utils.py 8.0 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19
# Copyright (c) 2021 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.

import os
import cv2
import time
import paddle
import numpy as np
20
from .visualization import plot_tracking_dict
21 22

__all__ = [
23
    'MOTTimer',
24
    'Detection',
25 26
    'write_mot_results',
    'save_vis_results',
27 28 29 30 31 32 33 34
    'load_det_results',
    'preprocess_reid',
    'get_crops',
    'clip_box',
    'scale_coords',
]


35
class MOTTimer(object):
36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77
    """
    This class used to compute and print the current FPS while evaling.
    """

    def __init__(self):
        self.total_time = 0.
        self.calls = 0
        self.start_time = 0.
        self.diff = 0.
        self.average_time = 0.
        self.duration = 0.

    def tic(self):
        # using time.time instead of time.clock because time time.clock
        # does not normalize for multithreading
        self.start_time = time.time()

    def toc(self, average=True):
        self.diff = time.time() - self.start_time
        self.total_time += self.diff
        self.calls += 1
        self.average_time = self.total_time / self.calls
        if average:
            self.duration = self.average_time
        else:
            self.duration = self.diff
        return self.duration

    def clear(self):
        self.total_time = 0.
        self.calls = 0
        self.start_time = 0.
        self.diff = 0.
        self.average_time = 0.
        self.duration = 0.


class Detection(object):
    """
    This class represents a bounding box detection in a single image.

    Args:
78
        tlwh (Tensor): Bounding box in format `(top left x, top left y,
79
            width, height)`.
80
        score (Tensor): Bounding box confidence score.
81 82
        feature (Tensor): A feature vector that describes the object 
            contained in this image.
83
        cls_id (Tensor): Bounding box category id.
84 85
    """

86
    def __init__(self, tlwh, score, feature, cls_id):
87
        self.tlwh = np.asarray(tlwh, dtype=np.float32)
88 89 90
        self.score = float(score)
        self.feature = np.asarray(feature, dtype=np.float32)
        self.cls_id = int(cls_id)
91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111

    def to_tlbr(self):
        """
        Convert bounding box to format `(min x, min y, max x, max y)`, i.e.,
        `(top left, bottom right)`.
        """
        ret = self.tlwh.copy()
        ret[2:] += ret[:2]
        return ret

    def to_xyah(self):
        """
        Convert bounding box to format `(center x, center y, aspect ratio,
        height)`, where the aspect ratio is `width / height`.
        """
        ret = self.tlwh.copy()
        ret[:2] += ret[2:] / 2
        ret[2] /= ret[3]
        return ret


112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173
def write_mot_results(filename, results, data_type='mot', num_classes=1):
    # support single and multi classes
    if data_type in ['mot', 'mcmot']:
        save_format = '{frame},{id},{x1},{y1},{w},{h},{score},{cls_id},-1,-1\n'
    elif data_type == 'kitti':
        save_format = '{frame} {id} car 0 0 -10 {x1} {y1} {x2} {y2} -10 -10 -10 -1000 -1000 -1000 -10\n'
    else:
        raise ValueError(data_type)

    f = open(filename, 'w')
    for cls_id in range(num_classes):
        for frame_id, tlwhs, tscores, track_ids in results[cls_id]:
            for tlwh, score, track_id in zip(tlwhs, tscores, track_ids):
                if track_id < 0: continue
                if data_type == 'kitti':
                    frame_id -= 1
                elif data_type == 'mot':
                    cls_id = -1
                elif data_type == 'mcmot':
                    cls_id = cls_id

                x1, y1, w, h = tlwh
                line = save_format.format(
                    frame=frame_id,
                    id=track_id,
                    x1=x1,
                    y1=y1,
                    w=w,
                    h=h,
                    score=score,
                    cls_id=cls_id)
                f.write(line)
    print('MOT results save in {}'.format(filename))


def save_vis_results(data,
                     frame_id,
                     online_ids,
                     online_tlwhs,
                     online_scores,
                     average_time,
                     show_image,
                     save_dir,
                     num_classes=1):
    if show_image or save_dir is not None:
        assert 'ori_image' in data
        img0 = data['ori_image'].numpy()[0]
        online_im = plot_tracking_dict(
            img0,
            num_classes,
            online_tlwhs,
            online_ids,
            online_scores,
            frame_id=frame_id,
            fps=1. / average_time)
    if show_image:
        cv2.imshow('online_im', online_im)
    if save_dir is not None:
        cv2.imwrite(
            os.path.join(save_dir, '{:05d}.jpg'.format(frame_id)), online_im)


