(signal.SIGINT, request_shutdown)
|
||
signal.signal(signal.SIGTERM, request_shutdown)
|
||
|
||
|
||
# =============================================================================
|
||
# YOLO output decoder (NMS only — boxes are pre-decoded by the model)
|
||
# =============================================================================
|
||
|
||
def _nms(boxes, scores, iou_thr=0.45):
|
||
order = np.argsort(scores)[::-1]
|
||
keep = []
|
||
while len(order) > 0:
|
||
idx = order[0]
|
||
keep.append(idx)
|
||
if len(order) == 1:
|
||
break
|
||
xx1 = np.maximum(boxes[idx, 0], boxes[order[1:], 0])
|
||
yy1 = np.maximum(boxes[idx, 1], boxes[order[1:], 1])
|
||
xx2 = np.minimum(boxes[idx, 2], boxes[order[1:], 2])
|
||
yy2 = np.minimum(boxes[idx, 3], boxes[order[1:], 3])
|
||
w = np.maximum(0.0, xx2 - xx1)
|
||
h = np.maximum(0.0, yy2 - yy1)
|
||
inter = w * h
|
||
area_i = (boxes[idx, 2] - boxes[idx, 0]) * (boxes[idx, 3] - boxes[idx, 1])
|
||
area_o = (boxes[order[1:], 2] - boxes[order[1:], 0]) * (boxes[order[1:], 3] - boxes[order[1:], 1])
|
||
iou = inter / (area_i + area_o - inter + 1e-16)
|
||
order = order[1:][iou < iou_thr]
|
||
return np.array(keep)
|
||
|
||
|
||
def _compute_iou(box1, boxes2):
|
||
"""IoU of one box (cxcywh) against a set (2D) or single box (1D)."""
|
||
if boxes2.ndim == 1:
|
||
boxes2 = boxes2.reshape(1, -1)
|
||
cx, cy, w, h = box1
|
||
x1, y1 = cx - w / 2, cy - h / 2
|
||
x2, y2 = cx + w / 2, cy + h / 2
|
||
area1 = w * h
|
||
|
||
cxs, cys, ws, hs = boxes2[:, 0], boxes2[:, 1], boxes2[:, 2], boxes2[:, 3]
|
||
x1s, y1s = cxs - ws / 2, cys - hs / 2
|
||
x2s, y2s = cxs + ws / 2, cys + hs / 2
|
||
areas2 = ws * hs
|
||
|
||
xx1 = np.maximum(x1, x1s)
|
||
yy1 = np.maximum(y1, y1s)
|
||
xx2 = np.minimum(x2, x2s)
|
||
yy2 = np.minimum(y2, y2s)
|
||
inter = np.maximum(0.0, xx2 - xx1) * np.maximum(0.0, yy2 - yy1)
|
||
return inter / (area1 + areas2 - inter + 1e-16)
|
||
|
||
|
||
# =============================================================================
|
||
# Simple IoU tracker (replaces bytetrack — same persist behaviour)
|
||
# =============================================================================
|
||
|
||
class SimpleTracker:
|
||
def __init__(self, max_age=30, min_hits=1, iou_threshold=0.3):
|
||
self.max_age = max_age
|
||
self.min_hits = min_hits
|
||
self.iou_threshold = iou_threshold
|
||
self.tracks = {} # track_id -> {box, cx, age, hits, time_since_update}
|
||
self.next_id = 1
|
||
|
||
def update(self, detections):
|
||
"""detections: list of (cx, box_cxcywh). Returns (track_map, det_to_track)."""
