* docs

* docs

* docs

* docs

* fix box merging logic

* always run paddleocr models on cpu

* docs clarity

* fix docs

* docs
This commit is contained in:
Josh Hawkins
2025-04-07 15:25:46 -05:00
committed by GitHub
parent f2840468b4
commit cb27bdb2f7
3 changed files with 29 additions and 13 deletions

View File

@@ -309,7 +309,11 @@ class LicensePlateProcessingMixin:
return image.transpose((2, 0, 1))[np.newaxis, ...]
def _merge_nearby_boxes(
self, boxes: List[np.ndarray], plate_width: float, gap_fraction: float = 0.1
self,
boxes: List[np.ndarray],
plate_width: float,
gap_fraction: float = 0.1,
min_overlap_fraction: float = -0.2,
) -> List[np.ndarray]:
"""
Merge bounding boxes that are likely part of the same license plate based on proximity,
@@ -329,6 +333,7 @@ class LicensePlateProcessingMixin:
return []
max_gap = plate_width * gap_fraction
min_overlap = plate_width * min_overlap_fraction
# Sort boxes by top left x
sorted_boxes = sorted(boxes, key=lambda x: x[0][0])
@@ -353,9 +358,10 @@ class LicensePlateProcessingMixin:
next_bottom = np.max(next_box[:, 1])
# Consider boxes part of the same plate if they are close horizontally or overlap
if horizontal_gap <= max_gap and max(current_top, next_top) <= min(
current_bottom, next_bottom
):
# within the allowed limit and their vertical positions overlap significantly
if min_overlap <= horizontal_gap <= max_gap and max(
current_top, next_top
) <= min(current_bottom, next_bottom):
merged_points = np.vstack((current_box, next_box))
new_box = np.array(
[
@@ -379,7 +385,7 @@ class LicensePlateProcessingMixin:
)
current_box = new_box
else:
# If the boxes are not close enough, add the current box to the result
# If the boxes are not close enough or overlap too much, add the current box to the result
merged_boxes.append(current_box)
current_box = next_box

View File

@@ -12,13 +12,13 @@ class LicensePlateModelRunner(DataProcessorModelRunner):
def __init__(self, requestor, device: str = "CPU", model_size: str = "large"):
super().__init__(requestor, device, model_size)
self.detection_model = PaddleOCRDetection(
model_size=model_size, requestor=requestor, device=device
model_size=model_size, requestor=requestor, device="CPU"
)
self.classification_model = PaddleOCRClassification(
model_size=model_size, requestor=requestor, device=device
model_size=model_size, requestor=requestor, device="CPU"
)
self.recognition_model = PaddleOCRRecognition(
model_size=model_size, requestor=requestor, device=device
model_size=model_size, requestor=requestor, device="CPU"
)
self.yolov9_detection_model = LicensePlateDetector(
model_size=model_size, requestor=requestor, device=device