文章目录
- 准备
- 1 处理单张图片
- 2 视频格式
- 3. rtsp码流格式
准备
project 下载
git clone https://github.com/pjreddie/darknet
cd darknet
#下载模型文件，大概200+M ，复制到 darknet 文件夹下
wget https://pjreddie.com/media/files/yolov3.weights
./darknet detect cfg/yolov3.cfg yolov3.weights data/dog.jpg #默认使用第1块GPU
./darknet -nogpu detect cfg/yolov3.cfg yolov3.weights data/dog.jpg #-nogpu:不使用GPU
#在darknet文件夹下的predictions.jpg即是检测后的结果1 处理单张图片
目标:指定一张图片的路径，指定检测生成的新图片的存放路径，进行 model检测+画框+另存为新图片.
from ctypes import *
import math
import random
import cv2
import os
def sample(probs):
s = sum(probs)
probs = [a / s for a in probs]
r = random.uniform(0, 1)
for i in range(len(probs)):
r = r - probs[i]
if r <= 0:
return i
return len(probs) - 1
def c_array(ctype, values):
arr = (ctype * len(values))()
arr[:] = values
return arr
class BOX(Structure):
_fields_ = [("x", c_float),
("y", c_float),
("w", c_float),
("h", c_float)]
class DETECTION(Structure):
_fields_ = [("bbox", BOX),
("classes", c_int),
("prob", POINTER(c_float)),
("mask", POINTER(c_float)),
("objectness", c_float),
("sort_class", c_int)]
class IMAGE(Structure):
_fields_ = [("w", c_int),
("h", c_int),
("c", c_int),
("data", POINTER(c_float))]
class METADATA(Structure):
_fields_ = [("classes", c_int),
("names", POINTER(c_char_p))]
lib = CDLL("/home/xxx/darknet/libdarknet.so", RTLD_GLOBAL)
# lib = CDLL("libdarknet.so", RTLD_GLOBAL)
lib.network_width.argtypes = [c_void_p]
lib.network_width.restype = c_int
lib.network_height.argtypes = [c_void_p]
lib.network_height.restype = c_int
predict = lib.network_predict
predict.argtypes = [c_void_p, POINTER(c_float)]
predict.restype = POINTER(c_float)
set_gpu = lib.cuda_set_device
set_gpu.argtypes = [c_int]
make_image = lib.make_image
make_image.argtypes = [c_int, c_int, c_int]
make_image.restype = IMAGE
get_network_boxes = lib.get_network_boxes
get_network_boxes.argtypes = [c_void_p, c_int, c_int, c_float, c_float, POINTER(c_int), c_int, POINTER(c_int)]
get_network_boxes.restype = POINTER(DETECTION)
make_network_boxes = lib.make_network_boxes
make_network_boxes.argtypes = [c_void_p]
make_network_boxes.restype = POINTER(DETECTION)
free_detections = lib.free_detections
free_detections.argtypes = [POINTER(DETECTION), c_int]
free_ptrs = lib.free_ptrs
free_ptrs.argtypes = [POINTER(c_void_p), c_int]
network_predict = lib.network_predict
network_predict.argtypes = [c_void_p, POINTER(c_float)]
reset_rnn = lib.reset_rnn
reset_rnn.argtypes = [c_void_p]
load_net = lib.load_network
load_net.argtypes = [c_char_p, c_char_p, c_int]
load_net.restype = c_void_p
do_nms_obj = lib.do_nms_obj
do_nms_obj.argtypes = [POINTER(DETECTION), c_int, c_int, c_float]
do_nms_sort = lib.do_nms_sort
do_nms_sort.argtypes = [POINTER(DETECTION), c_int, c_int, c_float]
free_image = lib.free_image
free_image.argtypes = [IMAGE]
letterbox_image = lib.letterbox_image
letterbox_image.argtypes = [IMAGE, c_int, c_int]
letterbox_image.restype = IMAGE
load_meta = lib.get_metadata
lib.get_metadata.argtypes = [c_char_p]
lib.get_metadata.restype = METADATA
load_image = lib.load_image_color
load_image.argtypes = [c_char_p, c_int, c_int]