|
||
now = time.monotonic()
|
||
|
||
for tid in self.tracks:
|
||
self.tracks[tid]['time_since_update'] += 1
|
||
|
||
matched_det = set()
|
||
matched_track = set()
|
||
assignments = [] # (track_id, det_idx)
|
||
det_to_track = {} # det_idx → track_id
|
||
|
||
if detections and self.tracks:
|
||
track_ids = list(self.tracks.keys())
|
||
track_boxes = np.stack([self.tracks[t]['box'] for t in track_ids], axis=0)
|
||
|
||
for di, det in enumerate(detections):
|
||
_, det_box = det
|
||
ious = np.array([_compute_iou(det_box, track_boxes[t:t + 1]) for t in range(len(track_ids))])
|
||
best_j = int(np.argmax(ious))
|
||
if ious[best_j] >= self.iou_threshold and track_ids[best_j] not in matched_track:
|
||
assignments.append((track_ids[best_j], di))
|
||
matched_track.add(track_ids[best_j])
|
||
matched_det.add(di)
|
||
|
||
for tid, di in assignments:
|
||
cx, box = detections[di]
|
||
self.tracks[tid]['cx'] = cx
|
||
self.tracks[tid]['box'] = box
|
||
self.tracks[tid]['hits'] += 1
|
||
self.tracks[tid]['time_since_update'] = 0
|
||
self.tracks[tid]['last_update'] = now
|
||
det_to_track[di] = tid
|
||
|
||
for di, det in enumerate(detections):
|
||
if di not in matched_det:
|
||
cx, box = det
|
||
new_id = self.next_id
|
||
self.next_id += 1
|
||
self.tracks[new_id] = {
|
||
'cx': cx, 'box': box, 'hits': 1,
|
||
'time_since_update': 0, 'last_update': now,
|
||
}
|
||
det_to_track[di] = new_id
|
||
|
||
stale = [tid for tid, t in self.tracks.items()
|
||
if t['time_since_update'] > self.max_age]
|
||
for tid in stale:
|
||
del self.tracks[tid]
|
||
|
||
track_map = {tid: self.tracks[tid]['cx']
|
||
for tid in self.tracks
|
||
if self.tracks[tid]['hits'] >= self.min_hits}
|
||
return track_map, det_to_track
|
||
|
||
|
||
# =============================================================================
|
||
# RKNN YOLO wrapper (detect output format: (1, 4+num_classes, N))
|
||
# =============================================================================
|
||
|
||
class RKNNYOLO:
|
||
def __init__(self, model_path, core_mask=1, imgsz=320, conf=0.3, iou=0.45,
|
||
num_classes=2, num_keypoints=0, score_sigmoid=False):
|
||
self.imgsz = imgsz
|
||
self.conf = conf
|
||
self.iou = iou
|
||
self.num_classes = num_classes
|
||
self.num_keypoints = num_keypoints
|
||
self.score_sigmoid = score_sigmoid
|
||
|
||
self.rknn = RKNNLite(verbose=False)
|
||
ret = self.rknn.load_rknn(model_path)
|
||
if ret != 0:
|
||
raise RuntimeError(f'Failed to load RKNN model: {model_path}')
|
||
ret = self.rknn.init_runtime(core_mask=core_mask)
|
||
if ret != 0:
|
||
raise RuntimeError(f'Failed to init RKNN runtime (core_mask={core_mask})')
|
||
|
||
try:
|
||
from rknnlite.api import RKNNLite as _RK
|
||
sdk_ver = self.rknn.get_sdk_version()
|
||
print(f'RKNN SDK version: {sdk_ver}')
|
||
except Exception:
|
||
pass
|
||
|
||
print(f'RKNN model loaded: {model_path} imgsz={imgsz} core_mask={core_mask}')
|
||
|
||
def _preprocess(self, frame):
|
||
"""Letterbox-resize to imgsz×imgsz, maintain aspect ratio, BGR→RGB, normalize."""
|
||
h0, w0 = frame.shape[:2]
|
||
scale = min(self.imgsz / h0, self.imgsz / w0)
|
||
nh, nw = int(h0 * scale), int(w0 * scale)
|
||
resized = cv2.resize(frame, (nw, nh), interpolation=cv2.INTER_LINEAR)
|
||
|
||
letterbox = np.full((self.imgsz, self.imgsz, 3), 114, dtype=np.uint8)
|
||
dy = (self.imgsz - nh) // 2
|
||
dx = (self.imgsz - nw) // 2
|
||
letterbox[dy:dy + nh, dx:dx + nw] = resized
|
||
|
||
rgb = cv2.cvtColor(letterbox, cv2.COLOR_BGR2RGB)
|
||
gains = np.array([scale, scale, dy, dx], dtype=np.float32)
