box_utils.py

# Copyright (c) 2018 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.
#
# Based on:
# --------------------------------------------------------
# Detectron
# Copyright (c) 2017-present, Facebook, Inc.
# Licensed under the Apache License, Version 2.0;
# Written by Ross Girshick
# --------------------------------------------------------

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

import numpy as np


def xywh_to_xyxy(xywh):
    """Convert [x1 y1 w h] box format to [x1 y1 x2 y2] format."""
    if isinstance(xywh, (list, tuple)):
        # Single box given as a list of coordinates
        assert len(xywh) == 4
        x1, y1 = xywh[0], xywh[1]
        x2 = x1 + np.maximum(0., xywh[2] - 1.)
        y2 = y1 + np.maximum(0., xywh[3] - 1.)
        return (x1, y1, x2, y2)
    elif isinstance(xywh, np.ndarray):
        # Multiple boxes given as a 2D ndarray
        return np.hstack(
            (xywh[:, 0:2], xywh[:, 0:2] + np.maximum(0, xywh[:, 2:4] - 1)))
    else:
        raise TypeError('Argument xywh must be a list, tuple, or numpy array.')


def xyxy_to_xywh(xyxy):
    """Convert [x1 y1 x2 y2] box format to [x1 y1 w h] format."""
    if isinstance(xyxy, (list, tuple)):
        # Single box given as a list of coordinates
        assert len(xyxy) == 4
        x1, y1 = xyxy[0], xyxy[1]
        w = xyxy[2] - x1 + 1
        h = xyxy[3] - y1 + 1
        return (x1, y1, w, h)
    elif isinstance(xyxy, np.ndarray):
        # Multiple boxes given as a 2D ndarray
        return np.hstack((xyxy[:, 0:2], xyxy[:, 2:4] - xyxy[:, 0:2] + 1))
    else:
        raise TypeError('Argument xyxy must be a list, tuple, or numpy array.')


def clip_xyxy_to_image(x1, y1, x2, y2, height, width):
    """Clip coordinates to an image with the given height and width."""
    x1 = np.minimum(width - 1., np.maximum(0., x1))
    y1 = np.minimum(height - 1., np.maximum(0., y1))
    x2 = np.minimum(width - 1., np.maximum(0., x2))
    y2 = np.minimum(height - 1., np.maximum(0., y2))
    return x1, y1, x2, y2

def nms(dets, thresh):
    """Apply classic DPM-style greedy NMS."""
    if dets.shape[0] == 0:
        return []
    x1 = dets[:, 0]
    y1 = dets[:, 1]
    x2 = dets[:, 2]
    y2 = dets[:, 3]
    scores = dets[:, 4]

    areas = (x2 - x1 + 1) * (y2 - y1 + 1)
    order = scores.argsort()[::-1]

    ndets = dets.shape[0]
    suppressed = np.zeros((ndets), dtype=np.int)

    # nominal indices
    # _i, _j
    # sorted indices
    # i, j
    # temp variables for box i's (the box currently under consideration)
    # ix1, iy1, ix2, iy2, iarea

    # variables for computing overlap with box j (lower scoring box)
    # xx1, yy1, xx2, yy2
    # w, h
    # inter, ovr

    for _i in range(ndets):
        i = order[_i]
        if suppressed[i] == 1:
            continue
        ix1 = x1[i]
        iy1 = y1[i]
        ix2 = x2[i]
        iy2 = y2[i]
        iarea = areas[i]
        for _j in range(_i + 1, ndets):
            j = order[_j]
            if suppressed[j] == 1:
                continue
            xx1 = max(ix1, x1[j])
            yy1 = max(iy1, y1[j])
            xx2 = min(ix2, x2[j])
            yy2 = min(iy2, y2[j])
            w = max(0.0, xx2 - xx1 + 1)
            h = max(0.0, yy2 - yy1 + 1)
            inter = w * h
            ovr = inter / (iarea + areas[j] - inter)
            if ovr >= thresh:
                suppressed[j] = 1

    return np.where(suppressed == 0)[0]