load_image.restype = IMAGE
rgbgr_image = lib.rgbgr_image
rgbgr_image.argtypes = [IMAGE]
predict_image = lib.network_predict_image
predict_image.argtypes = [c_void_p, IMAGE]
predict_image.restype = POINTER(c_float)
# net_d = load_net(b"../cfg/yolov3.cfg", b"../yolov3.weights", 0)
# meta_d = load_meta(b"../cfg/coco.data")
def classify(net, meta, im):
out = predict_image(net, im)
res = []
for i in range(meta.classes):
res.append((meta.names[i], out[i]))
res = sorted(res, key=lambda x: -x[1])
return res
def detect(net, meta, image, thresh=.5, hier_thresh=.5, nms=.45):
im = load_image(image, 0, 0)
num = c_int(0)
pnum = pointer(num)
predict_image(net, im)
dets = get_network_boxes(net, im.w, im.h, thresh, hier_thresh, None, 0, pnum)
num = pnum[0]
if (nms): do_nms_obj(dets, num, meta.classes, nms);
res = []
for j in range(num):
for i in range(meta.classes):
if dets[j].prob[i] > 0:
b = dets[j].bbox
res.append((meta.names[i], dets[j].prob[i], (b.x, b.y, b.w, b.h)))
res = sorted(res, key=lambda x: -x[1])
free_image(im)
free_detections(dets, num)
return res
def detect_and_boxing(net, meta, b_path, raw_path, save_path,
color=(0.255, 255), line_type=1):
image = cv2.imread(raw_path)
r = detect(net, meta, b_path)
if not len(r) > 0:
print("nothing detected in this picture!")
else:
for i in range(len(r)):
box_i = r[i]
label_i = box_i[0]
prob_i = box_i[1]
x_ = box_i[2][0]
y_ = box_i[2][1]
w_ = box_i[2][2]
h_ = box_i[2][3]
text_ = str(label_i) + "," + str(round(prob_i, 3))
cv2.rectangle(image, (int(x_ - w_ / 2), int(y_ - h_ / 2)),
(int(x_ + w_ / 2), int(y_ + h_ / 2)),
color, line_type)
cv2.putText(image, text_, (int(x_ - w_ / 2 - 5), int(y_ - h_ / 2 - 5)), cv2.FONT_HERSHEY_DUPLEX, 0.7, color,
2)
cv2.imwrite(save_path, image)
print("boxing ", i, " found ", label_i, "with prob = ", prob_i, ", finished!")
print("box position is :", box_i[2])
if __name__ == "__main__":
# net = load_net("cfg/densenet201.cfg", "/home/pjreddie/trained/densenet201.weights", 0)
# im = load_image("data/wolf.jpg", 0, 0)
# meta = load_meta("cfg/imagenet1k.data")
# r = classify(net, meta, im)
# print(r)
net = load_net(b"/home/xxx/darknet/cfg/yolov3.cfg", b"/home/xxx/darknet/yolov3.weights", 0)
meta = load_meta(b"/home/xxx/darknet/cfg/coco.data")
b_path = b"/home/xxx/darknet/data/dog.jpg"
raw_path = "/home/xxx/darknet/data/dog.jpg"
save_path = "/home/xxx/darknet/predictdemo.jpg"
detect_and_boxing(net, meta, b_path=b_path, raw_path=raw_path, save_path=save_path)核心改动处 ：
# lib = CDLL("libdarknet.so", RTLD_GLOBAL) , 改成自己的项目的具体地址
使用 cv2.rectangle 画框框， 使用cv2.putText 放文字，为了避免框框和文字交叉，我加了一丢丢的偏移量。其中 yolov3的输出是 ：
label_i = box_i[0] #标签
prob_i = box_i[1] #标签置信度
x_ = box_i[2][0]
y_ = box_i[2][1]
w_ = box_i[2][2]
h_ = box_i[2][3] # bbox信息(x,y,w,h)为物体的中心位置相对格子位置的偏移及宽度和高度,
cv2.rectangle(image, (int(x_ - w_ / 2), int(y_ - h_ / 2)),
(int(x_ + w_ / 2), int(y_ + h_ / 2)),
color, line_type)
cv2.putText(image, text_, (int(x_ - w_ / 2 - 5), int(y_ - h_ / 2 - 5)), cv2.FONT_HERSHEY_DUPLEX, 0.7, color,
2)
2 视频格式
目的:指定原视频的路径，指定新視頻和中间产生的临时帧的存放位置，进行 帧获取+ model检测+画框+另存为新帧
原作者将生成的图片重新生成视频格式, 我建议采用其他方式比如opencv 或者ffmpage.