|
||
return rgb, gains
|
||
|
||
def __call__(self, frame):
|
||
"""Run inference on BGR frame. Returns list of detection dicts."""
|
||
h0, w0 = frame.shape[:2]
|
||
rgb, gains = self._preprocess(frame)
|
||
scale, _, pad_y, pad_x = gains
|
||
|
||
inp = np.expand_dims(rgb, axis=0)
|
||
inp = np.ascontiguousarray(inp.astype(np.uint8))
|
||
|
||
outputs = self.rknn.inference(inputs=[inp])
|
||
|
||
if len(outputs) == 0:
|
||
return []
|
||
|
||
out = outputs[0] # (1, 4+num_classes, N) or (1, N, 4+num_classes)
|
||
out = np.squeeze(out, axis=0) # (C, N) or (N, C)
|
||
|
||
if out.shape[0] == self.num_classes + 4:
|
||
out = out.T # (C, N) → (N, C)
|
||
|
||
boxes_cxcywh = out[:, :4].copy() # cx, cy, w, h at model resolution
|
||
cls_raw = out[:, 4:].copy()
|
||
|
||
if self.score_sigmoid:
|
||
cls_scores = 1.0 / (1.0 + np.exp(-np.clip(cls_raw, -10, 10)))
|
||
else:
|
||
cls_scores = cls_raw
|
||
|
||
boxes_xyxy = np.stack([
|
||
boxes_cxcywh[:, 0] - boxes_cxcywh[:, 2] / 2,
|
||
boxes_cxcywh[:, 1] - boxes_cxcywh[:, 3] / 2,
|
||
boxes_cxcywh[:, 0] + boxes_cxcywh[:, 2] / 2,
|
||
boxes_cxcywh[:, 1] + boxes_cxcywh[:, 3] / 2,
|
||
], axis=1)
|
||
|
||
max_scores = cls_scores.max(axis=1)
|
||
class_ids = cls_scores.argmax(axis=1)
|
||
mask = max_scores > self.conf
|
||
|
||
if mask.sum() == 0:
|
||
return []
|
||
|
||
bboxes = boxes_xyxy[mask].astype(np.float32)
|
||
scores = max_scores[mask].astype(np.float32)
|
||
clses = class_ids[mask]
|
||
|
||
bboxes[:, 0] = (bboxes[:, 0] - pad_x) / scale
|
||
bboxes[:, 1] = (bboxes[:, 1] - pad_y) / scale
|
||
bboxes[:, 2] = (bboxes[:, 2] - pad_x) / scale
|
||
bboxes[:, 3] = (bboxes[:, 3] - pad_y) / scale
|
||
|
||
bboxes[:, 0] = np.clip(bboxes[:, 0], 0, w0)
|
||
bboxes[:, 1] = np.clip(bboxes[:, 1], 0, h0)
|
||
bboxes[:, 2] = np.clip(bboxes[:, 2], 0, w0)
|
||
bboxes[:, 3] = np.clip(bboxes[:, 3], 0, h0)
|
||
|
||
detections = []
|
||
for cls_id in range(self.num_classes):
|
||
idx = np.where(clses == cls_id)[0]
|
||
if len(idx) == 0:
|
||
continue
|
||
keep = _nms(bboxes[idx], scores[idx], iou_thr=self.iou)
|
||
for k in keep:
|
||
j = idx[k]
|
||
detections.append({
|
||
'bbox': bboxes[j].tolist(),
|
||
'score': float(scores[j]),
|
||
'cls': int(clses[j]),
|
||
'keypoints': None,
|
||
})
|
||
return detections
|
||
|
||
def release(self):
|
||
self.rknn.release()
|
||
|
||
|
||
# =============================================================================
|
||
# Drawing helpers (unchanged from original)
|
||
# =============================================================================
|
||
|
||
|
||
def resolve_line_x(frame_width):
|
||
if LINE_X is not None:
|
||
return LINE_X
|
||
if LINE_X_FRAC != 0.5:
|
||
return int(frame_width * LINE_X_FRAC)
|
||
return frame_width // 2
|
||
|
||
|
||
def crossed_line(prev_cx, cx, line_x, direction=CROSS_DIRECTION):
|
||
if direction == 'ltr':
|
||
return prev_cx < line_x <= cx
|
||
if direction == 'both':
|
||
return (prev_cx > line_x >= cx) or (prev_cx < line_x <= cx)
|
||
return prev_cx > line_x >= cx
|
||
|
||
|
||
def now_str():
|
||
return datetime.now().strftime('%Y-%m-%d %H:%M:%S')
|
||
|
||
|
||
def open_capture(source):
|
||
if source.lower().startswith(('rtsp://', 'http://')):
|
||
os.environ['OPENCV_FFMPEG_CAPTURE_OPTIONS'] = RTSP_FFMPEG_OPTIONS
|
||
cap = cv2.VideoCapture(source, cv2.CAP_FFMPEG)
|
||
cap.set(cv2.CAP_PROP_BUFFERSIZE, 1)
|
||
return cap
|
||
|
||
|
||
def warmup_stream(cap, n=WARMUP_FRAMES):
|
||
print('Warming up stream...')
|
||
for _ in range(n):
|
||
cap.read()
|
||
print('Stream ready!')
