Spaces:
Sleeping
Sleeping
| # app.py — 無菌手套姿勢檢測系統（F-segment 偵測）複賽正式版 | |
| # 說明： | |
| # 1) 結合 Mediapipe Pose + Hands / 自動腰線偵測，並檢測雙手「腰部以上」與「指尖朝上」比例 | |
| # 2) AND 規則：腰部以上比例 >= PASS_TH_POS 且 指尖朝上比例 >= PASS_TH_UP 才算通過 | |
| # 3) 本版 UI 採「正式評圖版」精簡介面： | |
| # a. 上傳影片區塊 | |
| # b. 統整結果表 + CSV 下載 | |
| # c. 三個可展開的說明區塊（標註資訊 / 系統限制 / 未來改善） | |
| import os | |
| import cv2 | |
| import numpy as np | |
| import pandas as pd | |
| import tempfile | |
| import gradio as gr | |
| # ----------------------------------------------------------------------------- | |
| # Mediapipe 相關設定（若無法匯入，則自動降級為僅顯示錯誤） | |
| # ----------------------------------------------------------------------------- | |
| _HAS_MP = True | |
| _HAS_POSE = True | |
| try: | |
| import mediapipe as mp | |
| mp_hands = mp.solutions.hands | |
| mp_pose = mp.solutions.pose | |
| except Exception: | |
| _HAS_MP = False | |
| _HAS_POSE = False | |
| # ----------------------------------------------------------------------------- | |
| # 全域參數：可視為本系統的「版本設定」 | |
| # ----------------------------------------------------------------------------- | |
| MAX_LONG_SIDE = 960 # 影像長邊縮放上限（避免太大） | |
| # 自動腰線預設 | |
| DEFAULT_WAIST_RATIO = 0.65 | |
| CLAMP_LOW = 0.58 # 自動腰線 y 下限 | |
| CLAMP_HIGH = 0.72 # 自動腰線 y 上限 | |
| WAIST_DELTA_Y = -0.05 # 自動腰線 Δy 微調（負值代表往上移） | |
| # 判定門檻（本次複賽設定） | |
| PASS_TH_POS = 50 # 腰部門檻 (%) | |
| PASS_TH_UP = 40 # 指尖門檻 (%) | |
| # 其他固定設定 | |
| TAIL_MODE = "全片" # 本版一律分析全片 | |
| TAIL_SECONDS = 3.0 # 保留參數（若未來要開啟尾段模式可用） | |
| COLS = [ | |
| "檔案名稱", "檢測結果", "整體正確率(%)", "腰部以上(%)", "指尖朝上(%)", | |
| "通過幀/有效幀", "有效幀/總幀", "FPS", "長度(秒)", | |
| "門檻設定", "判斷區間", "腰線 y", "腰線來源" | |
| ] | |
| # ----------------------------------------------------------------------------- | |
| # 工具函式 | |
| # ----------------------------------------------------------------------------- | |
| def _to_path(f): | |
| """把 gr.File / dict / 字串 轉成實際檔案路徑。""" | |
| if isinstance(f, str): | |
| return f | |
| if hasattr(f, "name"): | |
| return f.name | |
| if isinstance(f, dict) and "name" in f: | |
| return f["name"] | |
| return str(f) | |
| def _resize_keep_ar(frame, max_long=MAX_LONG_SIDE): | |
| """依長邊等比例縮放，避免影像過大。""" | |
| h, w = frame.shape[:2] | |
| long_side = max(h, w) | |
| if long_side <= max_long: | |
| return frame | |
| scale = max_long / long_side | |
| nh, nw = int(h * scale), int(w * scale) | |
| return cv2.resize(frame, (nw, nh), interpolation=cv2.INTER_AREA) | |
| def _is_index_up(lms, h): | |
| """ | |
| 判斷單手的食指是否「明顯朝上」： | |
| - 利用 PIP→TIP 向量的角度 | |
| - 並考慮 tip 與 wrist 的高度差 | |
| """ | |
| tip = lms[mp_hands.HandLandmark.INDEX_FINGER_TIP.value] | |
| pip = lms[mp_hands.HandLandmark.INDEX_FINGER_PIP.value] | |
| wrist = lms[mp_hands.HandLandmark.WRIST.value] | |
| dy = (pip.y - tip.y) * h | |
| dx = abs(pip.x - tip.x) * h | |
| angle_deg = np.degrees(np.arctan2(dy, dx)) | |
