radxa-d6a
723 lines
28 KiB
Python
723 lines
28 KiB
Python
"""
|
|
Sensor - Core sensor class for optical tactile sensing.
|
|
|
|
This module provides the Sensor class for capturing, processing, and analyzing
|
|
optical tactile sensor data with support for stitching, optical flow tracking,
|
|
and Helmholtz-Hodge decomposition.
|
|
"""
|
|
|
|
import os
|
|
import platform
|
|
import numpy as np
|
|
import cv2
|
|
import time
|
|
import threading
|
|
from enum import Enum, auto
|
|
from typing import Tuple
|
|
# from threading import Thread, Event
|
|
# from queue import Queue, Empty
|
|
|
|
from .Stitcher import Stitcher
|
|
from .tracker import Tracker
|
|
from .HHD import nHHD
|
|
from . import configs
|
|
from .get_depth import Contact3D
|
|
from .backend_availability import (check_cupy_available, check_opencl_available)
|
|
try:
|
|
import av # Optional: used for Linux camera capture path.
|
|
except ImportError:
|
|
av = None
|
|
|
|
class Sensor:
|
|
"""
|
|
Optical tactile sensor interface with deformation analysis.
|
|
|
|
Provides image capture, stitching, optical flow tracking, and force decomposition.
|
|
Supports both synchronous and asynchronous (pipelined) processing modes.
|
|
"""
|
|
|
|
# =========================================================================
|
|
# Info Enum (for read_info API)
|
|
# =========================================================================
|
|
|
|
class info(Enum):
|
|
"""Data types available through read_info()."""
|
|
VRAW = auto()
|
|
VNORMAL = auto()
|
|
VSHEAR = auto()
|
|
FPS = auto()
|
|
TIMESTAMP = auto()
|
|
FNORMAL = auto()
|
|
FSHEARX = auto()
|
|
FSHEARY = auto()
|
|
CENTROID = auto()
|
|
CONTOUR = auto()
|
|
DEPTH = auto()
|
|
IMG = auto()
|
|
|
|
# =========================================================================
|
|
# Initialization
|
|
# =========================================================================
|
|
|
|
def __init__(self, vid_src, cuda=True, isstitch=True, verbose=True, debug=False,
|
|
config_name="prototype", cal_path=None, override=False, box=None, mirror=True,
|
|
backend='auto'):
|
|
"""
|
|
Initialize Sensor with video source and configuration.
|
|
|
|
Args:
|
|
vid_src: Video source (int for camera ID, str for file path)
|
|
cuda: Enable CUDA acceleration (default: True)
|
|
isstitch: Enable stitching mode for multi-tile sensor (default: False)
|
|
verbose: Print initialization logs (default: True)
|
|
config_name: Configuration name (default: "prototype")
|
|
cal_path: Path to calibration file (default: None)
|
|
override: Skip auto-detection, use provided box (default: False)
|
|
box: Manual bounding boxes when override=True (default: None)
|
|
backend: Poisson backend (default: "auto")
|
|
"auto": Automatically select the best backend based on availability
|
|
"cupy": Use CuPy for GPU acceleration
|
|
"opencl": Use OpenCL for GPU acceleration
|
|
"cpu": Use CPU for computation
|
|
hhd_downsample: Downsample factor for flow field before HHD (default: 1, no downsampling).
|
|
Factor of 2 halves each dimension, giving ~4x speedup in Poisson solve.
|
|
"""
|
|
|
|
self.CUPY_AVAILABLE = check_cupy_available()
|
|
self.OPENCL_AVAILABLE = check_opencl_available()
|
|
|
|
if vid_src is None:
|
|
raise Exception("User must specify a video source.")