|
||
|
||
|
||
def open_video_writer(path, w, h, fps):
|
||
return cv2.VideoWriter(path, cv2.VideoWriter_fourcc(*'avc1'), fps, (w, h))
|
||
|
||
|
||
class CsvLogger:
|
||
def __init__(self, path, header):
|
||
Path(path).parent.mkdir(parents=True, exist_ok=True)
|
||
new_file = not Path(path).exists() or Path(path).stat().st_size == 0
|
||
self.file = open(path, 'a', newline='', buffering=1)
|
||
self.writer = csv.writer(self.file)
|
||
if new_file:
|
||
self.writer.writerow(header)
|
||
self.file.flush()
|
||
|
||
def write_row(self, row):
|
||
self.writer.writerow(row)
|
||
self.file.flush()
|
||
|
||
def close(self):
|
||
self.file.close()
|
||
|
||
|
||
class VideoSegmentWriter:
|
||
def __init__(self, output_dir, w, h, fps, segment_sec):
|
||
self.output_dir = Path(output_dir)
|
||
self.output_dir.mkdir(parents=True, exist_ok=True)
|
||
self.w, self.h, self.fps = w, h, fps
|
||
self.segment_sec = segment_sec
|
||
self.segment_start = time.monotonic()
|
||
self.writer = None
|
||
self._open_next()
|
||
|
||
def _segment_path(self):
|
||
ts = datetime.now().strftime('%Y%m%d_%H%M%S')
|
||
return str(self.output_dir / f'live_{ts}.mp4')
|
||
|
||
def _open_next(self):
|
||
if self.writer is not None:
|
||
self.writer.release()
|
||
path = self._segment_path()
|
||
self.writer = open_video_writer(path, self.w, self.h, self.fps)
|
||
self.segment_start = time.monotonic()
|
||
print(f'Recording segment: {path}')
|
||
|
||
def write(self, frame):
|
||
if time.monotonic() - self.segment_start >= self.segment_sec:
|
||
self._open_next()
|
||
self.writer.write(frame)
|
||
|
||
def release(self):
|
||
if self.writer is not None:
|
||
self.writer.release()
|
||
|
||
|
||
def prune_stale_tracks(tracked, now_mono):
|
||
stale = [tid for tid, (_, ts) in tracked.items() if now_mono - ts > TRACKED_PRUNE_SEC]
|
||
for tid in stale:
|
||
del tracked[tid]
|
||
|
||
|
||
def overlay_rect(img, x1, y1, x2, y2, color, alpha=0.65):
|
||
x1, y1 = max(0, x1), max(0, y1)
|
||
x2, y2 = min(img.shape[1], x2), min(img.shape[0], y2)
|
||
if x2 <= x1 or y2 <= y1:
|
||
return
|
||
roi = img[y1:y2, x1:x2]
|
||
patch = np.full_like(roi, color, dtype=np.uint8)
|
||
cv2.addWeighted(patch, alpha, roi, 1 - alpha, 0, roi)
|
||
|
||
|
||
def draw_pill(img, text, x, y, bg, fg=C_TEXT, font_scale=0.45, pad_x=6, pad_y=4):
|
||
font = cv2.FONT_HERSHEY_SIMPLEX
|
||
(tw, th), baseline = cv2.getTextSize(text, font, font_scale, 1)
|
||
x1, y1 = x, y - th - pad_y
|
||
x2, y2 = x + tw + pad_x * 2, y + baseline + pad_y
|
||
cv2.rectangle(img, (x1, y1), (x2, y2), bg, -1)
|
||
cv2.rectangle(img, (x1, y1), (x2, y2), C_BORDER, 1)
|
||
cv2.putText(img, text, (x + pad_x, y), font, font_scale, fg, 1, cv2.LINE_AA)
|
||
|
||
|
||
def draw_elegant_counting_line(img, line_x, h, pulse_remaining=0):
|
||
strength = pulse_remaining / max(LINE_PULSE_FRAMES, 1)
|
||
glow_alpha = 0.12 + 0.18 * strength
|
||
for offset in (14, 9, 5):
|
||
color = tuple(int(c * glow_alpha) for c in C_LINE_GLOW)
|
||
cv2.line(img, (line_x - offset, 0), (line_x - offset, h), color, 1, cv2.LINE_AA)
|
||
cv2.line(img, (line_x + offset, 0), (line_x + offset, h), color, 1, cv2.LINE_AA)
|
||
dash_len, gap = 18, 12
|
||
y = 0
|
||
while y < h:
|
||
y_end = min(y + dash_len, h)
|
||
cv2.line(img, (line_x, y), (line_x, y_end), C_LINE_CORE, 2, cv2.LINE_AA)
|
||
y += dash_len + gap
|
||
cv2.putText(img, 'COUNT LINE', (line_x - 46, 24), cv2.FONT_HERSHEY_SIMPLEX, 0.42, C_LINE_CORE, 1, cv2.LINE_AA)
|
||
|
||
|
||
def draw_hero_count(img, line_x, h, count, pulse_remaining=0):
|
||
text = str(count)
|
||
font = cv2.FONT_HERSHEY_SIMPLEX
|
||
boost = 0.35 * (pulse_remaining / max(COUNT_PULSE_FRAMES, 1))
|
||
font_scale, thickness = 1.6 + boost, 3
|
||
(tw, th), _ = cv2.getTextSize(text, font, font_scale, thickness)
|
||
pad = 14
|
||
tx, ty = line_x - tw // 2, h // 2 + th // 2
|
||
overlay_rect(img, tx - pad, ty - th - pad, tx + tw + pad, ty + pad // 2, C_PANEL, alpha=0.78)
|
||
