我想做一个AI发现视频中有手机出现就保存下来的例子，好似发现车辆越线就拍照保存，于是我将YOLO8的例子进行了拓展，手机能正常识别，并在串口中发送消息，但想进行保存时，我先将888的格式转为了565，而后保存为JPG格式图片，但我发现保存出来的JPG不正确，变成了黑色条纹图片。请问应该如何解决。
以下是我的代码，用的是嘉立创开发板庐山派K230,固件为1.2.1版本。
from libs.PipeLine import PipeLine, ScopedTiming
from libs.AIBase import AIBase
from libs.AI2D import Ai2d
import os
import ujson
from media.media import *
from time import *
import nncase_runtime as nn
import ulab.numpy as np
import time
import utime
import image
import random
import gc
import sys
import aidemo
from machine import UART
from machine import FPIOA
from machine import RTC
# 自定义YOLOv8检测类
class ObjectDetectionApp(AIBase):
def __init__(self,kmodel_path,labels,model_input_size,max_boxes_num,confidence_threshold=0.5,nms_threshold=0.2,rgb888p_size=[224,224],display_size=[1920,1080],debug_mode=0):
super().__init__(kmodel_path,model_input_size,rgb888p_size,debug_mode)
self.kmodel_path=kmodel_path
self.labels=labels
# 模型输入分辨率
self.model_input_size=model_input_size
# 阈值设置
self.confidence_threshold=confidence_threshold
self.nms_threshold=nms_threshold
self.max_boxes_num=max_boxes_num
# sensor给到AI的图像分辨率
self.rgb888p_size=[ALIGN_UP(rgb888p_size[0],16),rgb888p_size[1]]
# 显示分辨率
self.display_size=[ALIGN_UP(display_size[0],16),display_size[1]]
self.debug_mode=debug_mode
# 检测框预置颜色值
self.color_four=[(255, 220, 20, 60), (255, 119, 11, 32), (255, 0, 0, 142), (255, 0, 0, 230),
(255, 106, 0, 228), (255, 0, 60, 100), (255, 0, 80, 100), (255, 0, 0, 70),
(255, 0, 0, 192), (255, 250, 170, 30), (255, 100, 170, 30), (255, 220, 220, 0),
(255, 175, 116, 175), (255, 250, 0, 30), (255, 165, 42, 42), (255, 255, 77, 255),
(255, 0, 226, 252), (255, 182, 182, 255), (255, 0, 82, 0), (255, 120, 166, 157)]
# 宽高缩放比例
self.x_factor = float(self.rgb888p_size[0])/self.model_input_size[0]
self.y_factor = float(self.rgb888p_size[1])/self.model_input_size[1]
# Ai2d实例，用于实现模型预处理
self.ai2d=Ai2d(debug_mode)
# 设置Ai2d的输入输出格式和类型
self.ai2d.set_ai2d_dtype(nn.ai2d_format.NCHW_FMT,nn.ai2d_format.NCHW_FMT,np.uint8, np.uint8)
# 配置预处理操作，这里使用了resize，Ai2d支持crop/shift/pad/resize/affine，具体代码请打开/sdcard/app/libs/AI2D.py查看
def config_preprocess(self,input_image_size=None):
with ScopedTiming("set preprocess config",self.debug_mode > 0):
# 初始化ai2d预处理配置，默认为sensor给到AI的尺寸，您可以通过设置input_image_size自行修改输入尺寸
ai2d_input_size=input_image_size if input_image_size else self.rgb888p_size
self.ai2d.resize(nn.interp_method.tf_bilinear, nn.interp_mode.half_pixel)
self.ai2d.build([1,3,ai2d_input_size[1],ai2d_input_size[0]],[1,3,self.model_input_size[1],self.model_input_size[0]])
# 自定义当前任务的后处理
def postprocess(self,results):
with ScopedTiming("postprocess",self.debug_mode > 0):
result=results[0]
result = result.reshape((result.shape[0] * result.shape[1], result.shape[2]))
output_data = result.transpose()
boxes_ori = output_data[:,0:4]
scores_ori = output_data[:,4:]
confs_ori = np.max(scores_ori,axis=-1)
