修改线程架构

reproject/analyzer.py

@@ -2,6 +2,8 @@ import cv2
 import mediapipe as mp
 import time
 import numpy as np
+import threading
+import queue
 from collections import deque
 from geometry_utils import (
     calculate_ear,
@@ -39,9 +41,6 @@ class MonitorSystem:
         # 初始化人脸底库
         self.face_lib = FaceLibrary(face_db)
 
-        # 状态变量
-        self.current_user = None
-
         # --- 时间控制 ---
         self.last_identity_check_time = 0
         self.IDENTITY_CHECK_INTERVAL = 2.0
@@ -61,6 +60,13 @@ class MonitorSystem:
         # 缓存上一次的检测结果
         self.cached_emotion = {"label": "detecting...", "va": (0.0, 0.0)}
 
+        self.task_queue = queue.Queue(maxsize=2)
+        self.current_user = None
+        self.current_emotion = "Neutral"
+
+        self.id_emo_thread = threading.Thread(target=self._id_emo_loop, daemon=True)
+        self.id_emo_thread.start()
+
     def _get_smoothed_value(self, history, current_val):
         """内部函数：计算滑动平均值"""
         history.append(current_val)
@@ -182,20 +188,18 @@ class MonitorSystem:
         now = time.time()
         # --- 身份识别 ---
         if now - self.last_identity_check_time > self.IDENTITY_CHECK_INTERVAL:
-            # xs = [l.x for l in landmarks]
-            # ys = [l.y for l in landmarks]
-            # # 计算人脸框
-            # face_loc = (
-            #     int(min(ys) * h), int(max(xs) * w),
-            #     int(max(ys) * h), int(min(xs) * w)
-            # )
-            # pad = 20
-            # face_loc = (max(0, face_loc[0]-pad), min(w, face_loc[1]+pad),
-            #             min(h, face_loc[2]+pad), max(0, face_loc[3]-pad))
+            sface_loc = (
+                int(min(ys) * h), int(max(xs) * w),
+                int(max(ys) * h), int(min(xs) * w)
+            )
+            spad = 20
+            sface_loc = (max(0, sface_loc[0]-spad), min(w, sface_loc[1]+spad),
+                        min(h, sface_loc[2]+spad), max(0, sface_loc[3]-spad))
+
+            if self.task_queue.full():
+                self.task_queue.get()
+            self.task_queue.put((rgb_frame.copy(), sface_loc, 0))
             
-            match_result = self.face_lib.identify(rgb_frame, face_location=face_loc)
-            if match_result:
-                self.current_user = match_result["info"]
             self.last_identity_check_time = now
 
         analysis_data["identity"] = self.current_user
@@ -204,10 +208,6 @@ class MonitorSystem:
         if HAS_EMOTION_MODULE and (
             now - self.last_emotion_check_time > self.EMOTION_CHECK_INTERVAL
         ):
-            if results.multi_face_landmarks:
-                landmarks = results.multi_face_landmarks[0].landmark
-                xs = [l.x for l in landmarks]
-                ys = [l.y for l in landmarks]
 
             # 计算裁剪坐标
             x_min = int(min(xs) * w)
@@ -215,15 +215,37 @@ class MonitorSystem:
             y_min = int(min(ys) * h)
             y_max = int(max(ys) * h)
 
-                pad_x = int((x_max - x_min) * 0.2)
-                pad_y = int((y_max - y_min) * 0.2)
+            pad_x = int((x_max - x_min) * 0.1)
+            pad_y = int((y_max - y_min) * 0.1)
 
             x_min = max(0, x_min - pad_x)
             x_max = min(w, x_max + pad_x)
             y_min = max(0, y_min - pad_y)
             y_max = min(h, y_max + pad_y)
             
-                face_crop = frame[y_min:y_max, x_min:x_max]
+            face_loc = (y_min, x_max, y_max, x_min)
+            
+            if self.task_queue.full():
+                self.task_queue.get()
+            self.task_queue.put((frame.copy(), face_loc, 1))
+
+            self.last_emotion_check_time = now
+
+        analysis_data["emotion_label"] = self.cached_emotion["label"]
+        analysis_data["emotion_va"] = self.cached_emotion["va"]
+
+        return analysis_data
+    
+    def _id_emo_loop(self):
+        while True:
+            try:
+                frame, face_loc, task_type = self.task_queue.get()
+                if task_type == 0:
+                    match_result = self.face_lib.identify(frame, face_location=face_loc)
+                    if match_result:
+                        self.current_user = match_result["info"]
+                elif task_type == 1 and HAS_EMOTION_MODULE:
+                    face_crop = frame[face_loc[0]:face_loc[2], face_loc[3]:face_loc[1]]
 
                     if face_crop.size > 0:
                         try:
@@ -238,10 +260,5 @@ class MonitorSystem:
 
                         except Exception as e:
                             print(f"情绪分析出错: {e}")
-
-            self.last_emotion_check_time = now
-
-        analysis_data["emotion_label"] = self.cached_emotion["label"]
-        analysis_data["emotion_va"] = self.cached_emotion["va"]
-
-        return analysis_data
+            except Exception as e:
+                print(f"线程处理出错: {e}")

reproject/main.py

@@ -262,15 +262,15 @@ def video_stream_thread():
     #     f"filesink location={filename} "
     # )
     # out = cv2.VideoWriter(gst_pipeline, cv2.CAP_GSTREAMER, 0, fps, (width, height))
-    out1 = cv2.VideoWriter('output1.mp4', fourcc, 30.0, (1280, 720))
-    out2 = cv2.VideoWriter('output2.mp4', fourcc, 30.0, (1280, 720))
+    # out1 = cv2.VideoWriter('output1.mp4', fourcc, 30.0, (1280, 720))
+    # out2 = cv2.VideoWriter('output2.mp4', fourcc, 30.0, (1280, 720))
     while not stop_event.is_set():
         try:
             frame = video_queue.get(timeout=1)
             # small_frame = cv2.resize(apply_soft_roi(frame), (1280, 720))
             server.provide_frame(frame)
-            out1.write(frame)
-            out2.write(frame)
+            # out1.write(frame)
+            # out2.write(frame)
         except queue.Empty:
             continue
         except Exception as e:
@@ -320,8 +320,8 @@ def video_stream_thread():
     #     except Exception as e:
     #         print(f"[Video] 重连中... {e}")
     #         time.sleep(3)
-    out1.release()
-    out2.release()
+    # out1.release()
+    # out2.release()
     print("[Video] 线程结束")