bbox.py

#   Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserve.
#
# 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 print_function
import os
import sys
import cv2
import random
import datetime
import time
import math
import argparse
import numpy as np
import paddle

try:
    from iou import IOU
except BaseException:
    # IOU cython speedup 10x
    def IOU(ax1, ay1, ax2, ay2, bx1, by1, bx2, by2):
        sa = abs((ax2 - ax1) * (ay2 - ay1))
        sb = abs((bx2 - bx1) * (by2 - by1))
        x1, y1 = max(ax1, bx1), max(ay1, by1)
        x2, y2 = min(ax2, bx2), min(ay2, by2)
        w = x2 - x1
        h = y2 - y1
        if w < 0 or h < 0:
            return 0.0
        else:
            return 1.0 * w * h / (sa + sb - w * h)


def bboxlog(x1, y1, x2, y2, axc, ayc, aww, ahh):
    xc, yc, ww, hh = (x2 + x1) / 2, (y2 + y1) / 2, x2 - x1, y2 - y1
    dx, dy = (xc - axc) / aww, (yc - ayc) / ahh
    dw, dh = math.log(ww / aww), math.log(hh / ahh)
    return dx, dy, dw, dh


def bboxloginv(dx, dy, dw, dh, axc, ayc, aww, ahh):
    xc, yc = dx * aww + axc, dy * ahh + ayc
    ww, hh = math.exp(dw) * aww, math.exp(dh) * ahh
    x1, x2, y1, y2 = xc - ww / 2, xc + ww / 2, yc - hh / 2, yc + hh / 2
    return x1, y1, x2, y2


def nms(dets, thresh):
    if 0 == len(dets):
        return []
    x1, y1, x2, y2, scores = dets[:, 0], dets[:, 1], dets[:,2], \
                        dets[:, 3], dets[:,4]
    areas = (x2 - x1 + 1) * (y2 - y1 + 1)
    order = scores.argsort()[::-1]

    keep = []
    while order.size > 0:
        i = order[0]
        keep.append(i)
        xx1, yy1 = np.maximum(x1[i],
                              x1[order[1:]]), np.maximum(y1[i], y1[order[1:]])
        xx2, yy2 = np.minimum(x2[i],
                              x2[order[1:]]), np.minimum(y2[i], y2[order[1:]])

        w, h = np.maximum(0.0, xx2 - xx1 + 1), np.maximum(0.0, yy2 - yy1 + 1)
        ovr = w * h / (areas[i] + areas[order[1:]] - w * h)

        inds = np.where(ovr <= thresh)[0]
        order = order[inds + 1]

    return keep


def encode(matched, priors, variances):
    """Encode the variances from the priorbox layers into the ground truth boxes
    we have matched (based on jaccard overlap) with the prior boxes.
    Args:
        matched: (tensor) Coords of ground truth for each prior in point-form
            Shape: [num_priors, 4].
        priors: (tensor) Prior boxes in center-offset form
            Shape: [num_priors,4].
        variances: (list[float]) Variances of priorboxes
    Return:
        encoded boxes (tensor), Shape: [num_priors, 4]
    """

    # dist b/t match center and prior's center
    g_cxcy = (matched[:, :2] + matched[:, 2:]) / 2 - priors[:, :2]
    # encode variance
    g_cxcy /= (variances[0] * priors[:, 2:])
    # match wh / prior wh
    g_wh = (matched[:, 2:] - matched[:, :2]) / priors[:, 2:]
    g_wh = paddle.log(g_wh) / variances[1]
    # return target for smooth_l1_loss
    return paddle.concat([g_cxcy, g_wh], 1)  # [num_priors,4]


def decode(loc, priors, variances):
    """Decode locations from predictions using priors to undo
    the encoding we did for offset regression at train time.
    Args:
        loc (tensor): location predictions for loc layers,
            Shape: [num_priors,4]
        priors (tensor): Prior boxes in center-offset form.
            Shape: [num_priors,4].
        variances: (list[float]) Variances of priorboxes
    Return:
        decoded bounding box predictions
    """

    boxes = paddle.concat(
        (priors[:, :2] + loc[:, :2] * variances[0] * priors[:, 2:],
         priors[:, 2:] * paddle.exp(loc[:, 2:] * variances[1])), 1)
    boxes[:, :2] -= boxes[:, 2:] / 2
    boxes[:, 2:] += boxes[:, :2]
    return boxes


def batch_decode(loc, priors, variances):
    """Decode locations from predictions using priors to undo
    the encoding we did for offset regression at train time.
    Args:
        loc (tensor): location predictions for loc layers,
            Shape: [num_priors,4]
        priors (tensor): Prior boxes in center-offset form.
            Shape: [num_priors,4].
        variances: (list[float]) Variances of priorboxes
    Return:
        decoded bounding box predictions
    """

    boxes = paddle.concat(
        (priors[:, :, :2] + loc[:, :, :2] * variances[0] * priors[:, :, 2:],
         priors[:, :, 2:] * paddle.exp(loc[:, :, 2:] * variances[1])), 2)
    boxes[:, :, :2] -= boxes[:, :, 2:] / 2
    boxes[:, :, 2:] += boxes[:, :, :2]
    return boxes