『Python』图像金字塔、滑动窗口和非极大值抑制实现
图像金字塔
1.在从cv2.resize中,传入参数时先列后行的
2.使用了python中的生成器,调用时使用for i in pyramid即可
3.scaleFactor是缩放因子,需要保证缩放后的图不小于最小尺寸,对应神经网络就是训练尺寸
'''图像金字塔''' def resize(img, scaleFactor): # cv2.resize先接收列后接收行,返回亦然 return cv2.resize(img, (int(img.shape[1] * (1/scaleFactor)), int(img.shape[0] * (1/scaleFactor))), interpolation=cv2.INTER_AREA) def pyramid(image, scale=1.5, minSize = (200, 80)): yield image while True: image = resize(image, scale) if image.shape[0] < minSize[1] or image.shape[1] < minSize[0]: break yield image
滑动窗口
'''滑动窗口''' def sliding_window(image, stepSize, windowSize): for y in range(0, image.shape[0], stepSize): for x in range(0, image.shape[1], stepSize): yield(x, y, image[y:y+windowSize[1], x:x+windowSize[0]])
非极大值抑制
'''非极大值抑制''' def non_max_suppression_fast(boxes, overlapThresh): # 如果没有box,返回空list if len(boxes) == 0: return [] # 修改boxes的格式为float方便处理 if boxes.dtype.kind == 'i': boxes = boxes.astype('float') # 使用pick收集boxes pick = [] x1 = boxes[:, 0] y1 = boxes[:, 1] x2 = boxes[:, 2] y2 = boxes[:, 3] scores = boxes[:, 4] area = (x2 - x1 + 1) * (y2 - y1 + 1) # 按照score从小到大的顺序排序indexes idxs = np.argsort(scores)[::-1] while len(idxs) > 0: # 分配最后一个(得分最高)index给i,并使用pick收集这个index(即i) last = len(idxs) - 1 i = idxs[last] pick.append(i) # 在得分大于当前i的boxes中, # 找到重合部分的左上点和右下点 xx1 = np.maximum(x1[i], x1[idxs[:last]]) yy1 = np.maximum(y1[i], y1[idxs[:last]]) xx2 = np.minimum(x2[i], x2[idxs[:last]]) yy2 = np.minimum(y2[i], y2[idxs[:last]]) # 计算上面得到的重合面积 w = np.maximum(0, xx2 - xx1 + 1) h = np.maximum(0, yy2 - yy1 + 1) # 计算重合度 overlap = (w * h) / area[idxs[:last]] # 删除得分最高的项(循环开始已经收集了), # 删除 idxs = np.delete(idxs, np.concatenate(([last], np.where(overlap > overlapThresh)))) # [0]))) # 加上索引之后只删除一个得分最高的过重合矩形,所以不应该加索引 return boxes[pick].astype('int')