from ctypes import *
import math
import random
import cv2
import os
def sample(probs):
s = sum(probs)
probs = [a / s for a in probs]
r = random.uniform(0, 1)
for i in range(len(probs)):
r = r - probs[i]
if r <= 0:
return i
return len(probs) - 1
def c_array(ctype, values):
arr = (ctype * len(values))()
arr[:] = values
return arr
class BOX(Structure):
_fields_ = [("x", c_float),
("y", c_float),
("w", c_float),
("h", c_float)]
class DETECTION(Structure):
_fields_ = [("bbox", BOX),
("classes", c_int),
("prob", POINTER(c_float)),
("mask", POINTER(c_float)),
("objectness", c_float),
("sort_class", c_int)]
class IMAGE(Structure):
_fields_ = [("w", c_int),
("h", c_int),
("c", c_int),
("data", POINTER(c_float))]
class METADATA(Structure):
_fields_ = [("classes", c_int),
("names", POINTER(c_char_p))]
lib = CDLL("/home/xxx/darknet/libdarknet.so", RTLD_GLOBAL)
# lib = CDLL("libdarknet.so", RTLD_GLOBAL)
lib.network_width.argtypes = [c_void_p]
lib.network_width.restype = c_int
lib.network_height.argtypes = [c_void_p]
lib.network_height.restype = c_int
predict = lib.network_predict
predict.argtypes = [c_void_p, POINTER(c_float)]
predict.restype = POINTER(c_float)
set_gpu = lib.cuda_set_device
set_gpu.argtypes = [c_int]
make_image = lib.make_image
make_image.argtypes = [c_int, c_int, c_int]
make_image.restype = IMAGE
get_network_boxes = lib.get_network_boxes
get_network_boxes.argtypes = [c_void_p, c_int, c_int, c_float, c_float, POINTER(c_int), c_int, POINTER(c_int)]
get_network_boxes.restype = POINTER(DETECTION)
make_network_boxes = lib.make_network_boxes
make_network_boxes.argtypes = [c_void_p]
make_network_boxes.restype = POINTER(DETECTION)
free_detections = lib.free_detections
free_detections.argtypes = [POINTER(DETECTION), c_int]
free_ptrs = lib.free_ptrs
free_ptrs.argtypes = [POINTER(c_void_p), c_int]
network_predict = lib.network_predict
network_predict.argtypes = [c_void_p, POINTER(c_float)]
reset_rnn = lib.reset_rnn
reset_rnn.argtypes = [c_void_p]
load_net = lib.load_network
load_net.argtypes = [c_char_p, c_char_p, c_int]
load_net.restype = c_void_p
do_nms_obj = lib.do_nms_obj
do_nms_obj.argtypes = [POINTER(DETECTION), c_int, c_int, c_float]
do_nms_sort = lib.do_nms_sort
do_nms_sort.argtypes = [POINTER(DETECTION), c_int, c_int, c_float]
free_image = lib.free_image
free_image.argtypes = [IMAGE]
letterbox_image = lib.letterbox_image
letterbox_image.argtypes = [IMAGE, c_int, c_int]
letterbox_image.restype = IMAGE
load_meta = lib.get_metadata
lib.get_metadata.argtypes = [c_char_p]
lib.get_metadata.restype = METADATA
load_image = lib.load_image_color
load_image.argtypes = [c_char_p, c_int, c_int]
load_image.restype = IMAGE
rgbgr_image = lib.rgbgr_image
rgbgr_image.argtypes = [IMAGE]
predict_image = lib.network_predict_image
predict_image.argtypes = [c_void_p, IMAGE]
predict_image.restype = POINTER(c_float)
net_d = load_net(b"/home/xxx/darknet/cfg/yolov3.cfg", b"/home/xxx/darknet/yolov3.weights", 0)
meta_d = load_meta(b"/home/xxx/darknet/cfg/coco.data")