| height_diff = (wrist.y - tip.y) * h | |
| return (angle_deg > 25) and (height_diff > 40) | |
| # ----------------------------------------------------------------------------- | |
| # 自動腰線估計：Pose / Wrist percentile | |
| # ----------------------------------------------------------------------------- | |
| def _auto_waist_ratio_pose(video_path, sample_frames=40, | |
| clamp_low=CLAMP_LOW, clamp_high=CLAMP_HIGH): | |
| """以 Pose hip 平均位置估計腰線比例 y。""" | |
| if not _HAS_POSE: | |
| return None | |
| cap = cv2.VideoCapture(video_path) | |
| if not cap.isOpened(): | |
| return None | |
| total = int(cap.get(cv2.CAP_PROP_FRAME_COUNT) or 0) | |
| if total <= 0: | |
| cap.release() | |
| return None | |
| step = max(1, total // sample_frames) | |
| ys = [] | |
| with mp_pose.Pose( | |
| model_complexity=0, | |
| enable_segmentation=False, | |
| min_detection_confidence=0.5, | |
| min_tracking_confidence=0.5 | |
| ) as pose: | |
| idx = 0 | |
| while idx < total and len(ys) < sample_frames: | |
| cap.set(cv2.CAP_PROP_POS_FRAMES, idx) | |
| ok, frame = cap.read() | |
| if not ok: | |
| break | |
| frame = _resize_keep_ar(frame) | |
| rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB) | |
| res = pose.process(rgb) | |
| if res.pose_landmarks: | |
| lms = res.pose_landmarks.landmark | |
| hip_y = (lms[23].y + lms[24].y) / 2.0 | |
| ys.append(hip_y) | |
| idx += step | |
| cap.release() | |
| if not ys: | |
| return None | |
| p = float(np.median(ys)) + WAIST_DELTA_Y | |
| return float(min(clamp_high, max(clamp_low, p))) | |
| def _auto_waist_ratio_hand(video_path, sample_frames=40, | |
| percentile=85, | |
| clamp_low=CLAMP_LOW, clamp_high=CLAMP_HIGH): | |
| """以手腕高度的分位數估計腰線比例 y（作為 Pose 的備援）。""" | |
| if not _HAS_MP: | |
| return DEFAULT_WAIST_RATIO | |
| cap = cv2.VideoCapture(video_path) | |
| if not cap.isOpened(): | |
| return DEFAULT_WAIST_RATIO | |
| total = int(cap.get(cv2.CAP_PROP_FRAME_COUNT) or 0) | |
| if total <= 0: | |
| cap.release() | |
| return DEFAULT_WAIST_RATIO | |
| step = max(1, total // sample_frames) | |
| ys = [] | |
| with mp_hands.Hands( | |
| static_image_mode=False, | |
| max_num_hands=2, | |
| model_complexity=0, | |
| min_detection_confidence=0.5, | |
| min_tracking_confidence=0.5 | |
| ) as hands: | |
| idx = 0 | |
| while idx < total and len(ys) < sample_frames: | |
| cap.set(cv2.CAP_PROP_POS_FRAMES, idx) | |
| ok, frame = cap.read() | |
| if not ok: | |
| break | |
| frame = _resize_keep_ar(frame) | |
| rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB) | |
| res = hands.process(rgb) | |
| if res.multi_hand_landmarks: | |
| wrist_ys = [ | |
| lm.landmark[mp_hands.HandLandmark.WRIST.value].y | |
| for lm in res.multi_hand_landmarks | |
| ] | |
| if wrist_ys: | |
| ys.append(max(wrist_ys)) | |
| idx += step | |
| cap.release() | |
| if not ys: | |
| return DEFAULT_WAIST_RATIO | |
| p = float(np.percentile(ys, percentile)) + WAIST_DELTA_Y | |