cv2.rectangle(img, (tx - pad, ty - th - pad), (tx + tw + pad, ty + pad // 2), C_LINE_CORE, 2)
|
||
cv2.putText(img, text, (tx, ty), font, font_scale, C_GREEN, thickness, cv2.LINE_AA)
|
||
|
||
|
||
def draw_hud(img, w, batch_num, batch_count, total_ayam, elapsed_sec, rate, camera_id, clock):
|
||
bar_h = 52
|
||
overlay_rect(img, 0, 0, w, bar_h, C_PANEL, alpha=0.72)
|
||
cv2.line(img, (0, bar_h), (w, bar_h), C_BORDER, 1)
|
||
cv2.putText(img, 'BATCH', (16, 20), cv2.FONT_HERSHEY_SIMPLEX, 0.45, C_MUTED, 1, cv2.LINE_AA)
|
||
batch_label = str(batch_num) if batch_num else '—'
|
||
cv2.putText(img, batch_label, (16, 44), cv2.FONT_HERSHEY_SIMPLEX, 0.9, C_ACCENT, 2, cv2.LINE_AA)
|
||
cv2.putText(img, 'COUNT', (100, 20), cv2.FONT_HERSHEY_SIMPLEX, 0.45, C_MUTED, 1, cv2.LINE_AA)
|
||
cv2.putText(img, str(batch_count), (100, 44), cv2.FONT_HERSHEY_SIMPLEX, 0.9, C_GREEN, 2, cv2.LINE_AA)
|
||
cv2.putText(img, 'TOTAL', (190, 20), cv2.FONT_HERSHEY_SIMPLEX, 0.45, C_MUTED, 1, cv2.LINE_AA)
|
||
cv2.putText(img, str(total_ayam), (190, 44), cv2.FONT_HERSHEY_SIMPLEX, 0.7, C_TEXT, 1, cv2.LINE_AA)
|
||
cv2.putText(img, 'UPTIME', (280, 20), cv2.FONT_HERSHEY_SIMPLEX, 0.45, C_MUTED, 1, cv2.LINE_AA)
|
||
cv2.putText(img, f'{elapsed_sec / 3600:.1f}h', (280, 44), cv2.FONT_HERSHEY_SIMPLEX, 0.7, C_TEXT, 1, cv2.LINE_AA)
|
||
cv2.putText(img, 'RATE', (380, 20), cv2.FONT_HERSHEY_SIMPLEX, 0.45, C_MUTED, 1, cv2.LINE_AA)
|
||
cv2.putText(img, f'{rate:.1f}/min', (380, 44), cv2.FONT_HERSHEY_SIMPLEX, 0.7, C_ACCENT, 1, cv2.LINE_AA)
|
||
cv2.putText(img, clock, (w - 180, 36), cv2.FONT_HERSHEY_SIMPLEX, 0.55, C_TEXT, 1, cv2.LINE_AA)
|
||
cv2.putText(img, f'CAM {camera_id}', (w - 180, 20), cv2.FONT_HERSHEY_SIMPLEX, 0.45, C_MUTED, 1, cv2.LINE_AA)
|
||
|
||
|
||
def draw_footer(img, w, h, frame_idx, live_tag):
|
||
bar_h = 28
|
||
overlay_rect(img, 0, h - bar_h, w, h, C_PANEL, alpha=0.55)
|
||
cv2.putText(img, f'{live_tag} | Frame {frame_idx}', (12, h - 9), cv2.FONT_HERSHEY_SIMPLEX, 0.45, C_MUTED, 1, cv2.LINE_AA)
|
||
|
||
|
||
def draw_skeleton_bold(img, kpts):
|
||
for (a, b), color in zip(SKELETON, SK_COLORS):
|
||
if a < len(kpts) and b < len(kpts):
|
||
xa, ya = int(kpts[a][0]), int(kpts[a][1])
|
||
xb, yb = int(kpts[b][0]), int(kpts[b][1])
|
||
if xa > 0 and ya > 0 and xb > 0 and yb > 0:
|
||
cv2.line(img, (xa, ya), (xb, yb), color, 3, cv2.LINE_AA)
|
||
for kp in kpts:
|
||
x, y = int(kp[0]), int(kp[1])
|
||
if x > 0 and y > 0:
|
||
cv2.circle(img, (x, y), 6, (255, 255, 255), -1, cv2.LINE_AA)
|
||
cv2.circle(img, (x, y), 6, (40, 40, 40), 2, cv2.LINE_AA)
|
||
|
||
|
||
def draw_popups(img, popups, frame_idx):
|
||
alive = []
|
||
for pop in popups:
|
||
age = frame_idx - pop['born']
|
||
if age > POPUP_LIFETIME:
|
||
continue
|
||
alive.append(pop)
|
||
fade = 1.0 - age / POPUP_LIFETIME
|
||
y = pop['y'] - int(age * 1.8)
|
||
color = (int(C_GREEN[0] * fade), int(C_GREEN[1] * fade), int(C_GREEN[2] * fade))
|
||
cv2.putText(img, pop['text'], (pop['x'], y), cv2.FONT_HERSHEY_SIMPLEX, 0.7, color, 2, cv2.LINE_AA)
|
||
return alive
|
||
|
||
|
||
def draw_batch_banner(img, w, batch_num, pulse_remaining):
|
||
if pulse_remaining <= 0:
|
||
return
|
||
text = f'NEW BATCH {batch_num}'
|
||
font = cv2.FONT_HERSHEY_SIMPLEX
|
||
(tw, th), _ = cv2.getTextSize(text, font, 0.8, 2)
|
||
x1, y1 = w // 2 - tw // 2 - 16, 62
|
||
x2, y2 = w // 2 + tw // 2 + 16, 62 + th + 20
|
||
overlay_rect(img, x1, y1, x2, y2, C_PANEL, alpha=0.7)
|
||
cv2.rectangle(img, (x1, y1), (x2, y2), C_ACCENT, 2)
|
||
cv2.putText(img, text, (w // 2 - tw // 2, 62 + th + 4), font, 0.8, C_ACCENT, 2, cv2.LINE_AA)
|
||
|
||
|
||
def connect_stream(source, warmup=WARMUP_FRAMES):
|
||
attempts = 0
|
||
while not shutdown_requested:
|
||
cap = open_capture(source)
|
||
if not cap.isOpened():
|
||
attempts += 1
|
||
if MAX_RECONNECT_ATTEMPTS and attempts >= MAX_RECONNECT_ATTEMPTS:
|
||
raise RuntimeError(f'Cannot open source after {attempts} attempts: {source}')
|
||
print(f'Cannot open source, retry in {RECONNECT_DELAY_SEC}s...')