def classify(net, meta, im):
out = predict_image(net, im)
res = []
for i in range(meta.classes):
res.append((meta.names[i], out[i]))
res = sorted(res, key=lambda x: -x[1])
return res
def detect(net, meta, image, thresh=.5, hier_thresh=.5, nms=.45):
im = load_image(image, 0, 0)
num = c_int(0)
pnum = pointer(num)
predict_image(net, im)
dets = get_network_boxes(net, im.w, im.h, thresh, hier_thresh, None, 0, pnum)
num = pnum[0]
if (nms): do_nms_obj(dets, num, meta.classes, nms);
res = []
for j in range(num):
for i in range(meta.classes):
if dets[j].prob[i] > 0:
b = dets[j].bbox
res.append((meta.names[i], dets[j].prob[i], (b.x, b.y, b.w, b.h)))
res = sorted(res, key=lambda x: -x[1])
free_image(im)
free_detections(dets, num)
return res
# calc all box , red label for the biggest one ,yellow label for the rest, save the img to a specific path
def detect_and_boxing_default(b_path, raw_path, save_path,
color=(0.255, 255), line_type=1):
print("checking pic...", raw_path)
image = cv2.imread(raw_path)
r = detect(net_d, meta_d, b_path)
if not len(r) > 0:
print("nothing detected in this picture!")
else:
print(len(r), " stuff detected in this picture! boxing...")
print("going to save as :", save_path)
for i in range(len(r)):
box_i = r[i]
label_i = box_i[0]
prob_i = box_i[1]
x_ = box_i[2][0]
y_ = box_i[2][1]
w_ = box_i[2][2]
h_ = box_i[2][3]
text_ = str(label_i) + "," + str(round(prob_i, 3))
cv2.rectangle(image, (int(x_ - w_ / 2), int(y_ - h_ / 2)),
(int(x_ + w_ / 2), int(y_ + h_ / 2)),
color, line_type)
cv2.putText(image, text_, (int(x_ - w_ / 2 - 5), int(y_ - h_ / 2 - 5)), cv2.FONT_HERSHEY_DUPLEX, 0.7, color,
2)
cv2.imwrite(save_path, image)
def video_to_pics(video_path='/home/jiantang/work_data/sample_video.avi',
video_out_path='/home/jiantang/work_data/'):
print("video_to_pics start...")
vc = cv2.VideoCapture(video_path)
c = 1
if vc.isOpened():
rval, frame = vc.read()
else:
print('open error!')
rval = False
count_c = 1
while rval:
rval, frame = vc.read()
if rval:
print("dealing with frame : ", count_c)
cv2.imwrite(video_out_path + str(int(c)) + '.jpg', frame)
c += 1
cv2.waitKey(1)
count_c += 1
vc.release()
print("video_to_pics finished...")
def pics_boxing(pics_path, save_path):
raw_save_path = save_path
print("pics_boxing start...")
print("checking path : ", pics_path)
pics_names = os.listdir(pics_path)
print("found pics num :", len(pics_names))
count_c = 1
for name in pics_names:
print("dealing with pics ", count_c)
raw_path = pics_path + "/" + name
b_path = bytes(raw_path, encoding="utf8")
save_path = raw_save_path + "/" + name
detect_and_boxing_default(b_path, raw_path, save_path)
count_c += 1
print("pics_boxing finished...")
def pics_to_video(pics_path, video_new_path='/home/jiantang/work_data/sample_video_new.avi', ):
print("pics_to_video start...")
print("checking files in :", pics_path)
file_list = os.listdir(pics_path)
# remove non-jpg files, remove .jpg sign
tmp_jpg = []
for name in file_list:
if not name.endswith('.jpg'):
print("found sth called:", name, ", skip it.")