inds_ori = np.argmax(scores_ori,axis=-1)
boxes,scores,inds = [],[],[]
for i in range(len(boxes_ori)):
if confs_ori[i] > confidence_threshold:
scores.append(confs_ori[i])
inds.append(inds_ori[i])
x = boxes_ori[i,0]
y = boxes_ori[i,1]
w = boxes_ori[i,2]
h = boxes_ori[i,3]
left = int((x - 0.5 * w) * self.x_factor)
top = int((y - 0.5 * h) * self.y_factor)
right = int((x + 0.5 * w) * self.x_factor)
bottom = int((y + 0.5 * h) * self.y_factor)
boxes.append([left,top,right,bottom])
if len(boxes)==0:
return []
boxes = np.array(boxes)
scores = np.array(scores)
inds = np.array(inds)
# NMS过程
keep = self.nms(boxes,scores,nms_threshold)
dets = np.concatenate((boxes, scores.reshape((len(boxes),1)), inds.reshape((len(boxes),1))), axis=1)
dets_out = []
for keep_i in keep:
dets_out.append(dets[keep_i])
dets_out = np.array(dets_out)
dets_out = dets_out[:self.max_boxes_num, :]
return dets_out
# 绘制结果
def draw_result(self,pl,dets):
with ScopedTiming("display_draw",self.debug_mode >0):
if dets:
pl.osd_img.clear()
for det in dets:
x1, y1, x2, y2 = map(lambda x: int(round(x, 0)), det[:4])
x= x1*self.display_size[0] // self.rgb888p_size[0]
y= y1*self.display_size[1] // self.rgb888p_size[1]
w = (x2 - x1) * self.display_size[0] // self.rgb888p_size[0]
h = (y2 - y1) * self.display_size[1] // self.rgb888p_size[1]
#发现手机，超过阈值0.5，提示有手机了
if((int(det[5])==67)):
pl.osd_img.draw_rectangle(x,y, w, h, color=self.get_color(int(det[5])),thickness=4)
pl.osd_img.draw_string_advanced( x , y-50,32," " + self.labels[int(det[5])] + " " + str(round(det[4],2)) , color=self.get_color(int(det[5])))
if(round(det[4],2)>0.5):
return 1
else:
pl.osd_img.clear()
return 0
# 多目标检测 非最大值抑制方法实现
def nms(self,boxes,scores,thresh):
"""Pure Python NMS baseline."""
x1,y1,x2,y2 = boxes[:, 0],boxes[:, 1],boxes[:, 2],boxes[:, 3]
areas = (x2 - x1 + 1) * (y2 - y1 + 1)
order = np.argsort(scores,axis = 0)[::-1]
keep = []
while order.size > 0:
i = order[0]
keep.append(i)
new_x1,new_y1,new_x2,new_y2,new_areas = [],[],[],[],[]
for order_i in order:
new_x1.append(x1[order_i])
new_x2.append(x2[order_i])
new_y1.append(y1[order_i])
new_y2.append(y2[order_i])
new_areas.append(areas[order_i])
new_x1 = np.array(new_x1)
new_x2 = np.array(new_x2)
new_y1 = np.array(new_y1)
new_y2 = np.array(new_y2)
xx1 = np.maximum(x1[i], new_x1)
yy1 = np.maximum(y1[i], new_y1)
xx2 = np.minimum(x2[i], new_x2)
yy2 = np.minimum(y2[i], new_y2)
w = np.maximum(0.0, xx2 - xx1 + 1)
h = np.maximum(0.0, yy2 - yy1 + 1)
inter = w * h
new_areas = np.array(new_areas)
ovr = inter / (areas[i] + new_areas - inter)
new_order = []
for ovr_i,ind in enumerate(ovr):
if ind < thresh:
new_order.append(order[ovr_i])
order = np.array(new_order,dtype=np.uint8)
return keep
# 根据当前类别索引获取框的颜色
def get_color(self, x):
idx=x%len(self.color_four)
return self.color_four[idx]
if __name__=="__main__":
# 显示模式，默认"hdmi",可以选择"hdmi"和"lcd"
display_mode="hdmi"
