k210学习记录（人脸检测）

最新推荐文章于 2024-04-21 18:43:20 发布

不吃橘子的橘猫

最新推荐文章于 2024-04-21 18:43:20 发布

阅读量220

点赞数 1

分类专栏： k210 文章标签：学习 python 开发语言嵌入式硬件

本文链接：https://blog.csdn.net/weixin_73011353/article/details/131747334

版权

k210 专栏收录该内容

10 篇文章 0 订阅

订阅专栏

代码：

import sensor, image, time, lcd
from maix import KPU

lcd.init()
sensor.reset()
sensor.set_pixformat(sensor.RGB565)
sensor.set_framesize(sensor.QVGA)
sensor.skip_frames(time = 100)
clock = time.clock()

od_img = image.Image(size=(320,256))

anchor = (0.893, 1.463, 0.245, 0.389, 1.55, 2.58, 0.375, 0.594, 3.099, 5.038, 0.057, 0.090, 0.567, 0.904, 0.101, 0.160, 0.159, 0.255)
kpu = KPU()
kpu.load_kmodel("/sd/KPU/yolo_face_detect/yolo_face_detect.kmodel")
kpu.init_yolo2(anchor, anchor_num=9, img_w=320, img_h=240, net_w=320, net_h=256, layer_w=10, layer_h=8, threshold=0.7, nms_value=0.3, classes=1)

while True:
    clock.tick()
    img = sensor.snapshot()
    a = od_img.draw_image(img, 0,0)
    od_img.pix_to_ai()
    kpu.run_with_output(od_img)
    dect = kpu.regionlayer_yolo2()
    fps = clock.fps()
    if len(dect) > 0:
        print("dect:",dect)
        for l in dect :
            a = img.draw_rectangle(l[0],l[1],l[2],l[3], color=(0, 255, 0))
    a = img.draw_string(0, 0, "%2.1ffps" %(fps), color=(0, 60, 128), scale=2.0)
    lcd.display(img)

kpu.deinit()

解析：

1、导入相关库，初始化摄像头和LCD屏

import sensor, image, time, lcd
from maix import KPU


lcd.init()
sensor.reset()
sensor.set_pixformat(sensor.RGB565)
sensor.set_framesize(sensor.QVGA)
sensor.skip_frames(time = 100)
clock = time.clock()

2、初始化KPU相关参数，用yolo2计算是否符合模型要求，其中，od_img为神经网络图像

od_img = image.Image(size=(320,256))

anchor = (0.893, 1.463, 0.245, 0.389, 1.55, 2.58, 0.375, 0.594, 3.099, 5.038, 0.057, 0.090, 0.567, 0.904, 0.101, 0.160, 0.159, 0.255)
kpu = KPU()
kpu.load_kmodel("/sd/KPU/yolo_face_detect/yolo_face_detect.kmodel")
kpu.init_yolo2(anchor, anchor_num=9, img_w=320, img_h=240, net_w=320, net_h=256, layer_w=10, layer_h=8, threshold=0.7, nms_value=0.3, classes=1)

3、新建while循环，将图像传入KPU进行计算，使用yolo2神经网络算法进行解算，得到人脸的位置信息，然后将人脸框出来

while True:
    clock.tick()
    img = sensor.snapshot()
    a = od_img.draw_image(img, 0,0)
    od_img.pix_to_ai()
    kpu.run_with_output(od_img)
    dect = kpu.regionlayer_yolo2()
    fps = clock.fps()
    if len(dect) > 0:
        print("dect:",dect)
        for l in dect :
            a = img.draw_rectangle(l[0],l[1],l[2],l[3], color=(0, 255, 0))
    a = img.draw_string(0, 0, "%2.1ffps" %(fps), color=(0, 60, 128), scale=2.0)
    lcd.display(img)

kpu.deinit()