file_list.remove(name)
continue
tmp_jpg.append(name.replace(".jpg", ""))
# sort names
tmp_jpg.sort(key=int)
fourcc = cv2.VideoWriter_fourcc('I', '4', '2', '0') # 设置输出视频为avi格式
# cap_fps是帧率，可以根据随意设置；size要和图片的size一样，但是通过img.shape得到图像的参数是
# （height，width，channel），但是此处的size要传的是（width，height），这里一定要注意注意，
# 不然结果会打不开，提示“无法解码多工传送的流”等.比如通过img.shape得到常用的图片尺寸
# （1080,1920,3），则size设为（1920,1080）
cap_fps = 50
size = (1920, 1080)
# 设置视频输出的参数
video = cv2.VideoWriter(video_new_path, fourcc, cap_fps, size)
# video.write默认保存彩色图，如果是彩色图，则直接保存
for name in tmp_jpg:
img_E = cv2.imread(pics_path + "/" + name + ".jpg")
print("reading....")
video.write(img_E)
video.release()
print("pics_to_video finished...")
video_path = '/home/xxx/darknet/car.mp4'
video_out_path = '/home/xxx/darknet/output/pics/'
video_out_dir = '/home/xxx/darknet/output/pics'
video_out_new_path = '/home/xxx/darknet/output/pics_new'
video_new_path = '/home/xxx/darknet/output/pics_new/sample_video_new.avi'
video_to_pics(video_path, video_out_path)
pics_boxing(video_out_dir, video_out_new_path)
# pics_to_video(video_out_new_path, video_new_path)3. rtsp码流格式
在YOLO官网提供的Darknet源码中，有一个使用python接口的示例程序 darknet.py
使用是需要简单的修改.
if __name__ == "__main__":
net = load_net(b"/home/xxx/darknet/cfg/yolov3.cfg", b"/home/xxx/darknet/yolov3.weights", 0)
meta = load_meta(b"/home/xxx/darknet/cfg/coco.data")
r = detect(net, meta, b"/home/xxx/darknet/data/dog.jpg")
print(r)看detect函数的定义
def detect(net, meta, image, thresh=.5, hier_thresh=.5, nms=.45):
im = load_image(image, 0, 0)
num = c_int(0)
pnum = pointer(num)
predict_image(net, im)
dets = get_network_boxes(net, im.w, im.h, thresh, hier_thresh, None, 0, pnum)
num = pnum[0]
if (nms): do_nms_obj(dets, num, meta.classes, nms);
res = []
for j in range(num):
for i in range(meta.classes):
if dets[j].prob[i] > 0:
b = dets[j].bbox
res.append((meta.names[i], dets[j].prob[i], (b.x, b.y, b.w, b.h)))
res = sorted(res, key=lambda x: -x[1])
free_image(im)
free_detections(dets, num)
return res传入detect函数的第三个参数image是字符串类型，即路径，随后调用load_image函数加载图片得到im对象，（注意这个im是Darknet中自定义的结构体image类型，定义在include/darknet.h中，该文件的详细注释在群内有分享。）再进行后续处理，那么我们改写接口的时候就可以直接将第三个参数改为image类型。做如下的修改：
- 在darkenet.py中自定义一个函数，内容如下
def nparray_to_image(img):
data = img.ctypes.data_as(POINTER(c_ubyte))
image = ndarray_image(data, img.ctypes.shape, img.ctypes.strides)
return image- 在darknet.py中增加如下行代码，增加位置找到类似代码的位置就好
ndarray_image = lib.ndarray_to_image
ndarray_image.argtypes = [POINTER(c_ubyte), POINTER(c_long), POINTER(c_long)]
ndarray_image.restype = IMAGE- 在image.c中增加如下代码段，我新增的部分在OPENCV定义后面，灵活修改就好
int show_image(image p, const char *name, int ms)
{
#ifdef OPENCV
int c = show_image_cv(p, name, ms);
return c;
#else
fprintf(stderr, "Not compiled with OpenCV, saving to %s.png instead\n", name);
save_image(p, name);
return -1;
#endif
}
//modify by liu 新增部分
#ifdef NUMPY
image ndarray_to_image(unsigned char* src, long* shape, long* strides)
{
int h = shape[0];
int w = shape[1];
int c = shape[2];
int step_h = strides[0];
int step_w = strides[1];
int step_c = strides[2];
image im = make_image(w, h, c);
int i, j, k;