|
||
time.sleep(RECONNECT_DELAY_SEC)
|
||
continue
|
||
if warmup > 0 and source.lower().startswith(('rtsp://', 'http://')):
|
||
warmup_stream(cap, warmup)
|
||
w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
|
||
h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
|
||
fps = cap.get(cv2.CAP_PROP_FPS)
|
||
if not fps or fps <= 1:
|
||
fps = OUTPUT_FPS
|
||
return cap, w, h, fps
|
||
return None, 0, 0, OUTPUT_FPS
|
||
|
||
|
||
# =============================================================================
|
||
# Main loop
|
||
# =============================================================================
|
||
|
||
def run():
|
||
global shutdown_requested
|
||
|
||
store = BatchStore(
|
||
db_path=DB_PATH,
|
||
state_file=STATE_FILE,
|
||
camera_name=CAMERA_NAME,
|
||
object_label=OBJECT_LABEL,
|
||
cutoff_time=DAILY_CUTOFF_TIME,
|
||
batch_timeout=BATCH_TIMEOUT_SECONDS,
|
||
ignore_batch_label_timeout=IGNORE_BATCH_LABEL_TIMEOUT,
|
||
min_object_per_batch=MIN_OBJECT_PER_BATCH,
|
||
min_duration_per_batch=MIN_DURATION_PER_BATCH,
|
||
logger=lambda msg: print(f'[{now_str()}] {msg}'),
|
||
)
|
||
store.start_cutoff_watcher()
|
||
|
||
cross_logger = None
|
||
if EXPORT_CSV:
|
||
cross_logger = CsvLogger(CROSS_CSV, ['batch', 'frame', 'timestamp', 'chicken_id'])
|
||
|
||
# Load RKNN model
|
||
model = RKNNYOLO(
|
||
model_path=MODEL_PATH,
|
||
core_mask=CORE_MASK,
|
||
imgsz=IMGSZ,
|
||
conf=CONF,
|
||
num_classes=NUM_CLASSES,
|
||
score_sigmoid=SCORE_SIGMOID,
|
||
)
|
||
|
||
# Class IDs — order comes from RKNN model output (class index)
|
||
# class index 0 → CLASS_AYAM, index 1 → CLASS_TALENAN (or env-specified)
|
||
# Use class names in env order: first CLASS_AYAM → id 0, then CLASS_TALENAN → id 1
|
||
CLASS_IDS = {
|
||
os.getenv('CLASS_AYAM', 'ayam'): 0,
|
||
os.getenv('CLASS_TALENAN', 'talenan'): 1,
|
||
}
|
||
ayam_cls = CLASS_IDS[CLASS_AYAM]
|
||
talenan_cls = CLASS_IDS[CLASS_TALENAN]
|
||
|
||
ayam_tracker = SimpleTracker(max_age=60)
|
||
talenan_tracker = SimpleTracker(max_age=60)
|
||
|
||
ayam_line_crossed = set()
|
||
talenan_line_crossed = set()
|
||
|
||
ayam_cross_flash = {}
|
||
talenan_cross_flash = {}
|
||
line_pulse = count_pulse = batch_pulse = 0
|
||
popups = []
|
||
|
||
session_start = time.time()
|
||
frame_idx = 0
|
||
video_writer = None
|
||
|
||
cap, w, h, fps = connect_stream(SOURCE)
|
||
if cap is None:
|
||
store.shutdown()
|
||
model.release()
|
||
return
|
||
|
||
line_x = resolve_line_x(w)
|
||
print(f'RKNN counter | {w}x{h} @ {fps}fps | line x={line_x} | cross={CROSS_DIRECTION}')
|
||
print(f'Model: {MODEL_PATH} | imgsz={IMGSZ} | core_mask={CORE_MASK}')
|
||
print(f'DB: {DB_PATH}')
|
||
print(f'State: {STATE_FILE}')
|
||
|
||
if RECORD_VIDEO:
|
||
video_writer = VideoSegmentWriter(OUTPUT_DIR, w, h, fps, VIDEO_SEGMENT_SEC)
|
||
|
||
reconnect_count = 0
|
||
|
||
while not shutdown_requested:
|
||
ret, frame = cap.read()
|
||
if not ret:
|
||
if not IS_LIVE:
|
||
break
|
||
reconnect_count += 1
|
||
print(f'Stream dropped (attempt {reconnect_count}), reconnecting in {RECONNECT_DELAY_SEC}s...')
