AIlib2/DMPRUtils/jointUtil.py

import math

import numpy as np
import torch
import time


def dmpr_yolo( yolo_det, dmpr_det,pars):
    #if len(yolo_det)==0 or len(dmpr_det)==0:

    #print('line11:\n',yolo_det, dmpr_det,pars)
    time1=time.time()
    if len(yolo_det)==0:
        return yolo_det,' No yolo detections'
        
    img_shape = (pars['imgSize'][1],pars['imgSize'][0])
    cls = pars['carCls']; scaleRatio = pars['scaleRatio']
    illParkCls = pars['illCls'];border = pars['border']    
    
    yolo_det = np.array(yolo_det)
    yolo_det_0 = yolo_det.copy()

    
    
    
    #print('-'*10,'line17：',yolo_det_0)

    # 过滤在图像边界的box(防止出现类似一小半车辆的情况)
     
    x_c = (yolo_det[:, 0] + yolo_det[:, 2]) / 2
    y_c = (yolo_det[:, 1] + yolo_det[:, 3]) / 2
    tmp = (x_c >= border) & (x_c <= (img_shape[1] - border)) & (y_c >= border) & (y_c <= (img_shape[0] - border))
    yolo_det = yolo_det[tmp]
    

    # 创建yolo_det_clone内容为x1, y1, x2, y2, conf, cls, unlabel (unlabel代表该类是否需要忽略，0：不忽略 其他：忽略)
    yolo_det_clone = yolo_det.copy()
    tmp_0_tensor = np.zeros([len(yolo_det), 1])
    yolo_det_clone = np.concatenate([yolo_det_clone, tmp_0_tensor], axis=1)

    # cls为需要计算的类别
    yolo_det = yolo_det[yolo_det[:, -1] == cls]

    # new_yolo_det为膨胀后数据，内容为x1, y1, x2, y2, flag (flag代表膨胀后车位内是否包含角点 且 与角点方向差值小于90度, 其值为第一个满足条件的角点索引)
    new_yolo_det = np.zeros([len(yolo_det), 7])

    # yolo框膨胀，长的边两边各膨胀0.4倍总长，短的边两边各膨胀0.2倍总长
    x_length = yolo_det[:, 2] - yolo_det[:, 0]      #x2-x1
    y_length = yolo_det[:, 3] - yolo_det[:, 1]     #y2-y1

    # x, y哪个方向差值大哪个方向膨胀的多
    x_dilate_coefficient = ((x_length > y_length) + 1)*scaleRatio
    y_dilate_coefficient = ((~(x_length > y_length)) + 1)*scaleRatio

    # 原始框中心点x_c, y_c
    new_yolo_det[:, 5] = (yolo_det[:, 0] + yolo_det[:, 2]) / 2
    new_yolo_det[:, 6] = (yolo_det[:, 1] + yolo_det[:, 3]) / 2

    # 膨胀
    new_yolo_det[:, 0] = np.round(yolo_det[:, 0] - x_dilate_coefficient * x_length).clip(0, img_shape[1])   #x1 膨胀
    new_yolo_det[:, 1] = np.round(yolo_det[:, 1] - y_dilate_coefficient * y_length).clip(0, img_shape[0])   #y1 膨胀
    new_yolo_det[:, 2] = np.round(yolo_det[:, 2] + x_dilate_coefficient * x_length).clip(0, img_shape[1])   #x2 膨胀
    new_yolo_det[:, 3] = np.round(yolo_det[:, 3] + y_dilate_coefficient * y_length).clip(0, img_shape[0])   #y2 膨胀
    
    m, n = new_yolo_det.size, dmpr_det.size
   
    if not m or not n:
        #print('##line47 original yolo_det_clone:',yolo_det_clone)
        yolo_det_clone[np.logical_and( yolo_det_clone[:,-1]==0,yolo_det_clone[:,-2]==cls),-2] = illParkCls
         