|
|
|
|
# Store settings
|
|
self.vid_src = vid_src
|
|
self.isstitch = isstitch
|
|
self.cuda = cuda
|
|
self.verbose = verbose
|
|
self.debug = debug
|
|
self.config_name = config_name
|
|
self.cal_path = cal_path
|
|
self.mirror = mirror
|
|
|
|
# Load configuration
|
|
self.__config_cam = None
|
|
self.__config_stitcher = None
|
|
self.__config_contact = None
|
|
self._load_config()
|
|
|
|
# State variables
|
|
self.stitch_valid = False
|
|
self.compute_deformation_valid = False
|
|
self.compute_contact_valid = False
|
|
|
|
# Image Data Variables (public)
|
|
# self.stitch_calibration = []
|
|
self.frame = self.img = None
|
|
self.initial_img = None
|
|
shape = (self.__config_cam["resolution_stitch"][1], self.__config_cam["resolution_stitch"][0])
|
|
self.img_size_raw = None
|
|
self.img_filtered = None
|
|
|
|
# Optical Flow Data Variables (public)
|
|
self.flow = np.zeros(shape + (2,), dtype=np.float32)
|
|
self.vtemplate = np.zeros_like(self.flow)
|
|
self.vnormal = self.vtemplate
|
|
self.vshear = self.vtemplate
|
|
self.n_boxes = None
|
|
self.fnormal = self.fshearx = self.fsheary = self.ftor = 0.0
|
|
|
|
# Contact Data Variables (public)
|
|
self.centroid = (0, 0)
|
|
self.centroid_found = False
|
|
self.contour = np.empty(0)
|
|
self.depth_map = np.zeros_like(self.img)
|
|
|
|
# Timing
|
|
self.last_log_time = time.perf_counter()
|
|
self._fps = 0
|
|
self._last_capture_time = 0.0
|
|
self._last_processing_time = 0.0
|
|
self._last_stage_times = {
|
|
"extract_tiles": 0.0,
|
|
"stitch": 0.0,
|
|
"resize": 0.0,
|
|
"mirror": 0.0,
|
|
"astype": 0.0,
|
|
}
|
|
|
|
# Initialize components
|
|
self.stitcher = Stitcher(isstitch=isstitch, config_stitcher=self.__config_stitcher, verbose=self.verbose)
|
|
self.__tracker = Tracker(adaptive=True, cuda=cuda, verbose=self.verbose, config_tracker=self.__config_tracker)
|
|
self.__contact3d = Contact3D(config_contact=self.__config_contact, verbose=self.verbose)
|
|
self.__hhd = None
|
|
# cfg_ds = self.__config_tracker.get("hhd_downsample", None)
|
|
# self._hhd_downsample = max(1, int(cfg_ds if cfg_ds is not None else hhd_downsample))
|
|
self._hhd_downsample = self.__config_tracker.get("hhd_downsample", None)
|
|
self._hhd_grid_shape = None
|
|
cfg_backend = self.__config_tracker.get("backend", None)
|
|
self.poisson_backend = cfg_backend if cfg_backend is not None else backend
|
|
self._use_pyav = False
|
|
self._av_container = None
|
|
self._av_stream = None
|
|
self._av_decoder = None
|
|
self.cap = None
|
|
# Treat both camera index (0) and V4L2 path ("/dev/video0") as live camera for threading/low-latency path.
|
|
self._is_live_camera = (
|
|
isinstance(self.vid_src, int)
|
|
or (isinstance(self.vid_src, str) and self.vid_src.startswith("/dev/video"))
|
|
)
|
|
self._capture_thread = None
|
|
self._capture_running = False
|
|
self._latest_frame = None
|
|
self._latest_frame_seq = 0
|
|
self._last_consumed_seq = -1
|
|
self._latest_frame_lock = threading.Lock()
|
|
|
|
# Setup video capture
|
|
self._open_video_source(override, box)
|
|
|
|
if self.verbose:
|
|
print(f" Video source: {vid_src}")
|
|
print(f" Stitch mode: {self.stitch_valid}")
|
|
print(f" Optical flow algorithm: {self.__config_tracker['algorithm']}")
|
|
print(f" Poisson backend: {self.poisson_backend}")
|
|
# print(f" CUDA acceleration: {self.cuda}")
|
|
print(f" CuPy available: {self.CUPY_AVAILABLE}")
|
|
print(f" OpenCL available: {self.OPENCL_AVAILABLE}")
|
|
|
|
|
|
|
|
# =========================================================================
|
|
# Public API - Core Methods (Most Frequently Used)
|
|
# =========================================================================
|
|
|
|
def get_img(self):
|
|
"""
|
|
Capture and preprocess a frame.
