fix: ASRX duplication, TKG edges, trace ingest, and add pipeline progress publishing
- ASRX handler no longer stores duplicate 'asr' pre_chunks - Pre_chunks storage made idempotent (delete-before-insert) - Rule 1 + trace_ingest changed to query 'asrx' not 'asr' - Trace chunks removed (dynamic from TKG/Qdrant) - TKG scroll_face_points fixed: trace_id >= 1 (not == 1) - TKG AsrxSegmentEntry: start/end -> start_time/end_time (match ASRX JSON) - Unregister error handling: log instead of silent discard - Add publish_pipeline_progress calls at each pipeline stage (processors, rule1, face_trace, identity_agent, TKG, rule2, completion)
This commit is contained in:
Accusys
@@ -33,7 +33,54 @@ def process_pose(
|
||||
uuid: str = "",
|
||||
sample_interval: int = 3, # Changed from 30 to match Face
|
||||
publisher: RedisPublisher = None,
|
||||
target_frames: list = None,
|
||||
) -> dict:
|
||||
# Check if pose.json or pose.json.tmp already exists (from swift_face_pose)
|
||||
# executor.rs renames output to .json.tmp before running Python script
|
||||
tmp_path = output_path.replace('.json', '.json.tmp')
|
||||
|
||||
source_path = None
|
||||
if os.path.exists(output_path):
|
||||
source_path = output_path
|
||||
print(f"[Pose] Output exists from swift_face_pose: {output_path}", file=sys.stderr)
|
||||
elif os.path.exists(tmp_path):
|
||||
source_path = tmp_path
|
||||
print(f"[Pose] Temp output exists from swift_face_pose: {tmp_path}", file=sys.stderr)
|
||||
|
||||
if source_path:
|
||||
with open(source_path) as f:
|
||||
data = json.load(f)
|
||||
|
||||
detected_frames = len(data.get('frames', []))
|
||||
print(f"[Pose] Loaded {detected_frames} detected frames", file=sys.stderr)
|
||||
|
||||
# When target_frames is provided (8Hz sampling), skip interpolation
|
||||
# Swift already outputs at sample_interval=3, matching 8Hz for 24fps
|
||||
if target_frames is not None:
|
||||
print(f"[Pose] 8Hz mode: returning {detected_frames} frames without interpolation", file=sys.stderr)
|
||||
if publisher:
|
||||
publisher.progress("pose", 100, 100, f"{detected_frames} frames (8Hz, no interpolation)")
|
||||
return data
|
||||
|
||||
# Interpolate keypoints for all frames
|
||||
interpolated_data = interpolate_pose(data, video_path)
|
||||
|
||||
# Write interpolated output
|
||||
with open(output_path, 'w') as f:
|
||||
json.dump(interpolated_data, f)
|
||||
|
||||
# Delete .json.tmp file so executor.rs won't restore it
|
||||
if os.path.exists(tmp_path):
|
||||
os.remove(tmp_path)
|
||||
print(f"[Pose] Deleted temp file: {tmp_path}", file=sys.stderr)
|
||||
|
||||
total_frames = len(interpolated_data.get('frames', []))
|
||||
print(f"[Pose] Interpolated to {total_frames} frames", file=sys.stderr)
|
||||
|
||||
if publisher:
|
||||
publisher.progress("pose", 100, 100, f"Interpolated {total_frames} frames")
|
||||
return interpolated_data
|
||||
|
||||
swift_bin = SWIFT_POSE_PATH
|
||||
if not os.path.exists(swift_bin):
|
||||
swift_bin = SWIFT_POSE_ALT
|
||||
@@ -81,6 +128,126 @@ def process_pose(
|
||||
return json.load(f)
|
||||
|
||||
|
||||
def interpolate_pose(detected_data: dict, video_path: str) -> dict:
|
||||
"""Interpolate keypoints for all frames between detected frames"""
|
||||
import cv2
|
||||
import numpy as np
|
||||
|
||||
cap = cv2.VideoCapture(video_path)
|
||||
total_video_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
|
||||
fps = detected_data.get('fps', 30.0)
|
||||
|
||||
detected_frames = detected_data.get('frames', [])
|
||||
if not detected_frames:
|
||||
cap.release()
|
||||
return detected_data
|
||||
|
||||
# Build frame index map
|
||||
frame_map = {f['frame']: f for f in detected_frames}
|
||||
detected_frame_nums = sorted(frame_map.keys())
|
||||
|
||||
print(f"[Pose] Interpolating from {len(detected_frame_nums)} detected frames to {total_video_frames} total frames", file=sys.stderr)
|
||||
|
||||
# Get all persons from detected frames (assume same person tracking)
|
||||
all_persons = {}
|
||||
for f in detected_frames:
|
||||
for i, p in enumerate(f.get('persons', [])):
|
||||
if i not in all_persons:
|
||||
all_persons[i] = []
|
||||
all_persons[i].append((f['frame'], p))
|
||||
|
||||
