box_utils.py

# Copyright (c) 2019 PaddlePaddle Authors. All Rights Reserved
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.


from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from __future__ import unicode_literals

import numpy as np

import matplotlib
matplotlib.use('Agg')
from matplotlib import pyplot as plt
from PIL import Image


def coco_anno_box_to_center_relative(box, img_height, img_width):
    """
    Convert COCO annotations box with format [x1, y1, w, h] to 
    center mode [center_x, center_y, w, h] and divide image width
    and height to get relative value in range[0, 1]
    """
    assert len(box) == 4, "box should be a len(4) list or tuple"
    x, y, w, h = box

    x1 = max(x, 0)
    x2 = min(x + w - 1, img_width - 1)
    y1 = max(y, 0)
    y2 = min(y + h - 1, img_height - 1)

    x = (x1 + x2) / 2 / img_width
    y = (y1 + y2) / 2 / img_height
    w = (x2 - x1) / img_width
    h = (y2 - y1) / img_height

    return np.array([x, y, w, h])

def clip_relative_box_in_image(x, y, w, h):
    """Clip relative box coordinates x, y, w, h to [0, 1]"""
    x1 = max(x - w / 2, 0.)
    x2 = min(x + w / 2, 1.)
    y1 = min(y - h / 2, 0.)
    y2 = max(y + h / 2, 1.)
    x = (x1 + x2) / 2
    y = (y1 + y2) / 2
    w = x2 - x1
    h = y2 - y1

def box_xywh_to_xyxy(box):
    shape = box.shape
    assert shape[-1] == 4, "Box shape[-1] should be 4."

    box = box.reshape((-1, 4))
    box[:, 0], box[:, 2] = box[:, 0] - box[:, 2] / 2, box[:, 0] + box[:, 2] / 2
    box[:, 1], box[:, 3] = box[:, 1] - box[:, 3] / 2, box[:, 1] + box[:, 3] / 2
    box = box.reshape(shape)
    return box

def box_iou_xywh(box1, box2):
    assert box1.shape[-1] == 4, "Box1 shape[-1] should be 4."
    assert box2.shape[-1] == 4, "Box2 shape[-1] should be 4."

    b1_x1, b1_x2 = box1[:, 0] - box1[:, 2] / 2, box1[:, 0] + box1[:, 2] / 2
    b1_y1, b1_y2 = box1[:, 1] - box1[:, 3] / 2, box1[:, 1] + box1[:, 3] / 2
    b2_x1, b2_x2 = box2[:, 0] - box2[:, 2] / 2, box2[:, 0] + box2[:, 2] / 2
    b2_y1, b2_y2 = box2[:, 1] - box2[:, 3] / 2, box2[:, 1] + box2[:, 3] / 2

    inter_x1 = np.maximum(b1_x1, b2_x1)
    inter_x2 = np.minimum(b1_x2, b2_x2)
    inter_y1 = np.maximum(b1_y1, b2_y1)
    inter_y2 = np.minimum(b1_y2, b2_y2)
    inter_w = inter_x2 - inter_x1 + 1
    inter_h = inter_y2 - inter_y1 + 1
    inter_w[inter_w < 0] = 0
    inter_h[inter_h < 0] = 0

    inter_area = inter_w * inter_h
    b1_area = (b1_x2 - b1_x1 + 1) * (b1_y2 - b1_y1 + 1)
    b2_area = (b2_x2 - b2_x1 + 1) * (b2_y2 - b2_y1 + 1)

    return inter_area / (b1_area + b2_area - inter_area)

def box_iou_xyxy(box1, box2):
    assert box1.shape[-1] == 4, "Box1 shape[-1] should be 4."
    assert box2.shape[-1] == 4, "Box2 shape[-1] should be 4."

