使用TensorFlow和PyCharm为Reachy Mini构建实时物体检测应用

!pip install tensorflow tensorflow-hub opencv-python numpy Pillow

import tensorflow as tf
import tensorflow_hub as hub
import numpy as np
import cv2
import time
from IPython.display import display, clear_output
from PIL import Image

MODEL_HANDLE = "https://tfhub.dev/google/openimages_v4/ssd/mobilenet_v2/1"

print(f"TensorFlow 版本: {tf.__version__}")
print("正在加载模型（首次下载约30MB）...")

detector = hub.load(MODEL_HANDLE)
print("模型加载完成！")

def detect_objects(frame_bgr, min_score=0.5, max_detections=10):
    rgb = frame_bgr[:, :, ::-1]
    img_tensor = tf.image.convert_image_dtype(rgb, tf.float32)[tf.newaxis, ...]

    results = detector.signatures['default'](img_tensor)

    boxes = np.array(results["detection_boxes"])
    scores = np.array(results["detection_scores"])
    class_labels = np.array(results["detection_class_entities"])

    if boxes.ndim > 2:
        boxes = boxes[0]
    if scores.ndim > 1:
        scores = scores[0]
    if class_labels.ndim > 1:
        class_labels = class_labels[0]

    scores = np.atleast_1d(scores)
    indices = [i for i, score in enumerate(scores) if score >= min_score][:max_detections]

    detections = []
    for idx in indices:
        ymin, xmin, ymax, xmax = boxes[idx]
        label = class_labels[idx].decode('utf-8') if isinstance(class_labels[idx], bytes) else str(class_labels[idx])
        detections.append({
            "box": [ymin, xmin, ymax, xmax],
            "score": float(scores[idx]),
            "label": label
        })

    return detections


def draw_detections(frame_bgr, detections):
    h, w = frame_bgr.shape[:2]
    annotated = frame_bgr.copy()

    for det in detections:
        ymin, xmin, ymax, xmax = det["box"]
        x1, y1 = int(xmin * w), int(ymin * h)
        x2, y2 = int(xmax * w), int(ymax * h)

        color = (0, 255, 0)
        cv2.rectangle(annotated, (x1, y1), (x2, y2), color, 2)

        label = f"{det['label']} {det['score']:.0%}"
        font_scale, thickness = 0.6, 2
        (tw, th), _ = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, font_scale, thickness)
        cv2.rectangle(annotated, (x1, y1 - th - 8), (x1 + tw + 4, y1), color, -1)
        cv2.putText(annotated, label, (x1 + 2, y1 - 4),
                    cv2.FONT_HERSHEY_SIMPLEX, font_scale, (0, 0, 0), thickness)

    return annotated

cap = cv2.VideoCapture(0)
ret, frame = cap.read()
cap.release()

if not ret:
    print("错误：无法访问摄像头。请确保没有其他应用在使用它。")
else:
    print(f"帧已捕获: {frame.shape}")

    t0 = time.time()
    detections = detect_objects(frame)
    elapsed = time.time() - t0

    print(f"推理时间: {elapsed:.2f}s ({1/elapsed:.1f} FPS)")
    print(f"找到 {len(detections)} 个对象:")
    for d in detections:
        print(f"  - {d['label']}: {d['score']:.0%}")

    annotated = draw_detections(frame, detections)
    display(Image.fromarray(annotated[:, :, ::-1]))

cap = cv2.VideoCapture(0)

if not cap.isOpened():
    print("错误：无法打开摄像头。")
else:
    print("正在运行实时检测... (中断内核以停止)")
    try:
        while True:
            ret, frame = cap.read()
            if not ret:
                break

            t0 = time.time()
            detections = detect_objects(frame)
            fps = 1.0 / max(time.time() - t0, 0.001)

            annotated = draw_detections(frame, detections)
            cv2.putText(annotated, f"{fps:.1f} FPS", (10, 30),
                        cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0, 0, 255), 2)

            clear_output(wait=True)
            display(Image.fromarray(annotated[:, :, ::-1]))

            labels = ", ".join(f"{d['label']} ({d['score']:.0%})" for d in detections)
            print(f"{fps:.1f} FPS | {len(detections)} 个对象: {labels or '无'}")

    except KeyboardInterrupt:
        print("已停止。")
    finally:
        cap.release()
        print("摄像头已释放。")

reachy_mini_object_detector/
├── pyproject.toml
└── reachy_mini_object_detector/
    ├── detector.py       # TF Hub 模型封装
    ├── main.py           # 应用：头部跟踪 + Web 仪表盘
    └── static/           # Web UI 资源（在 :8042 端口提供）

pip install git+https://huggingface.co/spaces/backtoengineering/reachy_mini_object_detector

target_yaw = -(largest.center_x - 0.5) * CAMERA_FOV_H_DEG
target_pitch = (largest.center_y - 0.5) * CAMERA_FOV_V_DEG

self._current_yaw += TRACKING_ALPHA * (target_yaw - self._current_yaw)
self._current_pitch += TRACKING_ALPHA * (target_pitch - self._current_pitch)

phase = (t - t0) * 8.0  # 快速摆动
antenna_val = np.deg2rad(20.0 * np.sin(phase))
antennas = np.array([antenna_val, -antenna_val])