|
|
|
|
Returns:
|
|
np.ndarray: Processed grayscale image
|
|
"""
|
|
# Simple direct read - buffer size of 1 should minimize frame accumulation
|
|
# Timing measurement helps identify if capture or processing is the bottleneck
|
|
t_capture_start = time.perf_counter()
|
|
ret, frame = self._read_frame()
|
|
t_capture_end = time.perf_counter()
|
|
self._last_capture_time = t_capture_end - t_capture_start
|
|
|
|
if not ret:
|
|
print("Failed to get_img from video source.")
|
|
return None
|
|
|
|
# Start processing timing
|
|
t_processing_start = time.perf_counter()
|
|
|
|
# self.frame = frame.copy()
|
|
self.frame = frame
|
|
# Extract and stitch tiles
|
|
# self.stitcher.get_stitch_unit(frame)
|
|
self._extract_tiles(frame)
|
|
t_after_extract = time.perf_counter()
|
|
|
|
img = np.ascontiguousarray(self.stitcher.stitch_rt_optimized(blend=True))
|
|
t_after_stitch = time.perf_counter()
|
|
|
|
self.img_size_raw = img.shape
|
|
# Resize
|
|
img = cv2.resize(img, tuple(self._config_resolution_stitch), interpolation=cv2.INTER_LINEAR)
|
|
t_after_resize = time.perf_counter()
|
|
|
|
if self.mirror:
|
|
img = cv2.flip(img, 1)
|
|
t_after_mirror = time.perf_counter()
|
|
|
|
self.img = img.astype(np.uint8)
|
|
t_after_astype = time.perf_counter()
|
|
|
|
t_processing_end = time.perf_counter()
|
|
self._last_processing_time = t_processing_end - t_processing_start
|
|
self._last_stage_times["extract_tiles"] = t_after_extract - t_processing_start
|
|
self._last_stage_times["stitch"] = t_after_stitch - t_after_extract
|
|
self._last_stage_times["resize"] = t_after_resize - t_after_stitch
|
|
self._last_stage_times["mirror"] = t_after_mirror - t_after_resize
|
|
self._last_stage_times["astype"] = t_after_astype - t_after_mirror
|
|
|
|
# FPS calculation
|
|
self._fps = 1.0 / (time.perf_counter() - self.last_log_time)
|
|
self.last_log_time = time.perf_counter()
|
|
|
|
return self.img.copy()
|
|
|
|
def detect_motion(self, threshold=6):
|
|
|
|
# detect motion by optical flow magnitude
|
|
mag = np.linalg.norm(self.flow, axis=1)
|
|
# print(f"mag: {mag.max()}, {mag.min()}, {mag.mean()}")
|
|
return mag.mean() > threshold
|
|
|
|
def compute_deformation(self, decompose=True, check_motion=True, threshold=6):
|
|
"""
|
|
Compute optical flow and decompose into force components.
