# Edge Impulse - OpenMV FOMO Object Detection Example
#
# This work is licensed under the MIT license.
# Copyright (c) 2013-2024 OpenMV LLC. All rights reserved.
# https://github.com/openmv/openmv/blob/master/LICENSE
import sensor, image, time, os, ml, math, uos, gc
from ulab import numpy as np
from pyb import UART
uart = UART(3, 19200, timeout_char=200)
sensor.reset() # Reset and initialize the sensor.
sensor.set_pixformat(sensor.RGB565) # Set pixel format to RGB565 (or GRAYSCALE)
sensor.set_framesize(sensor.QVGA) # Set frame size to QVGA (320x240)
sensor.set_windowing((240, 240)) # Set 240x240 window.
sensor.skip_frames(time=2000) # Let the camera adjust.
#定义一个空列表,处理数据使用。
handedata_list = [] * 4
net = None
labels = None
# 设置最小置信度阈值
min_confidence = 0.95
#加载模型和异常处理
try:
# load the model, alloc the model file on the heap if we have at least 64K free after loading
net = ml.Model("trained.tflite", load_to_fb=True)
except Exception as e:
raise Exception('Failed to load "trained.tflite", did you copy the .tflite and labels.txt file onto the mass-storage device? (' + str(e) + ')')
try:
labels = [line.rstrip('\n') for line in open("labels.txt")]
except Exception as e:
raise Exception('Failed to load "labels.txt", did you copy the .tflite and labels.txt file onto the mass-storage device? (' + str(e) + ')')
colors = [ # Add more colors if you are detecting more than 7 types of classes at once.
(128, 0, 128), #紫色
( 0, 255, 0), #绿色
(255, 0 , 0), #红色
( 0, 0, 255), #蓝色
(255, 165, 0), #橙色
(128, 0, 255), #紫色
(255, 255, 0), #黄色
(0 , 255, 255), #青色
(255, 105, 180), #粉色
(144, 238, 144), #浅绿色
(169, 169, 169), #灰色
(255, 255, 255), #白色
]
# 定义置信度阈值列表，进行图像处理时使用
threshold_list = [(math.ceil(min_confidence * 255), 255)] #返回一个整数，将 x 四舍五入
# print(threshold_list)
# time.sleep(10)
# 定义FOMO后处理函数，处理模型输出，提取检测到的对象信息
def fomo_post_process(model, inputs, outputs):
ob, oh, ow, oc = model.output_shape[0] # 获取模型输出的形状，包含对象数量、输出高度、输出宽度和输出通道数
# 计算输入图像与输出图像的比例
x_scale = inputs[0].roi[2] / ow # 输入图像宽度与输出宽度的比例
y_scale = inputs[0].roi[3] / oh # 输入图像高度与输出高度的比例
scale = min(x_scale, y_scale) # 取最小比例作为缩放因子
# 计算输出图像的偏移量 以便将检测结果调整到输入图像的坐标系
x_offset = ((inputs[0].roi[2] - (ow * scale)) / 2) + inputs[0].roi[0]
y_offset = ((inputs[0].roi[3] - (ow * scale)) / 2) + inputs[0].roi[1]
# 初始化一个列表，用于存储每个输出通道的检测结果
l = [[] for i in range(oc)]
for i in range(oc):
img = image.Image(outputs[0][0, :, :, i] * 255)
blobs = img.find_blobs(
threshold_list, x_stride=1, y_stride=1, area_threshold=1, pixels_threshold=1
) #x_stride 是从左上角开始搜索blob要跳过的像素数量，为1既在x方向一个一个找
#过滤掉边界框面积和像素小于area_threshold,pixels_threshold的blobs
#通过灰度范围筛选可能的检测区域，后续搭配置信度来保留可信的检测结果
for b in blobs:
rect = b.rect() #返回一个矩形元组 (x, y, w, h) 表示blobs的边界框
x, y, w, h = rect
score = (
img.get_statistics(thresholds=threshold_list, roi=rect).l_mean() / 255.0
) #按照颜色划分，实际过程是置信度转化成灰度值
x = int((x * scale) + x_offset) #下面的一系列操作均为将识别到的边界框重新放置到原图上
y = int((y * scale) + y_offset)
w = int(w * scale)
h = int(h * scale)
l[i].append((x, y, w, h, score))
return l #这个列表中是各种类别的坐标和置信度得分
clock = time.clock()
while(True):
clock.tick()
img = sensor.snapshot()
#双循环寻找类别，寻找到哪个，就输出哪个 enumerate函数生成一个可迭代对象，比如这里列表内嵌套多个元组
for i, detection_list in enumerate(net.predict([img], callback=fomo_post_process)):
if i == 0: continue # background class
if len(detection_list) == 0: continue # no detections for this class?
print("********** %s **********" % labels[i]) #数字检测中这个i就是数字，小数点另行处理
for x, y, w, h, score in detection_list: #这个图像中，这个类别有多少个目标，这个循环就走多少次
center_x = math.floor(x + (w / 2))
center_y = math.floor(y + (h / 2))
# print(f"x {center_x}\ty {center_y}\tscore {score}")
img.draw_circle((center_x, center_y, 12), color=colors[i])
# print(f"x {x}\ty {y}\tscore {score}")
# img.draw_rectangle((x, y, w , h), color=colors[i]) #画圆改成画矩形
# detection_list的结构是一个列表，列表内的成员是元组
# 将x坐标提取出来以元组形式(x,labels[i])存储到列表中
data_tulpe = (x , int(labels[i]))
handedata_list.append(data_tulpe)
# 循环结束后按x的大小对列表进行排序
sorted_list = sorted(handedata_list, key=lambda x: x[0]) # 按照匹配结果的左上角坐标排序结构内部是元组
# 排序后将第二位数据标签提出来
result_list = [item[1] for item in sorted_list if len(item) >= 2]
# 这个列表中的数据就是识别到的数字，将其配合协议通过串口一起发送即可
print(result_list)
result_list.clear()
handedata_list.clear()
print(clock.fps(), "fps", end="\n\n")
# time.sleep(0.5)
请在这里粘贴代码