int index1, index2 = 0;
for(i = 0; i < h; ++i){
for(k= 0; k < c; ++k){
for(j = 0; j < w; ++j){
index1 = k*w*h + i*w + j;
index2 = step_h*i + step_w*j + step_c*k;
//fprintf(stderr, "w=%d h=%d c=%d step_w=%d step_h=%d step_c=%d \n", w, h, c, step_w, step_h, step_c);
//fprintf(stderr, "im.data[%d]=%u data[%d]=%f \n", index1, src[index2], index2, src[index2]/255.);
im.data[index1] = src[index2]/255.;
}
}
}
rgbgr_image(im);
return im;
}
#endif- 在image.h的19行后面加如下代码
#ifdef NUMPY
image ndarray_to_image(unsigned char* src, long* shape, long* strides);
#endif- 在makefile的47行后面中加如下代码
ifeq ($(NUMPY), 1)
COMMON+= -DNUMPY -I/usr/include/python2.7/ -I/usr/lib/python2.7/dist-packages/numpy/core/include/numpy/
CFLAGS+= -DNUMPY
endif前几行加 一条 NUMPY=1，增加后为：
GPU=1
CUDNN=1
OPENCV=1
OPENMP=0
NUMPY=1
DEBUG=0- 重新编译make clean + make
- 配置结束
from ctypes import *
import random
import cv2
def sample(probs):
s = sum(probs)
probs = [a / s for a in probs]
r = random.uniform(0, 1)
for i in range(len(probs)):
r = r - probs[i]
if r <= 0:
return i
return len(probs) - 1
def c_array(ctype, values):
arr = (ctype * len(values))()
arr[:] = values
return arr
class BOX(Structure):
_fields_ = [("x", c_float),
("y", c_float),
("w", c_float),
("h", c_float)]
class DETECTION(Structure):
_fields_ = [("bbox", BOX),
("classes", c_int),
("prob", POINTER(c_float)),
("mask", POINTER(c_float)),
("objectness", c_float),
("sort_class", c_int)]
class IMAGE(Structure):
_fields_ = [("w", c_int),
("h", c_int),
("c", c_int),
("data", POINTER(c_float))]
class METADATA(Structure):
_fields_ = [("classes", c_int),
("names", POINTER(c_char_p))]
lib = CDLL("/home/huadian/darknet/libdarknet.so", RTLD_GLOBAL)
lib.network_width.argtypes = [c_void_p]
lib.network_width.restype = c_int
lib.network_height.argtypes = [c_void_p]
lib.network_height.restype = c_int
predict = lib.network_predict
predict.argtypes = [c_void_p, POINTER(c_float)]
predict.restype = POINTER(c_float)
set_gpu = lib.cuda_set_device
set_gpu.argtypes = [c_int]
make_image = lib.make_image
make_image.argtypes = [c_int, c_int, c_int]
make_image.restype = IMAGE
ndarray_image = lib.ndarray_to_image
ndarray_image.argtypes = [POINTER(c_ubyte), POINTER(c_long), POINTER(c_long)]
ndarray_image.restype = IMAGE
get_network_boxes = lib.get_network_boxes
get_network_boxes.argtypes = [c_void_p, c_int, c_int, c_float, c_float, POINTER(c_int), c_int, POINTER(c_int)]
get_network_boxes.restype = POINTER(DETECTION)
make_network_boxes = lib.make_network_boxes
make_network_boxes.argtypes = [c_void_p]
make_network_boxes.restype = POINTER(DETECTION)
free_detections = lib.free_detections
free_detections.argtypes = [POINTER(DETECTION), c_int]
free_ptrs = lib.free_ptrs
free_ptrs.argtypes = [POINTER(c_void_p), c_int]
network_predict = lib.network_predict
network_predict.argtypes = [c_void_p, POINTER(c_float)]
reset_rnn = lib.reset_rnn
reset_rnn.argtypes = [c_void_p]
load_net = lib.load_network
load_net.argtypes = [c_char_p, c_char_p, c_int]
load_net.restype = c_void_p
do_nms_obj = lib.do_nms_obj
do_nms_obj.argtypes = [POINTER(DETECTION), c_int, c_int, c_float]
