Sipeed MAix BiT AIoT 开发套件测评-进阶应用探索

zygalaxy

Sipeed MAix BiT AIoT 开发套件测评-进阶应用探索 [复制链接]

<div class='showpostmsg'><i class="pstatus"> 本帖最后由 zygalaxy 于 2024-8-1 21:46 编辑 </i>

# 屏幕与摄像头集成应用 
屏幕与摄像头集成应用 时间规划：评测第五天至第六天 内容要点：   综合应用实例：设计一个结合屏幕显示与摄像头输入的小型项目，如实时监控系统原型，评估套件在实际应用中的表现和灵活性。
## 时间规划

- **评测第五天至第六天**

## 内容要点

### 屏幕显示效果

- 测试不同分辨率、色彩深度的图像显示，评价屏幕的亮度、对比度及视角。

<ignore_js_op>

<div class="tip tip_4 aimg_tip" id="aimg_828888_menu" style="position: absolute; display: none" disautofocus="true">
<div class="xs0">
<p><strong>Snipaste_2024-08-01_21-15-28.png</strong> <em class="xg1">(23.57 KB, 下载次数: 0)</em></p>
<p>
<a href="javascript:;" class="loginf" >下载附件</a>

<a href="javascript:;" onclick="showWindow(this.id, this.getAttribute('url'), 'get', 0);" id="savephoto_828888" url="home.php?mod=spacecp&ac=album&op=saveforumphoto&aid=828888&handlekey=savephoto_828888">保存到相册</a>

</p>

</div>
<div class="tip_horn"></div>
</div>

</ignore_js_op>

套件自带的屏幕是一款2.4寸的屏幕，显示图像信息比较细腻，正好比较适合k210的图像显示，能够在尽量不模糊的情况下保证显示得清晰

### 摄像头数据采集与处理：

- 编写程序实现摄像头数据的实时采集，并进行基础图像处理或AI分析，如人脸识别、物体追踪等。

以人脸检测为例子：

进入Maixpy hub 下载模型
https://dl.sipeed.com/MAIX/MaixPy/model

下载 face_model_at_0x300000.kfpkg 这个模型文件
 
用 kflash_gui 下载模型到 Flash， 或者放到 SD 卡中

```python

import sensor, image, lcd, time
import KPU as kpu
import gc, sys

def lcd_show_except(e):
    import uio
    err_str = uio.StringIO()
    sys.print_exception(e, err_str)
    err_str = err_str.getvalue()
    img = image.Image(size=(224,224))
    img.draw_string(0, 10, err_str, scale=1, color=(0xff,0x00,0x00))
    lcd.display(img)

def main(model_addr=0x300000, lcd_rotation=0, sensor_hmirror=False, sensor_vflip=False):
    try:
        sensor.reset()
    except Exception as e:
        raise Exception("sensor reset fail, please check hardware connection, or hardware damaged! err: {}".format(e))
    sensor.set_pixformat(sensor.RGB565)
    sensor.set_framesize(sensor.QVGA)
    sensor.set_hmirror(sensor_hmirror)
    sensor.set_vflip(sensor_vflip)
    sensor.run(1)

lcd.init(type=1)
    lcd.rotation(lcd_rotation)
    lcd.clear(lcd.WHITE)

anchors = (1.889, 2.5245, 2.9465, 3.94056, 3.99987, 5.3658, 5.155437, 6.92275, 6.718375, 9.01025)
    try:
        task = None
        task = kpu.load(model_addr)
        kpu.init_yolo2(task, 0.5, 0.3, 5, anchors) # threshold:[0,1], nms_value: [0, 1]
        while(True):
            img = sensor.snapshot()
            t = time.ticks_ms()
            objects = kpu.run_yolo2(task, img)
            t = time.ticks_ms() - t
            if objects:
                for obj in objects:
                    img.draw_rectangle(obj.rect())
            img.draw_string(0, 200, "t:%dms" %(t), scale=2)
            lcd.display(img)
    except Exception as e:
        raise e
    finally:
        if not task is None:
            kpu.deinit(task)

if __name__ == "__main__":
    try:
        main( model_addr=0x300000, lcd_rotation=0, sensor_hmirror=False, sensor_vflip=False)
        # main(model_addr="/sd/m.kmodel")
    except Exception as e:
        sys.print_exception(e)
        lcd_show_except(e)
    finally:
        gc.collect()
```