|
|
|
|
Returns:
|
|
np.ndarray: Optical flow field
|
|
"""
|
|
if self.img is None:
|
|
raise Exception("Warning: Get image first")
|
|
|
|
self.compute_flow()
|
|
# self.compute_hhd()
|
|
if check_motion:
|
|
if self.detect_motion(threshold=threshold):
|
|
self.compute_hhd()
|
|
return True
|
|
else:
|
|
return False
|
|
else:
|
|
if decompose:
|
|
self.compute_hhd()
|
|
|
|
return None
|
|
# return True
|
|
|
|
def compute_flow(self):
|
|
if self.img is None:
|
|
raise Exception("Warning: Get image first")
|
|
|
|
flow = self.__tracker.track(self.img)
|
|
# flow = self.__tracker.track_raft(self.img)
|
|
if hasattr(flow, 'download'):
|
|
flow = flow.download()
|
|
self.flow = flow
|
|
|
|
def compute_hhd(self):
|
|
|
|
flow = self.flow
|
|
if flow is None:
|
|
raise Exception("Warning: Compute flow first")
|
|
|
|
orig_h, orig_w = flow.shape[:2]
|
|
k = self._hhd_downsample
|
|
|
|
if k > 1:
|
|
ds_w = max(1, orig_w // k)
|
|
ds_h = max(1, orig_h // k)
|
|
flow_ds = cv2.resize(flow, (ds_w, ds_h), interpolation=cv2.INTER_AREA)
|
|
else:
|
|
flow_ds = flow
|
|
|
|
ds_shape = flow_ds.shape[:2]
|
|
if self.__hhd is None or self._hhd_grid_shape != ds_shape:
|
|
spacings = (18 * k, 18 * k)
|
|
self.__hhd = nHHD(cuda=self.cuda, grid=ds_shape, spacings=spacings, poisson_backend=self.poisson_backend, debug=self.debug)
|
|
self._hhd_grid_shape = ds_shape
|
|
|
|
_, forces = self.__hhd.get_force(flow_ds)
|
|
self.fnormal, self.fshearx, self.fsheary, self.ftor = forces
|
|
|
|
vnormal_ds = self.__hhd.get_normal()
|
|
vshear_ds = self.__hhd.get_shear()
|
|
|
|
if k > 1:
|
|
self.vnormal = cv2.resize(vnormal_ds, (orig_w, orig_h), interpolation=cv2.INTER_LINEAR)
|
|
self.vshear = cv2.resize(vshear_ds, (orig_w, orig_h), interpolation=cv2.INTER_LINEAR)
|
|
else:
|
|
self.vnormal = vnormal_ds
|
|
self.vshear = vshear_ds
|
|
|
|
self.compute_deformation_valid = True
|
|
|
|
return True
|
|
|
|
def compute_contact(self, vnormal=None):
|
|
"""
|
|
Compute contact information from vnormal field.
|
|
|
|
Args:
|
|
vnormal: Optional vnormal field. If None, uses self.vnormal.
|
|
|
|
Returns:
|
|
dict: Contact result with centroid, contour, and depth_map
|
|
"""
|
|
multiple_foe = False
|
|
|
|
# Use provided vnormal or fall back to internal state
|
|
vnormal_to_use = vnormal if vnormal is not None else self.vnormal
|
|
|
|
if vnormal_to_use is None:
|
|
raise Exception("Warning: vnormal is required for contact computation")
|
|
|
|
if multiple_foe:
|
|
result = self.__contact3d.compute_multiple_foe(vnormal_to_use)
|
|
else:
|
|
if self.cuda:
|
|
result = self.__contact3d.compute_foe_gpu(vnormal_to_use)
|
|
else:
|
|
result = self.__contact3d.compute_foe(vnormal_to_use)
|
|
|
|
self.centroid = result['centroid']
|
|
self.centroid_found = result['centroid_found']
|
|
if 'contour' in result:
|
|
self.contour = result['contour']
|
|
self.depth_map = result['divergence_map']
|
|
|
|
self.compute_contact_valid = True
|
|
return result
|
|
|
|
|
|
def read_info(self, *args) -> Tuple:
|
|
"""
|
|
Get sensor data by info type.
