1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
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
|
import sys
import os
from os.path import join
from pathlib import Path
import cv2 as cv
import numpy as np
import imutils
import operator
from app.utils import im_utils, logger_utils
from app.models.bbox import BBox
from app.settings import app_cfg as cfg
from app.settings import types
class DetectorCVDNN:
# MobileNet SSD
dnn_scale = 0.007843 # fixed
dnn_mean = (127.5, 127.5, 127.5) # fixed
dnn_crop = False # crop or force resize
blob_size = (300, 300)
conf = 0.95
# detect
CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
"bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
"dog", "horse", "motorbike", "person", "pottedplant", "sheep",
"sofa", "train", "tvmonitor"]
def __init__(self):
self.log = logger_utils.Logger.getLogger()
fp_prototxt = join(cfg.DIR_MODELS_CAFFE, 'mobilenet_ssd', 'MobileNetSSD_deploy.prototxt')
fp_model = join(cfg.DIR_MODELS_CAFFE, 'mobilenet_ssd', 'MobileNetSSD_deploy.caffemodel')
self.net = cv.dnn.readNet(fp_prototxt, fp_model)
self.net.setPreferableBackend(cv.dnn.DNN_BACKEND_OPENCV)
self.net.setPreferableTarget(cv.dnn.DNN_TARGET_CPU)
def detect(self, im, conf=None, largest=False, pyramids=None, zone=False, blob_size=None):
"""Detects bodies and returns (list) of (BBox)"""
conf = self.conf if conf is None else conf
blob_size = self.blob_size if blob_size is None else blob_size
im = cv.resize(im, blob_size)
dim = im.shape[:2][::-1]
blob = cv.dnn.blobFromImage(im, self.dnn_scale, dim, self.dnn_mean)
self.net.setInput(blob)
net_outputs = self.net.forward()
bboxes = []
for i in range(0, net_outputs.shape[2]):
det_conf = float(net_outputs[0, 0, i, 2])
bounds = np.array(net_outputs[0, 0, i, 3:7]) # bug: ensure all x,y within 1.0 ?
if det_conf > conf and np.all(bounds < 1):
idx = int(net_outputs[0, 0, i, 1])
if self.CLASSES[idx] == "person":
rect_norm = net_outputs[0, 0, i, 3:7]
bboxes.append(BBox(*rect_norm))
if largest and len(bboxes) > 1:
# only keep largest
bboxes.sort(key=operator.attrgetter('area'), reverse=True)
bboxes = [bboxes[0]]
return bboxes
|