### 综合应用实例

- 设计一个结合屏幕显示与摄像头输入的小型项目，如实时监控系统原型，评估套件在实际应用中的表现和灵活性。
---

实现一个人脸预警平台:``基于LTE网络的人脸识别预警系统``

项目实现的思路：
1.K210开发板使用ov2640摄像头模块读取当前环境中人脸信息，k210使用yolov2训练的模型进行推理，当检测到人脸信息时，k210把图像信息转化为16进制数据通过串口通信方式，与air780epv模块通过相连接，采用数据包发送模式，通过TCP协议向后端发送16进制图片信息。
后端flask通过socket接受来自k210的16进制图片信息，接收完成后将16进制数据使用opencv转换为2进制图片数据，使用opencv库再次还原为原始图片信息，同时通过websocket向前端发送检测信息，并且通过发送邮件方式给注册的用户发送预警邮件。
2.前端通过websocket通信方式接收来自后端传输的信息，并展示在实时监测页面，可以在网页查看历史人脸检测信息，同时在控制台可以通过echarts可视化查看目前系统预警次数，使数据更加清晰明了。

实现的代码：

前端关键代码：
```javascript
<template>
	<el-card>
		<template #header>
			监测数据
			<el-text size="small">数据更新时间：{{ currentTime }}</el-text>
		</template>
		
		<div class="detect-wrap w-full">
			<div class="img-wrap flex justify-between" v-if="isDetect">
				<img  class="w-1/2 max-h-[60vh]" : src="imgsrc"  alt=""  onclick="zoom(this, this.getAttribute('zoomfile'), 0, 0, '0')" zoomfile="" file="" inpost="1" onmouseover="showMenu({'ctrlid':this.id,'pos':'12'})" lazyloaded="true" initialized="true">
				<div
					class="text flex justify-center flex-col items-center flex-1"
				>
					<el-button type="danger">已检测到</el-button>
					检测时间：{{ currentTime }}
				</div>
			</div>
			<el-empty
				v-else
				description="当前暂无识别到人脸,请等待连接成功与识别"
			/>
		</div>
	</el-card>
</template>
```

后端关键代码：
```python
def receive_data():
    while True:
        client_socket, addr = server_socket.accept()  # 接受客户端连接
        print(f'Connected to {addr}')

start_marker = b'0x54'
        stop_marker = b'0x50'
        full_data = b''

while True:
            data = client_socket.recv(4096)

if not data:
                break

full_data += data

# 搜索当前接收的数据块中是否存在停止位
            stop_pos = data.find(stop_marker)
            if stop_pos != -1:
                # 如果找到了停止位，截取从起始位到停止位之间的数据作为有效数据
                start_pos = full_data.find(start_marker)
                if start_pos != -1:
                    valid_data = full_data[start_pos + len(start_marker):stop_pos]
                    # print("Received data:", valid_data.decode('utf-8'))
                    print("Received data:")
                else:
                    print("Warning: Start marker not found before stop marker.")

print("Reception complete.")
                break

# print("Received data chunk:", data.decode('utf-8'), "(waiting for stop marker)")
            print("Received data chunk:", "(waiting for stop marker)")

# 继续接收数据
            # time.sleep(1)  # 可能需要短暂延时，确保模块已切换到接收状态

# 如果循环正常结束（未接收到停止位），处理剩余数据
        if full_data.endswith(stop_marker):
            # print("Received data:", full_data[len(start_marker):-len(stop_marker)].decode('utf-8'))
            print("Received data:", )

print("Reception complete.")
            try:
                img_bytes = binascii.unhexlify(full_data[len(start_marker):-len(stop_marker)])
                # print(img_bytes)
                timestamp = str(int(time.time() * 1000))
                img_path = f'./static/{timestamp}.jpg'
                with open(img_path, 'wb') as f:
                    f.write(img_bytes)
                    # 需要添加ip地址
                    with app.app_context():
                        detect_history = DetectHistory(image='http://localhost:5000' + f'/static/{timestamp}.jpg',
                                                       time=timestamp)
                        db.session.add(detect_history)
                        db.session.commit()
                        db.session.close()
                        # 查询数据库所有用户邮箱

# 发送邮件
                        # 读取本地email文件
                        receivers = []

# Read emails from the file and append to the list
                        # with open('email.txt', 'r') as f:
                        #     for line in f:
                        #         receivers.append(line.strip())
                        #
                        users = User.query.all()
                        for user in users:
                            if user.email in receivers:
                                continue
                            else:
                                receivers.append(user.email)
                        for receiver in receivers:
                            msg = Message("预警信息",
                                          sender=app.config['MAIL_DEFAULT_SENDER'],
                                          recipients=[receiver])
                            msg.body = "检测到人脸"
                            msg.attach("image.jpg", "image/jpg", img_bytes)
                            mail.send(msg)

socketio.emit('detect', {
                        'image': 'http://localhost:5000' + f'/static/{timestamp}.jpg',
                        'timestamp': timestamp
                    })
            except Exception as e:
                print(e)
                print("Error occurred while processing data.")
                # continue

else:
        print("Warning: Reception incomplete. Stop marker not found.")

client_socket.close()  # 关闭连接