|
|
|
|
Args:
|
|
*args: info enum values (e.g., sensor.info.FPS, sensor.info.FNORMAL)
|
|
|
|
Returns:
|
|
Tuple: Requested data in order
|
|
"""
|
|
if any(arg in [self.info.IMG] for arg in args):
|
|
if self.img is None:
|
|
raise Exception("Warning: Get image first")
|
|
|
|
# if any(arg in [self.info.VRAW, self.info.VNORMAL, self.info.VSHEAR, self.info.FNORMAL, self.info.FSHEARX, self.info.FSHEARY] for arg in args):
|
|
# if not self.compute_deformation_valid:
|
|
# print("Warning: Compute deformation first")
|
|
# # raise Exception("Warning: Compute deformation first")
|
|
|
|
# if any(arg in [self.info.CENTROID, self.info.CONTOUR, self.info.DEPTH] for arg in args):
|
|
# if not self.compute_contact_valid:
|
|
# print("Warning: Compute contact first")
|
|
# raise Exception("Warning: Compute contact first")
|
|
|
|
mapping = {
|
|
# Return copies of arrays to prevent external modification of internal state
|
|
self.info.VRAW: lambda: self.flow.copy() if self.flow is not None else np.array([]),
|
|
self.info.VNORMAL: lambda: self.vnormal.copy() if self.vnormal is not None else np.array([]),
|
|
self.info.VSHEAR: lambda: self.vshear.copy() if self.vshear is not None else np.array([]),
|
|
# Scalar values are safe to return directly
|
|
self.info.FNORMAL: lambda: self.fnormal,
|
|
self.info.FSHEARX: lambda: self.fshearx,
|
|
self.info.FSHEARY: lambda: self.fsheary,
|
|
self.info.FPS: lambda: self._fps,
|
|
self.info.TIMESTAMP: lambda: time.strftime('%H:%M:%S'),
|
|
# Return copies of arrays to prevent external modification
|
|
self.info.DEPTH: lambda: self.depth_map.copy() if self.depth_map is not None else np.array([]),
|
|
# Centroid: can be tuple, list, or array - return a copy to prevent modification
|
|
# Return None if centroid is not found or empty
|
|
self.info.CENTROID: lambda: (
|
|
np.array(self.centroid).copy()
|
|
if self.centroid is not None and len(self.centroid) > 0
|
|
else None
|
|
),
|
|
self.info.CONTOUR: lambda: self.contour.copy() if self.contour is not None else np.array([]),
|
|
self.info.IMG: lambda: self.img.copy() if self.img is not None else np.array([]),
|
|
}
|
|
|
|
return tuple(mapping.get(arg, lambda: None)() for arg in args if isinstance(arg, self.info))
|
|
|
|
def reset(self):
|
|
"""Reset optical flow tracker."""
|
|
self.__tracker.reset()
|
|
if self.img is not None:
|
|
self.initial_img = self.img.copy()
|
|
|
|
|
|
def disconnect(self):
|
|
"""Release resources and stop async threads."""
|
|
self._capture_running = False
|
|
if self._capture_thread is not None:
|
|
self._capture_thread.join(timeout=1.0)
|
|
self._capture_thread = None
|
|
|
|
if self._use_pyav:
|
|
if self._av_container is not None:
|
|
self._av_container.close()
|
|
self._av_container = None
|
|
self._av_stream = None
|
|
self._av_decoder = None
|
|
if self.verbose:
|
|
print("Sensor disconnected.")
|
|
elif self.cap is not None and self.cap.isOpened():
|
|
self.cap.release()
|
|
if self.verbose:
|
|
print("Sensor disconnected.")
