OpenVINO行人属性识别

openlab_4276841a 更新于 3年前

OpenVINO不仅通过其IE组件实现加速推理,其提供的预训练库还支持各种常见的图像检测、分割、对象识别等的计算机视觉任务。前面小编写过一系列的文章详细介绍过OpenVINO的各种应用,可以看这里回顾一下:

这里分享一下如何通过OpenVINO提供的行人检测与行人属性识别模型实现一个实时的视频行人检测与属性识别的演示程序。先看一下效果:

模型:模型来自OpenVINO官方提供的预训练模型库

行人检测模型:
模型名称:pedestrian-detection-adas-0002
输入格式:NCHW= [1x3x384x672]
输出格式: DetectionOut 类型 [1, 1, N, 7]
基于Caffe SSD MobileNet V1版本训练生成

行人属性识别模型:
模型名称:person-attributes-recognition-crossroad-0230
输入格式:NCHW= [1x3x160x80]
输出格式:
输出层有三个,其中输出层名称为435的输出格式为
[1, 8, 1, 1] 是八个属性
另外两个输出层456,459表示两个颜色位置
基于pytorch训练生成的分类网络模型,支持的八种属性与准确率如下:

两个模型均可在intel OpenVINO的官方网站下载即可

代码实现

mport sy***r>import cv2
import numpy as np
import time
import logging as log
from openvino.inference_engine import IENetwork, IEPlugin
plugin_dir = "C:/Intel/openvino_2019.1.148/deployment_tools/inference_engine/bin/intel64/Release"
cpu_extension = "C:/Users/Administrator/Documents/Intel/OpenVINO/inference_engine_sample***uild/intel64/Release/cpu_extension.dll"
model_xml = "D:/project***odels/pedestrian-detection-adas-0002/FP32/pedestrian-detection-adas-0002.xml"
model_bin = "D:/project***odels/pedestrian-detection-adas-0002/FP32/pedestrian-detection-adas-0002.bin"

attribute_xml = "D:/project***odels/pedestrian-detection-adas-0002/person-attributes-recognition-crossroad-0230.xml"
attribute_bin = "D:/project***odels/pedestrian-detection-adas-0002/person-attributes-recognition-crossroad-0230.bin"

attrs = ['i***ale', 'ha***ag', 'ha***ackpack', 'has_hat', 'has_longsleeves', 'has_longpants', 'has_longhair', 'has_coat_jacket']

def demo():
# 加载MKLDNN - CPU Target
log.basicConfig(format="[ %(levelname)*******essage)s", level=log.INFO, stream=sys.stdout)
plugin = IEPlugin(device="CPU", plugin_dirs=plugin_dir)
plugin.add_cpu_extension(cpu_extension)

lut = [];
lut.append((0, 0, 255))
lut.append((255, 0, 0))
lut.append((0, 255, 0))
lut.append((0, 255, 255))
lut.append((255, 0, 255))
# 加载IR
log.info("Reading IR...")
net = IENetwork(model=model_xml, weight***odel_bin)
pedestrian_attr_net = IENetwork(model=attribute_xml, weights=attribute_bin)

if plugin.device == "CPU":
supported_layers = plugin.get_supported_layers(net)
not_supported_layers = [l for l in net.layers.keys() if l not in supported_layer****r> if len(not_supported_layers) != 0:
log.error("Following layers are not supported by the plugin for specified device {}:\n {}".
format(plugin.device, ', '.join(not_supported_layer******r> log.error("Please try to specify cpu extensions library path in demo's command line parameters using -l "
"or --cpu_extension command line argument")
sys.exit(1)
assert len(net.inputs.keys()) == 1, "Demo supports only single input topologie****r> assert len(net.outputs) == 1, "Demo supports only single output topologie****r>
# 获取输入输出层
input_blob = next(iter(net.input*****r> out_blob = next(iter(net.output*****r>
lm_input_blob = next(iter(pedestrian_attr_net.input*****r> lm_output_blob = next(iter(pedestrian_attr_net.output*****r> log.info("Loading IR to the plugin...")