```

项目部分页面展示：

<ignore_js_op>

<div class="tip tip_4 aimg_tip" id="aimg_828889_menu" style="position: absolute; display: none" disautofocus="true">
<div class="xs0">
<p><strong>Snipaste_2024-08-01_21-36-18.png</strong> <em class="xg1">(34.78 KB, 下载次数: 0)</em></p>
<p>
<a href="javascript:;" class="loginf" >下载附件</a>

<a href="javascript:;" onclick="showWindow(this.id, this.getAttribute('url'), 'get', 0);" id="savephoto_828889" url="home.php?mod=spacecp&ac=album&op=saveforumphoto&aid=828889&handlekey=savephoto_828889">保存到相册</a>

</p>

</div>
<div class="tip_horn"></div>
</div>

</ignore_js_op>

<ignore_js_op>

<div class="tip tip_4 aimg_tip" id="aimg_828890_menu" style="position: absolute; display: none" disautofocus="true">
<div class="xs0">
<p><strong>Snipaste_2024-08-01_21-36-36.png</strong> <em class="xg1">(53.56 KB, 下载次数: 0)</em></p>
<p>
<a href="javascript:;" class="loginf" >下载附件</a>

<a href="javascript:;" onclick="showWindow(this.id, this.getAttribute('url'), 'get', 0);" id="savephoto_828890" url="home.php?mod=spacecp&ac=album&op=saveforumphoto&aid=828890&handlekey=savephoto_828890">保存到相册</a>

</p>

</div>
<div class="tip_horn"></div>
</div>

</ignore_js_op>

<ignore_js_op>

<div class="tip tip_4 aimg_tip" id="aimg_828891_menu" style="position: absolute; display: none" disautofocus="true">
<div class="xs0">
<p><strong>Snipaste_2024-08-01_21-36-46.png</strong> <em class="xg1">(45.87 KB, 下载次数: 0)</em></p>
<p>
<a href="javascript:;" class="loginf" >下载附件</a>

<a href="javascript:;" onclick="showWindow(this.id, this.getAttribute('url'), 'get', 0);" id="savephoto_828891" url="home.php?mod=spacecp&ac=album&op=saveforumphoto&aid=828891&handlekey=savephoto_828891">保存到相册</a>

</p>

</div>
<div class="tip_horn"></div>
</div>

</ignore_js_op>

<ignore_js_op>

<div class="tip tip_4 aimg_tip" id="aimg_828892_menu" style="position: absolute; display: none" disautofocus="true">
<div class="xs0">
<p><strong>Snipaste_2024-08-01_21-37-45.png</strong> <em class="xg1">(51.03 KB, 下载次数: 0)</em></p>
<p>
<a href="javascript:;" class="loginf" >下载附件</a>

<a href="javascript:;" onclick="showWindow(this.id, this.getAttribute('url'), 'get', 0);" id="savephoto_828892" url="home.php?mod=spacecp&ac=album&op=saveforumphoto&aid=828892&handlekey=savephoto_828892">保存到相册</a>

</p>

</div>
<div class="tip_horn"></div>
</div>

</ignore_js_op>

套件在项目中的发挥了重要的作用，因为k210使用起来功能强大，加速了项目的开发，并为项目的添加了更多的新能力。

</div><script>					var loginstr = '<div class="locked">查看本帖全部内容，请<a href="javascript:;"   style="color:#e60000" class="loginf">登录</a>或者<a href="https://bbs.eeworld.com.cn/member.php?mod=register_eeworld.php&action=wechat" style="color:#e60000" target="_blank">注册</a></div>';
					
					if(parseInt(discuz_uid)==0){
						
					}		</script><script type="text/javascript">(function(d,c){var a=d.createElement("script"),m=d.getElementsByTagName("script")[0],eewurl="//counter.eeworld.com.cn/pv/count/";a.src=eewurl+c;m.parentNode.insertBefore(a,m)})(document,523)</script>