|
|
cv2.destroyAllWindows()
|
|
|
|
# =========================================================================
|
|
# Public API - Configuration & Calibration
|
|
# =========================================================================
|
|
|
|
# def export_config(self, path="./config/exported_config.json"):
|
|
# """Return current configuration dict."""
|
|
# configs.export_config(self._config, path)
|
|
# if self.verbose:
|
|
# print(f"Config exported to {path}")
|
|
# return True
|
|
|
|
|
|
|
|
# def stitch_cal(self):
|
|
# """
|
|
# Load or create stitch calibration.
|
|
|
|
# Returns:
|
|
# np.ndarray: Stitched calibration image
|
|
# """
|
|
# if self.cal_path is None:
|
|
# self.cal_path = "./config/cal.npy"
|
|
|
|
# if os.path.exists(self.cal_path):
|
|
# if self.verbose:
|
|
# print("Loading calibration from", self.cal_path)
|
|
# self.stitch_calibration = np.load(self.cal_path, allow_pickle=True)
|
|
# self.stitcher.stitch_calibration = self.stitch_calibration
|
|
# return self.stitcher.stitch_rt_optimized()
|
|
# else:
|
|
# if self.verbose:
|
|
# print("Creating new calibration...")
|
|
# img, self.stitch_calibration = self.stitcher.stitch_cal()
|
|
# os.makedirs("./config", exist_ok=True)
|
|
# np.save(self.cal_path, self.stitch_calibration)
|
|
# if self.verbose:
|
|
# print("Calibration saved to", self.cal_path)
|
|
# return img
|
|
|
|
# =========================================================================
|
|
# Private - Initialization Helpers
|
|
# =========================================================================
|
|
|
|
def _load_config(self):
|
|
"""Load sensor configuration from JSON file."""
|
|
self._config = configs.load_config(self.config_name)
|
|
self.__config_cam = self._config["camera"]
|
|
self._config_resolution_raw = self.__config_cam["resolution_raw"]
|
|
self._config_fps = self.__config_cam["fps"]
|
|
self._config_units = self.__config_cam["units"]
|
|
self._config_resolution_stitch = self.__config_cam["resolution_stitch"]
|
|
|
|
self._config_dis_preset = self._config["tracker"]["dis_preset"]
|
|
|
|
self.__config_tracker = self._config["tracker"]
|
|
self.__config_stitcher = self._config["stitcher"]
|
|
self.__config_contact = self._config["contact"]
|
|
|
|
if self.verbose:
|
|
print(f"Config: {self.config_name}")
|
|
return True
|
|
|
|
def _open_video_source(self, override, box):
|
|
"""Initialize video capture and calibration."""
