Naaturel/board-mate
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Integrate detection service

Browse Source
This commit is contained in:
Laurent
2025-12-31 12:15:59 +01:00
parent 98c4aeeba1
commit 01594d02ed
6 changed files with 109 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

51
rpi/services/detection_service.py
View File

@@ -3,6 +3,7 @@ import numpy as np
from pathlib import Path
from ultralytics.engine.results import Results
from hardware.camera.camera import Camera
from models.detection.detector import Detector
from models.detection.board_manager import BoardManager
from models.detection.pieces_manager import PiecesManager
@@ -18,6 +19,8 @@ class DetectionService:
scale_size : tuple[int, int]
camera : Camera
def __init__(self):
current_file = Path(__file__).resolve()
project_root = current_file.parent.parent
@@ -28,11 +31,23 @@ class DetectionService:
self.pieces_manager = PiecesManager()
self.board_manager = BoardManager()
self.scale_size = (800, 800)
self.camera = Camera()
def start(self):
self.camera.open()
def stop(self):
self.camera.close()
def analyze_single_frame(self) -> str | None:
frame = self.camera.take_photo()
fen = self.__get_fen(frame)
return fen
def run_complete_detection(self, frame : np.ndarray, display=False) -> dict[str, list[Results]] :
pieces_prediction = self.run_pieces_detection(frame)
edges_prediction = self.run_edges_detection(frame)
def __run_complete_detection(self, frame : np.ndarray, display=False) -> dict[str, list[Results]] :
pieces_prediction = self.__run_pieces_detection(frame)
edges_prediction = self.__run_edges_detection(frame)
if display:
edges_annotated_frame = edges_prediction[0].plot()
@@ -42,22 +57,22 @@ class DetectionService:
return { "edges" : edges_prediction, "pieces" : pieces_prediction}
def run_pieces_detection(self, frame : np.ndarray, display=False) -> list[Results]:
def __run_pieces_detection(self, frame : np.ndarray, display=False) -> list[Results]:
prediction = self.pieces_detector.make_prediction(frame)
if display:
self.__display_frame(prediction[0].plot())
return prediction
def run_edges_detection(self, frame : np.ndarray, display=False) -> list[Results]:
def __run_edges_detection(self, frame : np.ndarray, display=False) -> list[Results]:
prediction = self.edges_detector.make_prediction(frame)
if display:
self.__display_frame(prediction[0].plot())
return prediction
def get_fen(self, frame : np.ndarray) -> str | None:
result = self.run_complete_detection(frame)
def __get_fen(self, frame : np.ndarray) -> str | None:
result = self.__run_complete_detection(frame)
edges_prediction = result["edges"]
pieces_prediction = result["pieces"]
@@ -75,7 +90,6 @@ class DetectionService:
return self.pieces_manager.board_to_fen(board)
def __display_frame(self, frame : np.ndarray):
cv2.namedWindow("Frame", cv2.WINDOW_NORMAL)
cv2.resizeWindow("Frame", self.scale_size[0], self.scale_size[1])
@@ -83,24 +97,3 @@ class DetectionService:
cv2.waitKey(0)
cv2.destroyAllWindows()
return
if __name__ == "__main__" :
import os
import random
service = DetectionService()
img_folder = "../training/datasets/pieces/unified/test/images/"
test_images = os.listdir(img_folder)
rnd = random.randint(0, len(test_images) - 1)
img_path = os.path.join(img_folder, test_images[rnd])
image = cv2.imread(img_path)
fen = service.get_fen(image)
print(fen)
service.run_complete_detection(image, display=True)