|
||
cap.release()
|
||
time.sleep(RECONNECT_DELAY_SEC)
|
||
cap, w, h, fps = connect_stream(SOURCE)
|
||
if cap is None:
|
||
break
|
||
line_x = resolve_line_x(w)
|
||
continue
|
||
|
||
now = time.time()
|
||
elapsed = now - session_start
|
||
mono = time.monotonic()
|
||
ayam_crossed_frame = batch_closed_frame = batch_started_frame = False
|
||
|
||
# RKNN inference
|
||
detections = model(frame)
|
||
|
||
if detections:
|
||
ayam_dets = [] # list of (cx, xywh_box)
|
||
talenan_dets = []
|
||
ayam_kpts_map = {} # det_idx → keypoints
|
||
talenan_kpts_map = {}
|
||
|
||
for di, det in enumerate(detections):
|
||
bbox = det['bbox']
|
||
cls_id = det['cls']
|
||
cx = (bbox[0] + bbox[2]) / 2.0
|
||
x1, y1, x2, y2 = bbox
|
||
wb, hb = x2 - x1, y2 - y1
|
||
box_cxcywh = np.array([cx, (y1 + y2) / 2, wb, hb], dtype=np.float32)
|
||
|
||
if cls_id == talenan_cls:
|
||
talenan_dets.append((cx, box_cxcywh))
|
||
if det['keypoints'] is not None:
|
||
talenan_kpts_map[len(talenan_dets) - 1] = det['keypoints']
|
||
elif cls_id == ayam_cls:
|
||
ayam_dets.append((cx, box_cxcywh))
|
||
if det['keypoints'] is not None:
|
||
ayam_kpts_map[len(ayam_dets) - 1] = det['keypoints']
|
||
|
||
# Track ayam — returns (track_id → cx, detection_idx → track_id)
|
||
ayam_cx_map, ayam_det_to_track = ayam_tracker.update(ayam_dets)
|
||
|
||
# Track talenan
|
||
talenan_cx_map, talenan_det_to_track = talenan_tracker.update(talenan_dets)
|
||
|
||
# Process talenan crossings
|
||
for di, (cx, box) in enumerate(talenan_dets):
|
||
tid = talenan_det_to_track.get(di)
|
||
if tid is None:
|
||
continue
|
||
if tid in talenan_tracker.tracks:
|
||
if tid in talenan_tracked:
|
||
prev_cx = talenan_tracked[tid][0]
|
||
if crossed_line(prev_cx, cx, line_x) and tid not in talenan_line_crossed:
|
||
talenan_line_crossed.add(tid)
|
||
if store.record_talenan_crossing(tid):
|
||
batch_closed_frame = True
|
||
talenan_cross_flash[tid] = CROSS_FLASH_FRAMES
|
||
popups.append({
|
||
'x': int(cx) - 20,
|
||
'y': int(box[1]),
|
||
'born': frame_idx,
|
||
'text': 'BATCH CLOSED',
|
||
})
|
||
talenan_tracked[tid] = (cx, mono)
|
||
|
||
# Process ayam crossings
|
||
for di, (cx, box) in enumerate(ayam_dets):
|
||
tid = ayam_det_to_track.get(di)
|
||
if tid is None:
|
||
continue
|
||
if tid in ayam_tracker.tracks:
|
||
if tid in ayam_tracked:
|
||
prev_cx = ayam_tracked[tid][0]
|
||
if crossed_line(prev_cx, cx, line_x) and tid not in ayam_line_crossed:
|
||
ayam_line_crossed.add(tid)
|
||
_, started_new = store.record_ayam_crossing(tid)
|
||
if cross_logger:
|
||
cross_logger.write_row([
|
||
store.current_batch_number, frame_idx,
|
||
datetime.now().isoformat(), tid,
|
||
])
|
||
ayam_crossed_frame = True
|
||
if started_new:
|
||
batch_started_frame = True
|
||
ayam_cross_flash[tid] = CROSS_FLASH_FRAMES
|
||
popups.append({
|
||
'x': int(cx) - 12,
|
||
'y': int(box[1]),
|
||
'born': frame_idx,
|
||
'text': '+1',
|
||
})
|
||
ayam_tracked[tid] = (cx, mono)
|
||
|
||
# Draw talenan
|
||
for di, (cx, box) in enumerate(talenan_dets):
|
||
tid = talenan_det_to_track.get(di)
|
||
if tid is None:
|
||
continue
|
||
x1 = int(box[0] - box[2] / 2)
|
||
y1 = int(box[1] - box[3] / 2)
|
||
x2 = int(box[0] + box[2] / 2)
|
||