|
|
# _is_camera_index = isinstance(self.vid_src, int)
|
|
# _is_v4l2_path = isinstance(self.vid_src, str) and self.vid_src.startswith("/dev/video")
|
|
# use_linux_camera_pyav = (
|
|
# platform.system() == "Linux"
|
|
# and (_is_camera_index or _is_v4l2_path)
|
|
# and av is not None
|
|
# )
|
|
|
|
# if use_linux_camera_pyav:
|
|
# device = self.vid_src if _is_v4l2_path else f"/dev/video{self.vid_src}"
|
|
# if self.verbose:
|
|
# print(f"Using PyAV Linux camera backend: {device}")
|
|
# try:
|
|
# self._av_container = av.open(
|
|
# device,
|
|
# format="v4l2",
|
|
# options={
|
|
# "input_format": "mjpeg",
|
|
# "video_size": f"{self._config_resolution_raw[0]}x{self._config_resolution_raw[1]}",
|
|
# "framerate": str(self._config_fps),
|
|
# },
|
|
# )
|
|
# self._av_stream = self._av_container.streams.video[0]
|
|
# self._av_decoder = self._av_container.decode(self._av_stream)
|
|
# self._use_pyav = True
|
|
# except Exception as exc:
|
|
# if self.verbose:
|
|
# print(f"PyAV camera open failed ({exc}), fallback to OpenCV backend.")
|
|
# self._use_pyav = False
|
|
|
|
self.use_pyav = False
|
|
if not self._use_pyav:
|
|
self.cap = cv2.VideoCapture(self.vid_src)
|
|
# Set buffer size to 1 to reduce latency and avoid frame accumulation
|
|
# Note: Not all backends support this, but it helps when available
|
|
# try:
|
|
# self.cap.set(cv2.CAP_PROP_BUFFERSIZE, 1)
|
|
# except Exception:
|
|
# pass # Some backends don't support this property
|
|
self.cap.set(cv2.CAP_PROP_FOURCC, cv2.VideoWriter.fourcc('M', 'J', 'P', 'G'))
|
|
self.cap.set(cv2.CAP_PROP_FPS, self._config_fps)
|
|
self.cap.set(cv2.CAP_PROP_FRAME_WIDTH, self._config_resolution_raw[0])
|
|
self.cap.set(cv2.CAP_PROP_FRAME_HEIGHT, self._config_resolution_raw[1])
|
|
|
|
|
|
if self.verbose:
|
|
print("Connecting to video source...")
|
|
|
|
|
|
if not self._is_source_open():
|
|
raise Exception("Failed to open video source.")
|
|
|
|
if self.verbose and not self._use_pyav and self.cap is not None:
|
|
fourcc_int = int(self.cap.get(cv2.CAP_PROP_FOURCC))
|
|
fourcc_bytes = [(fourcc_int >> (8 * i)) & 0xFF for i in range(4)]
|
|
# Show printable FOURCC only; some backends return 0 or non-printable bytes.
|
|
if fourcc_int <= 0:
|
|
fourcc = "N/A"
|
|
else:
|
|
fourcc = "".join(chr(b) if 32 <= b <= 126 else "." for b in fourcc_bytes)
|
|
width = int(self.cap.get(cv2.CAP_PROP_FRAME_WIDTH))
|
|
height = int(self.cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
|
|
fps = self.cap.get(cv2.CAP_PROP_FPS)
|
|
backend_id = int(self.cap.get(cv2.CAP_PROP_BACKEND))
|
|
print(
|
|
f"OpenCV negotiated stream: FOURCC='{fourcc}' "
|
|
f"(int={fourcc_int}, hex=0x{fourcc_int:08X}), "
|
|
f"size={width}x{height}, fps={fps:.2f}, backend_id={backend_id}"
|
|
)
|
|
|
|
# Wait for first valid frame
|
|
frame = None
|
|
while frame is None:
|
|
ret, frame = self._read_frame_raw()
|
|
if not ret:
|
|
time.sleep(0.1)
|
|
|
|
if override:
|
|
if box is not None:
|
|
self.stitcher.isstitch = self.isstitch = False
|
|
self.stitcher.boxes = box
|
|
else:
|
|
print("Override=True but no box provided.")
|
|
else:
|
|
self._find_stitch_boxes(frame)
|
|
self._extract_tiles(frame)
|
|
# Feature-based stitching no longer needs eager overlap calibration here.
|
|
# Keep stitch_cal() as a fallback so older overlap-based stitching still works.
|
|
img = self.stitcher.stitch_rt_optimized()
|
|
# if img is None:
|
|
# img = self.stitch_cal()
|
|
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
|
|
self.resolution_stitch = img.shape
|
|
self.initial_img = cv2.resize(img, tuple(self._config_resolution_stitch), interpolation=cv2.INTER_CUBIC)
|
|
if self.mirror:
|
|
self.initial_img = cv2.flip(self.initial_img, 1)
|
|
self.initial_img = self.initial_img.astype(np.uint8)
|
|
|
|
# For live cameras, start a latest-frame capture thread to avoid latency buildup.
|
|
if self._is_live_camera:
|
|
self._start_capture_thread()
|
|
|
|
|
|
def _find_stitch_boxes(self, img_src, show=False):
|
|
"""Detect vision tile boxes with camera stabilization."""