        #yolo_det_clone[yolo_det_clone[:, -1] == 0 & yolo_det_clone[:, -2==cls] , -2] = illParkCls
        return yolo_det_clone[:,0:6], ' no cars or T/L corners'

    new_yolo = new_yolo_det[:, np.newaxis, :].repeat(dmpr_det.shape[0], 1)      # 扩展为 (m , n, 5)
    dmpr_det = dmpr_det[np.newaxis, ...].repeat(new_yolo_det.shape[0], 0)
    yolo_dmpr = np.concatenate((new_yolo, dmpr_det), axis=2)                    #  (m, n, 10)

    x_p, y_p = yolo_dmpr[..., 8], yolo_dmpr[..., 9]
    x1, y1, x2, y2 = yolo_dmpr[..., 0], yolo_dmpr[..., 1], yolo_dmpr[..., 2], yolo_dmpr[..., 3]
    x_c, y_c = yolo_dmpr[..., 5], yolo_dmpr[..., 6]

    direction1 = np.arctan2(y_c - y_p, x_c - x_p) / math.pi * 180
    direction2 = yolo_dmpr[..., 10] / math.pi * 180
    direction3 = direction2 + 90                    # L形角点另外一个方向
    direction3[direction3 > 180] -= 360
    ang_diff = direction1 - direction2
    ang_diff2 = direction1 - direction3

    # 判断膨胀后yolo框包含角点关系 && 包含角点的时候计算水平框中心点与角点的角度关系
    # direction ∈ （-180， 180） 若角差大于180，需算补角
    # T形角点比较一个方向，L形角点比较两个方向
    mask = (x_p >= x1) & (x_p <= x2) & (y_p >= y1) & (y_p <= y2) & \
           (((yolo_dmpr[..., 11] <= 0.5) &                          # T形角点情况
                (((ang_diff >= -90) & (ang_diff <= 90)) | ((ang_diff > 180) & ((360 - ang_diff) <= 90)) |
                    (((ang_diff) < -180) & ((360 + ang_diff) <= 90)))) |
            ((yolo_dmpr[..., 11] > 0.5) &                            # L形角点情况
                (((ang_diff >= -90) & (ang_diff <= 90)) | ((ang_diff > 180) & ((360 - ang_diff) <= 90)) |
                    (((ang_diff) < -180) & ((360 + ang_diff) <= 90))) &
                (((ang_diff2 >= -90) & (ang_diff2 <= 90)) | ((ang_diff2 > 180) & ((360 - ang_diff2) <= 90)) |
                    (((ang_diff2) < -180) & ((360 + ang_diff2) <= 90)))))

    res = np.sum(mask, axis=1)

    yolo_det_clone[yolo_det_clone[:, -2] == cls, -1] = res
    #print('##line69 original yolo_det_clone:',yolo_det_clone)
    #yolo_det_clone[yolo_det_clone[:, -1] == 0, -2] = illParkCls
    
    #print('-'*20,'--line78',yolo_det_clone)
    yolo_det_clone[  np.logical_and( yolo_det_clone[:,-1]==0,yolo_det_clone[:,-2]==cls) ,-2 ] = illParkCls
    #print('-'*20,'--line80:',yolo_det_clone)
    yolo_det_clone = yolo_det_clone[:,0:6]
    time2=time.time()
    
    return np.array(yolo_det_clone), 'dmpr_yolo:%.1f'%( (time2-time1)*1000 )
def stdc_yolo(stdc_det, yolo_det):
    im = np.uint8(stdc_det)
    x_c = ((yolo_det[:, 0] + yolo_det[:, 2]) // 2).astype(int)
    y_c = ((yolo_det[:, 1] + yolo_det[:, 3]) // 2).astype(int)

    yolo_filted = yolo_det[im[y_c, x_c] == 0]

    return yolo_filted
    
def dmpr_yolo_stdc(predsList,pars):
    if len(predsList)==2:
        yolo_det, dmpr_det = predsList[0:2]
    else:    
        yolo_det, dmpr_det,stdc_det = predsList[0:3]
    if len(yolo_det)==0:
        return  yolo_det,' No yolo detections'
    if isinstance(yolo_det,list):
        yolo_det = np.array(yolo_det)
    if   len(predsList)>2:  
        yolo_det = stdc_yolo(stdc_det, yolo_det)
    return dmpr_yolo(yolo_det, dmpr_det,pars)