# Interpolate each person's keypoints for each frame
|
||||
interpolated_frames = []
|
||||
|
||||
for frame_num in range(total_video_frames):
|
||||
ts = frame_num / fps
|
||||
|
||||
persons_in_frame = []
|
||||
|
||||
for person_id, person_frames in all_persons.items():
|
||||
# Find closest detected frames before and after
|
||||
before = None
|
||||
after = None
|
||||
for fn, p in person_frames:
|
||||
if fn <= frame_num:
|
||||
before = (fn, p)
|
||||
if fn >= frame_num and after is None:
|
||||
after = (fn, p)
|
||||
|
||||
if before is None and after is None:
|
||||
continue
|
||||
|
||||
# Interpolate keypoints
|
||||
interpolated_keypoints = []
|
||||
bbox = None
|
||||
|
||||
if before and after and before[0] != after[0]:
|
||||
# Linear interpolation
|
||||
t0, t1 = before[0], after[0]
|
||||
t = (frame_num - t0) / (t1 - t0) if t1 != t0 else 0
|
||||
|
||||
kp_before = before[1].get('keypoints', [])
|
||||
kp_after = after[1].get('keypoints', [])
|
||||
bbox_before = before[1].get('bbox', {})
|
||||
bbox_after = after[1].get('bbox', {})
|
||||
|
||||
# Interpolate keypoints
|
||||
for i in range(max(len(kp_before), len(kp_after))):
|
||||
kp0 = kp_before[i] if i < len(kp_before) else kp_after[i]
|
||||
kp1 = kp_after[i] if i < len(kp_after) else kp_before[i]
|
||||
|
||||
x = kp0['x'] + t * (kp1['x'] - kp0['x'])
|
||||
y = kp0['y'] + t * (kp1['y'] - kp0['y'])
|
||||
c = kp0['confidence'] + t * (kp1['confidence'] - kp0['confidence'])
|
||||
|
||||
interpolated_keypoints.append({
|
||||
'name': kp0['name'],
|
||||
'x': x,
|
||||
'y': y,
|
||||
'confidence': c
|
||||
})
|
||||
|
||||
# Interpolate bbox
|
||||
if bbox_before and bbox_after:
|
||||
bbox = {
|
||||
'x': int(bbox_before['x'] + t * (bbox_after['x'] - bbox_before['x'])),
|
||||
'y': int(bbox_before['y'] + t * (bbox_after['y'] - bbox_before['y'])),
|
||||
'width': int(bbox_before['width'] + t * (bbox_after['width'] - bbox_before['width'])),
|
||||
'height': int(bbox_before['height'] + t * (bbox_after['height'] - bbox_before['height']))
|
||||
}
|
||||
|
||||
elif before:
|
||||
# Use before frame's data
|
||||
interpolated_keypoints = before[1].get('keypoints', [])
|
||||
bbox = before[1].get('bbox', {})
|
||||
|
||||
elif after:
|
||||
# Use after frame's data
|
||||
interpolated_keypoints = after[1].get('keypoints', [])
|
||||
bbox = after[1].get('bbox', {})
|
||||
|
||||
if bbox and bbox.get('width', 0) > 0 and bbox.get('height', 0) > 0:
|
||||
persons_in_frame.append({
|
||||
'keypoints': interpolated_keypoints,
|
||||
'bbox': bbox
|
||||
})
|
||||
|
||||
if persons_in_frame:
|
||||
interpolated_frames.append({
|
||||
'frame': frame_num,
|
||||
'timestamp': ts,
|
||||
'persons': persons_in_frame
|
||||
})
|
||||
|
||||
cap.release()
|
||||
|
||||
return {
|
||||
'frame_count': len(interpolated_frames),
|
||||
'fps': fps,
|
||||
'frames': interpolated_frames
|
||||
}
|
||||
|
||||
|
||||
def _fallback(video_path, output_path, uuid, sample_interval):
|
||||
"""Fallback to YOLOv8 Pose"""
|
||||
from ultralytics import YOLO
|
||||
@@ -135,14 +302,21 @@ if __name__ == "__main__":
|
||||
parser.add_argument("output_path")
|
||||
parser.add_argument("--uuid", "-u", default="")
|
||||
parser.add_argument("--sample-interval", type=int, default=3) # Changed from 30 to match Face
|
||||
parser.add_argument("--frames", type=str, default=None,
|
||||
help="Comma-separated frame numbers for 8Hz sampling")
|
||||
args = parser.parse_args()
|
||||
|
||||
target_frames = None
|
||||
if args.frames:
|
||||
target_frames = [int(f) for f in args.frames.split(",") if f.strip()]
|
||||
print(f"[Pose] 8Hz target frames: {len(target_frames)} frames", file=sys.stderr)
|
||||
|
||||
publisher = RedisPublisher(args.uuid) if args.uuid else None
|
||||
if publisher:
|
||||
publisher.info("pose", "POSE_START")
|
||||
|
||||
result = process_pose(args.video_path, args.output_path, args.uuid,
|
||||
args.sample_interval, publisher)
|
||||
args.sample_interval, publisher, target_frames)
|
||||
with open(args.output_path, "w") as f:
|
||||
json.dump(result, f, indent=2)
|
||||
print(f"Pose: {len(result.get('frames', []))} frames with poses")
|
||||
|
||||
Reference in New Issue
Block a user