if display_mode=="hdmi":
display_size=[1920,1080]
else:
display_size=[800,480]
# 模型路径
#kmodel_path="/sdcard/app/tests/kmodel/yolov8n_320.kmodel"
kmodel_path="/sdcard/examples/kmodel/yolov8n_320.kmodel"
labels = ["person", "bicycle", "car", "motorcycle", "airplane", "bus", "train", "truck", "boat", "traffic light", "fire hydrant", "stop sign", "parking meter", "bench", "bird", "cat", "dog", "horse", "sheep", "cow", "elephant", "bear", "zebra", "giraffe", "backpack", "umbrella", "handbag", "tie", "suitcase", "frisbee", "skis", "snowboard", "sports ball", "kite", "baseball bat", "baseball glove", "skateboard", "surfboard", "tennis racket", "bottle", "wine glass", "cup", "fork", "knife", "spoon", "bowl", "banana", "apple", "sandwich", "orange", "broccoli", "carrot", "hot dog", "pizza", "donut", "cake", "chair", "couch", "potted plant", "bed", "dining table", "toilet", "tv", "laptop", "mouse", "remote", "keyboard", "cell phone", "microwave", "oven", "toaster", "sink", "refrigerator", "book", "clock", "vase", "scissors", "teddy bear", "hair drier", "toothbrush"]
# 其它参数设置
confidence_threshold = 0.2
nms_threshold = 0.2
max_boxes_num = 50
rgb888p_size=[320,320]
phone_counts = 0
# 实例化FPIOA
fpioa = FPIOA()
fpioa.set_function(11, fpioa.UART2_TXD)
fpioa.set_function(12, fpioa.UART2_RXD)
# UART2: baudrate 115200, 8bits, parity none, one stopbits
uart = UART(UART.UART2, baudrate=115200, bits=UART.EIGHTBITS, parity=UART.PARITY_NONE, stop=UART.STOPBITS_ONE)
# 首次上电设置RTC日期和时间。(2024, 1, 1, 0, 0, 0, 0, 0)按顺序分别表示（年，月，日，星期，时，分，秒，微妙），
# 其中星期使用0-6表示星期一到星期日。
rtc = RTC()
if rtc.datetime()[0] != 2024:
rtc.datetime((2024, 8, 15, 0, 0, 0, 0, 0))
# 初始化PipeLine
pl=PipeLine(rgb888p_size=rgb888p_size,display_size=display_size,display_mode=display_mode)
pl.create()
# 初始化自定义目标检测实例
ob_det=ObjectDetectionApp(kmodel_path,labels=labels,model_input_size=[320,320],max_boxes_num=max_boxes_num,confidence_threshold=confidence_threshold,nms_threshold=nms_threshold,rgb888p_size=rgb888p_size,display_size=display_size,debug_mode=0)
ob_det.config_preprocess()
kkk=1
try:
while True:
os.exitpoint()
with ScopedTiming("total",0):
# 获取当前帧数据
img=pl.get_frame()
# 推理当前帧
res=ob_det.run(img)
# 绘制结果到PipeLine的osd图像
rets=ob_det.draw_result(pl,res)
if(rets>0):
phone_counts=phone_counts+1
if(phone_counts>5):
phone_counts=0
r = uart.write("1\r\n")
print("find phone ,like large than 55%\r\n")
#保存图片
dt=rtc.datetime()
save_img_path="/sdcard/%d%d%d%d%d%d.jpg"%(dt[0],dt[1],dt[2],dt[3],dt[4],dt[7])
print(save_img_path)
#img_jpg=pl.osd_img.to_rgb565()
#img_jpg.save(save_img_path)#保存JPG图片不正常，求助！！！！！！！！！
#text=uart.read(20) #接收20个字符
#if text != b'':
# print(text) #通过REPL打印串口2接收的数据
# 显示当前的绘制结果
pl.show_image()
#Display.show_image(pl.osd_img, 0, 0, Display.LAYER_OSD3)
gc.collect()
except Exception as e:
sys.print_exception(e)
finally:
ob_det.deinit()
pl.destroy()