# 创建可执行网络
exec_net = plugin.load(network=net, num_requests=2)
lm_exec_net = plugin.load(network=pedestrian_attr_net)
n, c, h, w = net.inputs[input_blob].shape
del net

# we did not need pedestrian model any more
mn, mc, mh, mw = pedestrian_attr_net.inputs[lm_input_blob].shape
del pedestrian_attr_net

# 开始视频文件或者摄像头
cap = cv2.VideoCapture("D:/images/video/fromis-song***p4")
# cap = cv2.VideoCapture(0)

cur_request_id = 0
next_request_id = 1

log.info("Starting inference in async mode...")
log.info("To switch between sync and async modes press Tab button")
log.info("To stop the demo execution press Esc button")
is_async_mode = True
render_time = 0

# 读取视频流
ret, frame = cap.read()
initial_w = cap.get(3)
initial_h = cap.get(4)

# 开始检测
while cap.isOpened():
if is_async_mode:
ret, next_frame = cap.read()
else:
ret, frame = cap.read()
if not ret:
break

# next_frame = cv2.flip(next_frame, 1)

# 开启同步或者异步执行模式
inf_start = time.time()
if is_async_mode:
in_frame = cv2.resize(next_frame, (w, h))
in_frame = in_frame.transpose((2, 0, 1)) # Change data layout from HWC to CHW
in_frame = in_frame.reshape((n, c, h, w))
exec_net.start_async(request_id=next_request_id, inputs={input_blob: in_frame})
else:
in_frame = cv2.resize(frame, (w, h))
in_frame = in_frame.transpose((2, 0, 1)) # Change data layout from HWC to CHW
in_frame = in_frame.reshape((n, c, h, w))
exec_net.start_async(request_id=cur_request_id, inputs={input_blob: in_frame})
if exec_net.requests[cur_request_id].wait(-1) == 0:

# 解析DetectionOut
res = exec_net.requests[cur_request_id].outputs[out_blob]
for obj in res[0][0]:
# Draw only objects when probability more than specified threshold
if obj[2] > 0.5:
xmin = int(obj[3] * initial_w)
ymin = int(obj[4] * initial_h)
xmax = int(obj[5] * initial_w)
ymax = int(obj[6] * initial_h)
class_id = int(obj[1])

# Draw box and label\class_id
cv2.rectangle(frame, (xmin, ymin), (xmax, ymax), (0, 0, 255), 2)
if xmin > 0 and ymin > 0 and (xmax < initial_w) and (ymax < initial_h):
roi = frame[ymin:ymax, xmin:xmax, :]
pedestrian_roi = cv2.resize(roi, (mw, mh))
pedestrian_roi = pedestrian_roi.transpose((2, 0, 1))
pedestrian_roi = pedestrian_roi.reshape((mn, mc, mh, mw))

# 行人属性识别
lm_exec_net.infer(inputs={'0': pedestrian_roi})
attr_res = lm_exec_net.requests[0].outputs[lm_output_blob]
attr_res = np.reshape(attr_res, (8, 1))

# 解析行人八个属性指标
for i in range(len(attrs)):
if attr_res[i][0] > 0.5:
cv2.putText(frame, attrs[i] + ": " + str(1),
(xmin+30, ymin+20*i),
cv2.FONT_HERSHEY_COMPLEX, 0.5, (0, 0, 255), 1)
else:
cv2.putText(frame, attrs[i] + ": " + str(0),
(xmin + 30, ymin + 20 * i),
cv2.FONT_HERSHEY_COMPLEX, 0.5, (0, 0, 255), 1)
cv2.putText(frame, "Person" + ' ' + str(round(obj[2] * 100, 1)) + ' %', (xmin, ymin - 7),
cv2.FONT_HERSHEY_COMPLEX, 0.5, (255, 0, 0), 1)
inf_end = time.time()
det_time = inf_end - inf_start

# 显示绘制文本
inf_time_message = "Inference time: {:.3f} ms, FPS:{:.3f}".format(det_time * 1000, 1000 / (det_time * 1000 + 1))
render_time_message = "OpenCV rendering time: {:.3f} ms".format(render_time * 1000)
async_mode_message = "Async mode is on. Processing request {}".format(cur_request_id) if is_async_mode else \
"Async mode is off. Processing request {}".format(cur_request_id)

cv2.putText(frame, inf_time_message, (15, 15), cv2.FONT_HERSHEY_COMPLEX, 0.5, (255, 255, 0), 1)
cv2.putText(frame, render_time_message, (15, 30), cv2.FONT_HERSHEY_COMPLEX, 0.5, (10, 10, 200), 1)
cv2.putText(frame, async_mode_message, (10, int(initial_h - 20)), cv2.FONT_HERSHEY_COMPLEX, 0.5,
(10, 10, 200), 1)

# 显示
render_start = time.time()
cv2.imshow("OpenVINO-face-landmark-detection@57558865", frame)
render_end = time.time()
render_time = render_end - render_start

# ready for next frame
if is_async_mode:
cur_request_id, next_request_id = next_request_id, cur_request_id
frame = next_frame

key = cv2.waitKey(50)
if key == 27:
break

# 释放资源
cv2.destroyAllWindow*****r> del exec_net
del lm_exec_net
del plugin


if __name__ == '__main__':
sys.exit(demo() or 0)

使用两段视频测试截图分别如下:




0个评论