|
|
n_boxes, v_mean0, timeout = 0, 0, 5
|
|
start_time = cv2.getTickCount()
|
|
|
|
while n_boxes < self._config_units:
|
|
ret, frame = self._read_frame_raw()
|
|
if not ret:
|
|
continue
|
|
v_mean = np.sum(cv2.mean(frame))
|
|
|
|
if abs(v_mean - v_mean0) < 5:
|
|
n_boxes, boxes = self.stitcher.find_stitch_boxes(frame, show=show)
|
|
|
|
if (cv2.getTickCount() - start_time) / cv2.getTickFrequency() > timeout:
|
|
print("Timeout finding vision units.")
|
|
self.stitcher.isstitch = self.isstitch = False
|
|
break
|
|
v_mean0 = v_mean
|
|
|
|
self.n_boxes = n_boxes
|
|
self.boxes = boxes
|
|
self.stitch_valid = self.isstitch and n_boxes == self._config_units
|
|
|
|
status = "valid for stitching" if self.stitch_valid else "non-stitch mode"
|
|
print(f"Sensor: {status}")
|
|
return n_boxes
|
|
|
|
def _extract_tiles(self, img_src):
|
|
"""Extract tiles from source image."""
|
|
self.stitcher.get_stitch_unit(img_src)
|
|
self.stitcher.extract_tiles()
|
|
return True
|
|
|
|
def _is_source_open(self):
|
|
if self._use_pyav:
|
|
return self._av_container is not None
|
|
return self.cap is not None and self.cap.isOpened()
|
|
|
|
def _read_frame(self):
|
|
if self._capture_running:
|
|
# Startup race guard: wait briefly until capture thread publishes first frame.
|
|
if self._latest_frame is None:
|
|
deadline = time.perf_counter() + 1.0
|
|
while time.perf_counter() < deadline:
|
|
with self._latest_frame_lock:
|
|
if self._latest_frame is not None:
|
|
break
|
|
time.sleep(0.001)
|
|
|
|
# Return latest frame immediately (do not wait for next camera tick).
|
|
# This keeps end-to-end latency minimal; caller may receive repeated
|
|
# frames if processing runs faster than camera FPS.
|
|
with self._latest_frame_lock:
|
|
frame = self._latest_frame
|
|
seq = self._latest_frame_seq
|
|
if frame is not None:
|
|
self._last_consumed_seq = seq
|
|
return True, frame.copy()
|
|
return False, None
|
|
return self._read_frame_raw()
|
|
|
|
def _read_frame_raw(self):
|
|
if self._use_pyav:
|
|
if self._av_decoder is None:
|
|
return False, None
|
|
try:
|
|
frame = next(self._av_decoder)
|
|
except StopIteration:
|
|
return False, None
|
|
except Exception:
|
|
return False, None
|
|
return True, frame.to_ndarray(format="bgr24")
|
|
if self.cap is None:
|
|
return False, None
|
|
return self.cap.read()
|
|
|
|
def _start_capture_thread(self):
|
|
if self._capture_thread is not None:
|
|
return
|
|
self._capture_running = True
|
|
self._capture_thread = threading.Thread(target=self._capture_loop, daemon=True)
|
|
self._capture_thread.start()
|
|
if self.verbose:
|
|
print("Latest-frame capture thread started.")
|
|
|
|
def _capture_loop(self):
|
|
while self._capture_running:
|
|
ret, frame = self._read_frame_raw()
|
|
if not ret:
|
|
time.sleep(0.001)
|
|
continue
|
|
with self._latest_frame_lock:
|
|
self._latest_frame = frame
|
|
self._latest_frame_seq += 1
|
|
|
|
|
|
# =========================================================================
|
|
# Private - Utilities
|
|
# =========================================================================
|
|
|
|
def _print_timings(self, name, timings):
|
|
"""Print timing breakdown."""
|
|
print(f"\n[{name} timing]")
|
|
for k, v in timings.items():
|
|
if k != 'total':
|
|
print(f" {k}: {v:7.2f} ms")
|
|
print(f" ─────────────────────────")
|
|
print(f" TOTAL: {timings['total']:7.2f} ms ({1000/timings['total']:.1f} FPS)")
|
|
|