    b1_x1, b1_y1, b1_x2, b1_y2 = box1[:, 0], box1[:, 1], box1[:, 2], box1[:, 3]
    b2_x1, b2_y1, b2_x2, b2_y2 = box2[:, 0], box2[:, 1], box2[:, 2], box2[:, 3]

    inter_x1 = np.maximum(b1_x1, b2_x1)
    inter_x2 = np.minimum(b1_x2, b2_x2)
    inter_y1 = np.maximum(b1_y1, b2_y1)
    inter_y2 = np.minimum(b1_y2, b2_y2)
    inter_w = inter_x2 - inter_x1
    inter_h = inter_y2 - inter_y1
    inter_w[inter_w < 0] = 0
    inter_h[inter_h < 0] = 0

    inter_area = inter_w * inter_h
    b1_area = (b1_x2 - b1_x1) * (b1_y2 - b1_y1)
    b2_area = (b2_x2 - b2_x1) * (b2_y2 - b2_y1)

    return inter_area / (b1_area + b2_area - inter_area)

def box_crop(boxes, labels, scores, crop, img_shape):
    x, y, w, h = map(float, crop)
    im_w, im_h = map(float, img_shape)

    boxes = boxes.copy()
    boxes[:, 0], boxes[:, 2] = (boxes[:, 0] - boxes[:, 2] / 2) * im_w, (boxes[:, 0] + boxes[:, 2] / 2) * im_w
    boxes[:, 1], boxes[:, 3] = (boxes[:, 1] - boxes[:, 3] / 2) * im_h, (boxes[:, 1] + boxes[:, 3] / 2) * im_h

    crop_box = np.array([x, y, x + w, y + h])
    centers = (boxes[:, :2] + boxes[:, 2:]) / 2.0
    mask = np.logical_and(crop_box[:2] <= centers, centers <= crop_box[2:]).all(axis=1)

    boxes[:, :2] = np.maximum(boxes[:, :2], crop_box[:2])
    boxes[:, 2:] = np.minimum(boxes[:, 2:], crop_box[2:])
    boxes[:, :2] -= crop_box[:2]
    boxes[:, 2:] -= crop_box[:2]

    mask = np.logical_and(mask, (boxes[:, :2] < boxes[:, 2:]).all(axis=1))
    boxes = boxes * np.expand_dims(mask.astype('float32'), axis=1)
    labels = labels * mask.astype('float32')
    scores = scores * mask.astype('float32')
    boxes[:, 0], boxes[:, 2] = (boxes[:, 0] + boxes[:, 2]) / 2 / w, (boxes[:, 2] - boxes[:, 0]) / w
    boxes[:, 1], boxes[:, 3] = (boxes[:, 1] + boxes[:, 3]) / 2 / h, (boxes[:, 3] - boxes[:, 1]) / h

    return boxes, labels, scores, mask.sum()

def draw_boxes_on_image(image_path, boxes, scores, labels, label_names, score_thresh=0.5):
    image = np.array(Image.open(image_path))
    plt.figure()
    _, ax = plt.subplots(1)
    ax.imshow(image)

    image_name = image_path.split('/')[-1]
    print("Image {} detect: ".format(image_name))
    colors = {}
    for box, score, label in zip(boxes, scores, labels):
        if score < score_thresh:
            continue
        if box[2] <= box[0] or box[3] <= box[1]:
            continue
        label = int(label)
        if label not in colors:
            colors[label] = plt.get_cmap('hsv')(label / len(label_names))
        x1, y1, x2, y2 = box[0], box[1], box[2], box[3]
        rect = plt.Rectangle((x1, y1), x2 - x1, y2 - y1, 
                            fill=False, linewidth=2.0, 
                            edgecolor=colors[label])
        ax.add_patch(rect)
        ax.text(x1, y1, '{} {:.4f}'.format(label_names[label], score), 
                verticalalignment='bottom', horizontalalignment='left',
                bbox={'facecolor': colors[label], 'alpha': 0.5, 'pad': 0},
                fontsize=8, color='white')
        print("\t {:15s} at {:25} score: {:.5f}".format(label_names[int(label)], map(int, list(box)), score))
    image_name = image_name.replace('jpg', 'png')
    plt.axis('off')
    plt.gca().xaxis.set_major_locator(plt.NullLocator())
    plt.gca().yaxis.set_major_locator(plt.NullLocator())
    plt.savefig("./output/{}".format(image_name), bbox_inches='tight', pad_inches=0.0)
    print("Detect result save at ./output/{}\n".format(image_name))
    plt.cla()
    plt.close('all')