174 175
def load_det_results(det_file, num_frames):
    assert os.path.exists(det_file) and os.path.isfile(det_file), \
176
        '{} is not exist or not a file.'.format(det_file)
177
    labels = np.loadtxt(det_file, dtype='float32', delimiter=',')
178 179
    assert labels.shape[1] == 7, \
        "Each line of {} should have 7 items: '[frame_id],[x0],[y0],[w],[h],[score],[class_id]'.".format(det_file)
180
    results_list = []
181 182
    for frame_i in range(num_frames):
        results = {'bbox': [], 'score': [], 'cls_id': []}
183
        lables_with_frame = labels[labels[:, 0] == frame_i + 1]
184 185
        # each line of lables_with_frame:
        # [frame_id],[x0],[y0],[w],[h],[score],[class_id]
186
        for l in lables_with_frame:
187 188
            results['bbox'].append(l[1:5])
            results['score'].append(l[5])
189
            results['cls_id'].append(l[6])
190 191 192 193 194 195
        results_list.append(results)
    return results_list


def scale_coords(coords, input_shape, im_shape, scale_factor):
    im_shape = im_shape.numpy()[0]
196 197 198 199
    ratio = scale_factor[0][0]
    pad_w = (input_shape[1] - int(im_shape[1])) / 2
    pad_h = (input_shape[0] - int(im_shape[0])) / 2
    coords = paddle.cast(coords, 'float32')
200 201
    coords[:, 0::2] -= pad_w
    coords[:, 1::2] -= pad_h
202
    coords[:, 0:4] /= ratio
203 204 205 206 207 208 209 210 211 212 213
    coords[:, :4] = paddle.clip(coords[:, :4], min=0, max=coords[:, :4].max())
    return coords.round()


def clip_box(xyxy, input_shape, im_shape, scale_factor):
    im_shape = im_shape.numpy()[0]
    ratio = scale_factor.numpy()[0][0]
    img0_shape = [int(im_shape[0] / ratio), int(im_shape[1] / ratio)]

    xyxy[:, 0::2] = paddle.clip(xyxy[:, 0::2], min=0, max=img0_shape[1])
    xyxy[:, 1::2] = paddle.clip(xyxy[:, 1::2], min=0, max=img0_shape[0])
214 215 216 217 218 219
    w = xyxy[:, 2:3] - xyxy[:, 0:1]
    h = xyxy[:, 3:4] - xyxy[:, 1:2]
    mask = paddle.logical_and(h > 0, w > 0)
    keep_idx = paddle.nonzero(mask)
    xyxy = paddle.gather_nd(xyxy, keep_idx[:, :1])
    return xyxy, keep_idx
220 221


222
def get_crops(xyxy, ori_img, w, h):
223 224 225 226 227 228 229 230
    crops = []
    xyxy = xyxy.numpy().astype(np.int64)
    ori_img = ori_img.numpy()
    ori_img = np.squeeze(ori_img, axis=0).transpose(1, 0, 2)
    for i, bbox in enumerate(xyxy):
        crop = ori_img[bbox[0]:bbox[2], bbox[1]:bbox[3], :]
        crops.append(crop)
    crops = preprocess_reid(crops, w, h)
231
    return crops
232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250


def preprocess_reid(imgs,
                    w=64,
                    h=192,
                    mean=[0.485, 0.456, 0.406],
                    std=[0.229, 0.224, 0.225]):
    im_batch = []
    for img in imgs:
        img = cv2.resize(img, (w, h))
        img = img[:, :, ::-1].astype('float32').transpose((2, 0, 1)) / 255
        img_mean = np.array(mean).reshape((3, 1, 1))
        img_std = np.array(std).reshape((3, 1, 1))
        img -= img_mean
        img /= img_std
        img = np.expand_dims(img, axis=0)
        im_batch.append(img)
    im_batch = np.concatenate(im_batch, 0)
    return im_batch