烟花爆竹门店AI监控识别预警算法：基于YOLOv10改进模型的边缘计算实战

import torch
import torch.nn as nn

class ChannelAttention(nn.Module):
    def __init__(self, in_planes, ratio=16):
        super(ChannelAttention, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.max_pool = nn.AdaptiveMaxPool2d(1)
        self.fc = nn.Sequential(nn.Conv2d(in_planes, in_planes // ratio, 1, bias=False),
                                nn.ReLU(),
                                nn.Conv2d(in_planes // ratio, in_planes, 1, bias=False))
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        avg_out = self.fc(self.avg_pool(x))
        max_out = self.fc(self.max_pool(x))
        out = avg_out + max_out
        return self.sigmoid(out)

class SpatialAttention(nn.Module):
    def __init__(self, kernel_size=7):
        super(SpatialAttention, self).__init__()
        self.conv1 = nn.Conv2d(2, 1, kernel_size, padding=kernel_size//2, bias=False)
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        avg_out = torch.mean(x, dim=1, keepdim=True)
        max_out, _ = torch.max(x, dim=1, keepdim=True)
        x = torch.cat([avg_out, max_out], dim=1)
        x = self.conv1(x)
        return self.sigmoid(x)

class CBAM(nn.Module):
    def __init__(self, in_planes, ratio=16, kernel_size=7):
        super(CBAM, self).__init__()
        self.ca = ChannelAttention(in_planes, ratio)
        self.sa = SpatialAttention(kernel_size)

    def forward(self, x):
        out = x * self.ca(x)
        out = out * self.sa(out)
        return out

# 集成到YOLOv10的C2f模块后
# 伪代码示例：
# self.cbam = CBAM(in_channels=512)
# x = self.cbam(x)

import asyncio

async def handle_risk_event(detection_result):
    """
    处理AI识别到的风险事件
    :param detection_result: 包含类别、置信度、坐标的字典
    """
    risk_type = detection_result['class']
    confidence = detection_result['confidence']
    
    # 设定置信度阈值，避免误报
    if confidence < 0.75:
        return

    print(f"⚠️ 检测到风险：{risk_type}，置信度：{confidence:.2f}")

    # 1. 本地语音警告（调用TTS或预录音频）
    await play_local_warning(risk_type)

    # 2. 上传证据至监管平台
    if risk_type in ['smoking', 'fire_smoke', 'over_piling']:
        await upload_evidence_to_cloud(detection_result['image_crop'], risk_type)
        
    # 3. 联动控制器（如触发排风系统，针对烟雾场景）
    if risk_type == 'fire_smoke':
        await trigger_ventilation_system()

async def play_local_warning(risk_type):
    warning_msgs = {
        'smoking': '警告！店内严禁吸烟，请立即熄灭！',
        'over_piling': '警告！货物堆放超高，存在倾倒风险！',
        'overcrowding': '警告！店内人员超限，请有序购买！',
        'outdoor_display': '警告！严禁店外摆放烟花爆竹！'
    }
    msg = warning_msgs.get(risk_type, '注意！您已违规操作！')
    print(f"🔊 播放语音：{msg}")
    # 实际开发中此处调用音频播放硬件接口

# 模拟运行
# asyncio.run(handle_risk_event({'class': 'smoking', 'confidence': 0.88, 'image_crop': 'img_001.jpg'}))