| return float(min(clamp_high, max(clamp_low, p))) | |
| # ----------------------------------------------------------------------------- | |
| # 單一影片分析 | |
| # ----------------------------------------------------------------------------- | |
| def analyze_one_video(video_path): | |
| """分析單一影片，回傳一列結果。""" | |
| cap = cv2.VideoCapture(video_path) | |
| if not cap.isOpened(): | |
| return [ | |
| os.path.basename(video_path), "未通過", | |
| 0, 0, 0, | |
| "0/0", "0/0", 0, 0, | |
| f"{PASS_TH_POS}/{PASS_TH_UP}", "-", | |
| "-", "開啟失敗" | |
| ] | |
| fps = cap.get(cv2.CAP_PROP_FPS) or 30.0 | |
| total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT) or 0) | |
| duration_s = (total_frames / fps) if total_frames > 0 else 0.0 | |
| # 本版設定只分析全片 | |
| start = 0 | |
| span = "全片" | |
| cap.set(cv2.CAP_PROP_POS_FRAMES, start) | |
| # 決定腰線位置 | |
| used_y_ratio = DEFAULT_WAIST_RATIO | |
| waist_source = "預設值" | |
| # 先嘗試 Pose，自動腰線 | |
| auto_pose = _auto_waist_ratio_pose(video_path) | |
| if auto_pose is not None: | |
| used_y_ratio = auto_pose | |
| waist_source = "Pose" | |
| else: | |
| # 若 Pose 不可靠，改採 Wrist percentile | |
| used_y_ratio = _auto_waist_ratio_hand(video_path) | |
| waist_source = "手腕分位數" | |
| hands = None | |
| if _HAS_MP: | |
| hands = mp_hands.Hands( | |
| static_image_mode=False, | |
| max_num_hands=2, | |
| model_complexity=0, | |
| min_detection_confidence=0.5, | |
| min_tracking_confidence=0.5 | |
| ) | |
| valid = ok_pos = ok_up = ok_both = 0 | |
| while True: | |
| ok, frame = cap.read() | |
| if not ok: | |
| break | |
| frame = _resize_keep_ar(frame) | |
| h, w = frame.shape[:2] | |
| y_ref = int(h * used_y_ratio) | |
| this_pos = this_up = False | |
| detected = False | |
| if _HAS_MP and hands: | |
| rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB) | |
| res = hands.process(rgb) | |
| if res.multi_hand_landmarks: | |
| detected = True | |
| pos_flags = [] | |
| up_flags = [] | |
| for lmset in res.multi_hand_landmarks: | |
| lms = lmset.landmark | |
| wrist = lms[mp_hands.HandLandmark.WRIST.value] | |
| pos_flags.append((wrist.y * h) <= y_ref) | |
| up_flags.append(_is_index_up(lms, h)) | |
| # 要求雙手皆符合（若只偵測到一手，就以那一手為準） | |
| if len(pos_flags) >= 2: | |
| this_pos = all(pos_flags[:2]) | |
| this_up = all(up_flags[:2]) | |
| else: | |
| this_pos = pos_flags[0] | |
| this_up = up_flags[0] | |
| if detected: | |
| valid += 1 | |
| if this_pos: | |
| ok_pos += 1 | |
| if this_up: | |
| ok_up += 1 | |
| if this_pos and this_up: | |
| ok_both += 1 | |
| cap.release() | |
| if hands: | |
| hands.close() | |
| if valid == 0: | |
| above_ratio = up_ratio = acc = 0.0 | |
| passed_valid = "0/0" | |
| else: | |
| above_ratio = (ok_pos / valid) * 100.0 | |
| up_ratio = (ok_up / valid) * 100.0 | |
| acc = (ok_both / valid) * 100.0 | |
| passed_valid = f"{ok_both}/{valid}" | |