do_nms_sort = lib.do_nms_sort
do_nms_sort.argtypes = [POINTER(DETECTION), c_int, c_int, c_float]
free_image = lib.free_image
free_image.argtypes = [IMAGE]
letterbox_image = lib.letterbox_image
letterbox_image.argtypes = [IMAGE, c_int, c_int]
letterbox_image.restype = IMAGE
load_meta = lib.get_metadata
lib.get_metadata.argtypes = [c_char_p]
lib.get_metadata.restype = METADATA
load_image = lib.load_image_color
load_image.argtypes = [c_char_p, c_int, c_int]
load_image.restype = IMAGE
rgbgr_image = lib.rgbgr_image
rgbgr_image.argtypes = [IMAGE]
# modify by liu
predict_image = lib.network_predict_image
predict_image.argtypes = [c_void_p, IMAGE]
predict_image.restype = POINTER(c_float)
def classify(net, meta, im):
out = predict_image(net, im)
res = []
for i in range(meta.classes):
res.append((meta.names[i], out[i]))
res = sorted(res, key=lambda x: -x[1])
return res
def detect(net, meta, im, thresh=.5, hier_thresh=.5, nms=.45):
# im = load_image(image, 0, 0)
num = c_int(0)
pnum = pointer(num)
predict_image(net, im)
dets = get_network_boxes(net, im.w, im.h, thresh, hier_thresh, None, 0, pnum)
num = pnum[0]
if (nms): do_nms_obj(dets, num, meta.classes, nms);
res = []
for j in range(num):
for i in range(meta.classes):
if dets[j].prob[i] > 0:
b = dets[j].bbox
res.append((meta.names[i], dets[j].prob[i], (b.x, b.y, b.w, b.h)))
res = sorted(res, key=lambda x: -x[1])
free_image(im)
free_detections(dets, num)
return res
# modify by liu
def nparray_to_image(img):
data = img.ctypes.data_as(POINTER(c_ubyte))
image = ndarray_image(data, img.ctypes.shape, img.ctypes.strides)
return image
# calc all box , red label for the biggest one ,yellow label for the rest, save the img to a specific path
def detect_and_boxing(net, meta, b_path, raw_path, save_path,
color=(0.255, 255), line_type=1):
image = cv2.imread(raw_path)
r = detect(net, meta, b_path)
if not len(r) > 0:
print("nothing detected in this picture!")
else:
for i in range(len(r)):
box_i = r[i]
label_i = box_i[0]
prob_i = box_i[1]
x_ = box_i[2][0]
y_ = box_i[2][1]
w_ = box_i[2][2]
h_ = box_i[2][3]
text_ = str(label_i) + "," + str(round(prob_i, 3))
cv2.rectangle(image, (int(x_ - w_ / 2), int(y_ - h_ / 2)),
(int(x_ + w_ / 2), int(y_ + h_ / 2)),
color, line_type)
cv2.putText(image, text_, (int(x_ - w_ / 2 - 5), int(y_ - h_ / 2 - 5)), cv2.FONT_HERSHEY_DUPLEX, 0.7, color,
2)
cv2.imwrite(save_path, image)
print("boxing ", i, " found ", label_i, "with prob = ", prob_i, ", finished!")
print("box position is :", box_i[2])
if __name__ == "__main__":
net = load_net(b"/home/xxx/darknet/cfg/yolov3.cfg", b"/home/huadian/darknet/yolov3.weights", 0)
meta = load_meta(b"/home/xxx/darknet/cfg/coco.data")
# 使用rtsp格式播放
vid = cv2.VideoCapture('rtsp://admin:liupeng199188@192.168.12.100/Streaming/Channels/1801')
while True:
return_value, arr = vid.read()
im = nparray_to_image(arr)
r = detect(net, meta, im)
print(r)
print("this frame ok!")
# image = cv2.imread("/home/xxx/darknet/data/dog.jpg")
# image = nparray_to_image(image)
# r = detect(net, meta, image)
# print(r)
本文章为转载内容，我们尊重原作者对文章享有的著作权。如有内容错误或侵权问题，欢迎原作者联系我们进行内容更正或删除文章。