y2 = int(box[1] + box[3] / 2)
|
||
flash = talenan_cross_flash.get(tid, 0)
|
||
color = C_GREEN if flash > 0 else C_TALENAN_BOX
|
||
cv2.rectangle(frame, (x1, y1), (x2, y2), color, 3 if flash > 0 else 2)
|
||
draw_pill(frame, f'TALENAN {tid}', x1, y1 - 4, color)
|
||
|
||
# Draw ayam
|
||
for di, (cx, box) in enumerate(ayam_dets):
|
||
tid = ayam_det_to_track.get(di)
|
||
if tid is None:
|
||
continue
|
||
x1 = int(box[0] - box[2] / 2)
|
||
y1 = int(box[1] - box[3] / 2)
|
||
x2 = int(box[0] + box[2] / 2)
|
||
y2 = int(box[1] + box[3] / 2)
|
||
flash = ayam_cross_flash.get(tid, 0)
|
||
color = C_GREEN if flash > 0 else C_AYAM_BOX
|
||
cv2.rectangle(frame, (x1, y1), (x2, y2), color, 3 if flash > 0 else 2)
|
||
draw_pill(frame, f'ID {tid}', x1, y1 - 4, color)
|
||
kpts = ayam_kpts_map.get(di)
|
||
if kpts is not None:
|
||
draw_skeleton_bold(frame, kpts)
|
||
|
||
if ayam_crossed_frame:
|
||
line_pulse = LINE_PULSE_FRAMES
|
||
count_pulse = COUNT_PULSE_FRAMES
|
||
if batch_closed_frame:
|
||
line_pulse = LINE_PULSE_FRAMES
|
||
if batch_started_frame:
|
||
batch_pulse = BATCH_PULSE_FRAMES
|
||
|
||
batch_num = store.current_batch_number or 0
|
||
batch_count = store.current_batch_count
|
||
display_total = store.display_total()
|
||
rate = (display_total / elapsed * 60) if elapsed > 0 else 0.0
|
||
|
||
draw_elegant_counting_line(frame, line_x, h, line_pulse)
|
||
draw_hero_count(frame, line_x, h, batch_count, count_pulse)
|
||
draw_hud(frame, w, batch_num, batch_count, display_total, elapsed, rate, CAMERA_NAME, now_str())
|
||
draw_batch_banner(frame, w, batch_num, batch_pulse)
|
||
draw_footer(frame, w, h, frame_idx, 'LIVE-RKNN' if IS_LIVE else 'FILE-RKNN')
|
||
popups = draw_popups(frame, popups, frame_idx)
|
||
|
||
for flash_store in (ayam_cross_flash, talenan_cross_flash):
|
||
for tid in list(flash_store):
|
||
flash_store[tid] -= 1
|
||
if flash_store[tid] <= 0:
|
||
del flash_store[tid]
|
||
line_pulse = max(0, line_pulse - 1)
|
||
count_pulse = max(0, count_pulse - 1)
|
||
batch_pulse = max(0, batch_pulse - 1)
|
||
|
||
if video_writer is not None:
|
||
video_writer.write(frame)
|
||
|
||
if LIVE_STREAM_ENABLED and frame_idx % LIVE_STREAM_EVERY_N == 0:
|
||
try:
|
||
Path(LIVE_STREAM_FRAME_PATH).parent.mkdir(parents=True, exist_ok=True)
|
||
_, jpeg = cv2.imencode('.jpg', frame, [cv2.IMWRITE_JPEG_QUALITY, LIVE_STREAM_QUALITY])
|
||
with open(LIVE_STREAM_FRAME_PATH, 'wb') as f:
|
||
f.write(jpeg.tobytes())
|
||
except Exception:
|
||
pass
|
||
|
||
frame_idx += 1
|
||
if frame_idx % FLUSH_EVERY_N_FRAMES == 0:
|
||
print(
|
||
f'[{now_str()}] Frame {frame_idx} | Batch {batch_num}: {batch_count} '
|
||
f'| Total: {display_total} | Uptime {elapsed / 3600:.2f}h'
|
||
)
|
||
prune_stale_tracks(ayam_tracked, mono)
|
||
prune_stale_tracks(talenan_tracked, mono)
|
||
|
||
cap.release()
|
||
if video_writer is not None:
|
||
video_writer.release()
|
||
if cross_logger:
|
||
cross_logger.close()
|
||
model.release()
|
||
store.shutdown()
|
||
|
||
print('\n=== Batch Summary (SQLite) ===')
|
||
print(f'Database: {DB_PATH}')
|
||
|
||
|
||
# Tracked state dicts: track_id → (cx, monotonic_time)
|
||
ayam_tracked = {}
|
||
talenan_tracked = {}
|
||
|
||
|
||
if __name__ == '__main__':
|
||
run()
|