| result_str = ( | |
| "通過" | |
| if (above_ratio >= PASS_TH_POS and up_ratio >= PASS_TH_UP) | |
| else "未通過" | |
| ) | |
| valid_total = f"{valid}/{total_frames}" | |
| return [ | |
| os.path.basename(video_path), result_str, | |
| round(acc, 2), round(above_ratio, 2), round(up_ratio, 2), | |
| passed_valid, valid_total, int(round(fps)), round(duration_s, 2), | |
| f"{int(PASS_TH_POS)}/{int(PASS_TH_UP)}", | |
| span, round(float(used_y_ratio), 3), waist_source | |
| ] | |
| # ----------------------------------------------------------------------------- | |
| # 多支影片分析核心 + 統整摘要 | |
| # ----------------------------------------------------------------------------- | |
| def run_core(files, state): | |
| """實際進行分析並回傳 df 和 CSV 路徑。""" | |
| if not files: | |
| df = pd.DataFrame([], columns=COLS) | |
| tmp_path = None | |
| return None, df, [], tmp_path | |
| rows = [] | |
| for f in files: | |
| path = _to_path(f) | |
| if os.path.exists(path): | |
| rows.append(analyze_one_video(path)) | |
| state_new = (state or []) + rows | |
| df = pd.DataFrame(state_new, columns=COLS) | |
| tmp = tempfile.NamedTemporaryFile(suffix=".csv", delete=False) | |
| df.to_csv(tmp.name, index=False, encoding="utf-8-sig") | |
| return files, df, state_new, tmp.name | |
| def build_summary_text(df: pd.DataFrame) -> str: | |
| """產生較完整的統整摘要。""" | |
| if df is None or df.empty: | |
| return "尚未進行分析。" | |
| total = len(df) | |
| passed = (df["檢測結果"] == "通過").sum() | |
| failed = total - passed | |
| pass_rate = (passed / total * 100.0) if total > 0 else 0.0 | |
| mean_acc = df["整體正確率(%)"].mean() | |
| mean_pos = df["腰部以上(%)"].mean() | |
| mean_up = df["指尖朝上(%)"].mean() | |
| best_row = df.loc[df["整體正確率(%)"].idxmax()] | |
| worst_row = df.loc[df["整體正確率(%)"].idxmin()] | |
| text = f"""### 📌 統整摘要 | |
| - 本次分析 **{total} 支影片**，其中 **{passed} 支通過、{failed} 支未通過**（通過率約 **{pass_rate:.1f}%**）。 | |
| - 平均整體正確率：約 **{mean_acc:.1f}%**。 | |
| - 平均腰部以上比例：約 **{mean_pos:.1f}%**；平均指尖朝上比例：約 **{mean_up:.1f}%**。 | |
| - 最佳表現影片：**{best_row['檔案名稱']}**（整體正確率 **{best_row['整體正確率(%)']:.1f}%**）。 | |
| - 需要特別留意的影片：**{worst_row['檔案名稱']}**（整體正確率 **{worst_row['整體正確率(%)']:.1f}%**）。 | |
| - 目前門檻設定：**腰部門檻 {PASS_TH_POS:.0f}%、指尖門檻 {PASS_TH_UP:.0f}%**，採 **AND 規則**（兩者皆需達標）。 | |
| - 腰線來源：優先使用 **Pose 腰點中位數自動估計**，必要時改採 **手腕高度分位數** 作為備援，並限制在安全範圍內。 | |
| """ | |
| return text | |
| def run_with_status(files, state): | |
| """供按鈕呼叫：更新狀態列 + DataFrame + CSV + 摘要。""" | |
| # 進入分析狀態 | |
| status_text = "🟠 系統正在分析影片，請稍候…" | |
| files2, df, state2, csv_path = run_core(files, state) | |
| summary_text = build_summary_text(df) | |
| # 分析完成狀態 | |
| status_text = "🟢 分析完成，可以檢視表格並下載 CSV 報表。" | |
| return status_text, files2, df, state2, csv_path, summary_text | |
| def do_clear(state): | |
| """清除按鈕：重置所有顯示。""" | |
| df = pd.DataFrame([], columns=COLS) | |
| status_text = "🟢 系統就緒，請上傳影片後按下「分析」。" | |
| return status_text, None, df, [], None, "尚未進行分析。" | |
