控制邊框邊界溢出代碼與NMS代碼

def _load_pascal_annotation(self, index):

	 #Load image and bounding boxes info from XML file in the PASCAL VOC format  
	 #翻譯：以PASCAL VOC格式從XML文件中加載圖像和邊框信息
	 
     filename = os.path.join(self._data_path, 'Annotations', index + '.xml')
     tree = ET.parse(filename)
     objs = tree.findall('object')
     size = tree.find('size')
     width = size.find('width').text
     height = size.find('height').text
     print(width, height)
     num_objs = len(objs)

     boxes = np.zeros((num_objs, 4), dtype=np.unit16)
     gt_classes = np.zeros((num_objs), dtype=np.int32)
     overlaps = np.zeros((num_objs, self.num_classes), dtype=np.float32)
     
     # "Seg" area for pascal is just the box area   翻譯：pascal的“Seg”區域就是方框區域
     seg_areas = np.zeros((num_objs), dtype=np.float32)

     # Load object bounding boxes into a data frame   翻譯：將對象包圍框加載到數據幀中
     for ix, obj in enumerate(objs):

          clsname = obj.find('name').text.lower().strip()
          bbox = obj.find('bndbox')
          
          # Make pixel indexes 0-based   翻譯：使像素索引基於0
          x1 = max(float(bbox.find('xmin').text - 1), 0)
          y1 = max(float(bbox.find('ymin').text - 1), 0)
          x2 = min(float(bbox.find('xmax').text), float(width))
          y2 = min(float(bbox.find('ymax').text), float(height))

          if x1 > x2: x1 = x2
          if y1 > y2: y1 = y2

          cls = self._classes_to_ind[clsname]
          boxes[ix, :] = [x1, y1, x2, y2]
          seg_areas[ix] = (x2 - x1 + 1) * (y2 - y1 + 1)
          gt_classes[ix] = cls
          overlaps[ix, cls] = 1.0

NMS

#!/usr/bin/env python
# _*_ coding: utf-8 _*_
import cv2
import numpy as np
"""
    Non-max Suppression Algorithm
    @param list  Object candidate bounding boxes
    @param list  Confidence score of bounding boxes
    @param float IoU threshold
    @return Rest boxes after nms operation
"""
# 首先選定一個IOU閾值，例如爲0.4。然後將所有3個窗口（bounding box）
# 按照得分由高到低排序。然後選中得分最高的窗口，
# 遍歷計算剩餘的2個窗口與該窗口的重疊面積比例（IOU），
# 如果IOU大於閾值0.4,則將窗口刪除。然後，
# 再從剩餘的窗口中選中一個得分最高的，
# 重複上述過程。直至所有窗口都被處理。

def nms(bounding_boxes, confidence_score, threshold):
    # If no bounding boxes, return empty list  如果沒有bbox,則返回空列表
    if len(bounding_boxes) == 0:
        return [], []

    # Bounding boxes 將所有3個窗口（bounding box）按照得分由高到低排序
    boxes = np.array(bounding_boxes)

    # coordinates of bounding boxes
    start_x = boxes[:, 0]
    start_y = boxes[:, 1]
    end_x = boxes[:, 2]
    end_y = boxes[:, 3]

    # Confidence scores of bounding boxes
    score = np.array(confidence_score)

    # Picked bounding boxes
    picked_boxes = []
    picked_score = []

    # Compute areas of bounding boxes
    areas = (end_x - start_x + 1) * (end_y - start_y + 1)

    # Sort by confidence score of bounding boxes
    order = np.argsort(score)

    # Iterate bounding boxes
    while order.size > 0:
        # The index of largest confidence score
        index = order[-1]

        # Pick the bounding box with largest confidence score
        picked_boxes.append(bounding_boxes[index])
        picked_score.append(confidence_score[index])
        # a=start_x[index]
        # b=order[:-1]
        # c=start_x[order[:-1]]
        # Compute ordinates of intersection-over-union(IOU)
        x1 = np.maximum(start_x[index], start_x[order[:-1]])
        x2 = np.minimum(end_x[index], end_x[order[:-1]])
        y1 = np.maximum(start_y[index], start_y[order[:-1]])
        y2 = np.minimum(end_y[index], end_y[order[:-1]])

        # Compute areas of intersection-over-union
        w = np.maximum(0.0, x2 - x1 + 1)
        h = np.maximum(0.0, y2 - y1 + 1)
        intersection = w * h
        print("------w------")
        print(w)
        print("------h------")
        print(h)

        # Compute the ratio between intersection and union
        ratio = intersection / (areas[index] + areas[order[:-1]] - intersection)
        print("----ratio-----")
        print(ratio)

        left = np.where(ratio < threshold)
        print("-----left------")
        print(left)
        order = order[left]

    return picked_boxes, picked_score


# Image name
image_name = 'nms.jpg'

# Bounding boxes
bounding_boxes = [(187, 82, 337, 317), (150, 67, 305, 282), (246, 121, 368, 304)]
confidence_score = [0.9, 0.75, 0.8]

# Read image
image = cv2.imread(image_name)

# Copy image as original
org = image.copy()

# Draw parameters
font = cv2.FONT_HERSHEY_SIMPLEX
font_scale = 1
thickness = 2

# IoU threshold
threshold = 0.4

# Draw bounding boxes and confidence score
for (start_x, start_y, end_x, end_y), confidence in zip(bounding_boxes, confidence_score):
    (w, h), baseline = cv2.getTextSize(str(confidence), font, font_scale, thickness)
    cv2.rectangle(org, (start_x, start_y - (2 * baseline + 5)), (start_x + w, start_y), (0, 255, 255), -1)
    cv2.rectangle(org, (start_x, start_y), (end_x, end_y), (0, 255, 255), 2)
    cv2.putText(org, str(confidence), (start_x, start_y), font, font_scale, (0, 0, 0), thickness)

# Run non-max suppression algorithm
picked_boxes, picked_score = nms(bounding_boxes, confidence_score, threshold)

# Draw bounding boxes and confidence score after non-maximum supression
for (start_x, start_y, end_x, end_y), confidence in zip(picked_boxes, picked_score):
    (w, h), baseline = cv2.getTextSize(str(confidence), font, font_scale, thickness)
    cv2.rectangle(image, (start_x, start_y - (2 * baseline + 5)), (start_x + w, start_y), (0, 255, 255), -1)
    cv2.rectangle(image, (start_x, start_y), (end_x, end_y), (0, 255, 255), 2)
    cv2.putText(image, str(confidence), (start_x, start_y), font, font_scale, (0, 0, 0), thickness)

# Show image
cv2.imshow('Original', org)
cv2.imshow('NMS', image)
cv2.waitKey(0)

圖片：

結果：