| # ----------------------------------------------------------------------------- | |
| # Gradio UI 建構 | |
| # ----------------------------------------------------------------------------- | |
| with gr.Blocks( | |
| title="無菌手套姿勢檢測系統（F-segment 偵測）", | |
| css=""" | |
| #status-text { | |
| color: #1565c0; /* 深藍色狀態列 */ | |
| font-weight: 600; | |
| padding: 4px 0; | |
| } | |
| """ | |
| ) as demo: | |
| # 標題 | |
| gr.Markdown("# 👑 醫療技術AI王") | |
| gr.Markdown("## 🧤 無菌手套姿勢檢測系統（F-segment 偵測）") | |
| status_md = gr.Markdown( | |
| "🟢 系統就緒，請上傳影片後按下「分析」。", | |
| elem_id="status-text" | |
| ) | |
| # 上傳區 | |
| files = gr.File( | |
| label="上傳檢測影片（mp4，可多支）", | |
| file_types=[".mp4"], | |
| file_count="multiple" | |
| ) | |
| # 按鈕列 | |
| with gr.Row(): | |
| btn_run = gr.Button("分析", variant="primary", scale=1) | |
| btn_csv = gr.DownloadButton("下載 CSV 報表", visible=False, scale=1) | |
| btn_clear = gr.Button("清除", variant="secondary", scale=1) | |
| # 狀態儲存 | |
| table_state = gr.State([]) | |
| # 結果表格 | |
| table = gr.Dataframe( | |
| headers=COLS, | |
| label="📊 手套穿戴通過率彙整表", | |
| interactive=False, | |
| wrap=True | |
| ) | |
| # 統整摘要 | |
| summary = gr.Markdown("尚未進行分析。") | |
| # 額外說明面板（可收合） | |
| with gr.Accordion("📘 本次標註資訊（可展開）", open=False): | |
| gr.Markdown(""" | |
| ### 🔍 本次標註 | |
| - **標準片（應通過）**：FV3、FV4、FV5、FV6 | |
| - **錯片（應不通過）**：WFV6-2、WFV6 | |
| ### 🟡 邊界案例說明 | |
| - **FV5** | |
| - 臨床判定為「動作正確」，屬標準片。 | |
| - 目前版本採取較保守的腰線與門檻設定，在自動腰線估計偏高的情況下， | |
| 會被系統判為「未通過」，屬於安全邊界上的 **false negative（誤殺）**。 | |
| - 此設計反映系統的取捨：**寧可多擋一支可疑影片，也不輕易放過可能錯誤的動作。** | |
| """) | |
| with gr.Accordion("⚠️ 系統限制說明（可展開）", open=False): | |
| gr.Markdown(""" | |
| ### 📌 系統目前限制 | |
| - 受拍攝角度與距離影響：腰線位置與手部高度皆為 2D 投影，視角改變可能影響判斷。 | |
| - 光線與背景：低光源、強反光或背景雜訊會影響 Mediapipe 標記的穩定度。 | |
| - 動作抖動：快速移動或 motion blur 會降低有效幀比例，使通過率偏低。 | |
| """) | |
| with gr.Accordion("🚀 未來改善方向（可展開）", open=False): | |
| gr.Markdown(""" | |
| ### 🌱 系統優化方向 | |
| - 引入 YOLO / 其他手部偵測模型，提升各種光線與遮擋情境下的穩定度。 | |
| - 加入 temporal smoothing（時序平滑），降低單一錯誤幀對結果的影響。 | |
| - 導入影像前處理（亮度 / 對比度校正）以改善暗色環境的偵測品質。 | |
| - 若資料量充足，可進一步訓練專用的 F-segment 深度學習模型。 | |
| """) | |
| # 事件綁定：顯示 Gradio 內建 minimal 進度條即可 | |
| btn_run.click( | |
| fn=run_with_status, | |
| inputs=[files, table_state], | |
| outputs=[status_md, files, table, table_state, btn_csv, summary], | |
| show_progress="minimal" | |
| ) | |
| btn_clear.click( | |
| fn=do_clear, | |
| inputs=[table_state], | |
| outputs=[status_md, files, table, table_state, btn_csv, summary], | |
| show_progress="hidden" | |
| ) | |
| # ----------------------------------------------------------------------------- | |
| # 啟動（本地測試用；在 HuggingFace 會由 Spaces 自動呼叫 demo） | |
| # ----------------------------------------------------------------------------- | |
| if __name__ == "__main__": | |
| demo.launch(server_name="0.0.0.0", server_port=7860) | |