【python】OpenCV—Hand Detection

---

更多有趣的代码示例，可参考【Programming】

---

1、功能描述

基于 opencv-python 和 mediapipe 进行手部检测

2、代码实现

导入必要的库函数

import cv2
import mediapipe as mp

进入主程序首先实例化 HandDetector() 类，读入图片，调用 find_hands 方法实现手部检测

if __name__ == "__main__":detector = HandDetector()img = cv2.imread("1.jpg")img, results = detector.find_hands(img)

HandDetector 类初始化如下，主要是配置好 mediapipe 的手部关键点检测算子以及可视化工具

class HandDetector:def __init__(self, static_mode=False, max_hands=2, detection_confidence=0.5, tracking_confidence=0.5):self.static_mode = static_modeself.max_hands = max_handsself.detection_confidence = detection_confidenceself.tracking_confidence = tracking_confidenceself.mp_hands = mp.solutions.handsself.hands = self.mp_hands.Hands(static_image_mode=static_mode,max_num_hands=max_hands,min_detection_confidence=detection_confidence,min_tracking_confidence=tracking_confidence)self.mp_drawing = mp.solutions.drawing_utilsself.mp_drawing_styles = mp.solutions.drawing_styles

find_hands 方法实现如下，用于检测手部关键点，并返回绘制后的图片（mediapipe绘制的）和检测结果

    def find_hands(self, img, draw=True):img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)self.results = self.hands.process(img_rgb)if self.results.multi_hand_landmarks and draw:for hand_landmarks in self.results.multi_hand_landmarks:self.mp_drawing.draw_landmarks(img,hand_landmarks,self.mp_hands.HAND_CONNECTIONS,self.mp_drawing_styles.get_default_hand_landmarks_style(),self.mp_drawing_styles.get_default_hand_connections_style())return img, self.results

接下来调用 find_positions 方法，根据手部关键点，找出手部检测框

    lm_list, bbox = detector.find_positions(img, hand_index=0)

find_positions 方法实现如下，遍历手部关键点，保存最大最小横纵坐标，在此基础上，外扩（w+h）/ 2 的一定比例，返回关键点列表和手部检测框

    def find_positions(self, img, hand_index=0):h, w, c = img.shapelandmark_list = []bbox = [0, 0, 0, 0]  # x_min, y_min, x_max, y_max# Check if any hands detectedif not self.results.multi_hand_landmarks:return landmark_list, bbox# Check if requested hand index existsif hand_index >= len(self.results.multi_hand_landmarks):return landmark_list, bbox# Extract hand landmarkshand = self.results.multi_hand_landmarks[hand_index]# Initialize bounding box coordinatesx_min, y_min = w, hx_max, y_max = 0, 0# Process each landmarkfor id, lm in enumerate(hand.landmark):# Convert normalized coordinates to pixel coordinatescx, cy, cz = int(lm.x * w), int(lm.y * h), lm.zlandmark_list.append([id, cx, cy, cz])# Update bounding boxx_min = min(x_min, cx)y_min = min(y_min, cy)x_max = max(x_max, cx)y_max = max(y_max, cy)# Add padding to bounding boxpadding = int((y_max - y_min + x_max - x_min) * 0.1 / 2)bbox = [max(0, x_min - padding),max(0, y_min - padding),min(w, x_max + padding),min(h, y_max + padding)]return landmark_list, bbox

如果检测出来了关键点，调用 get_hand_type 获取检测出来的是左手还是右手，调用 draw_bounding_box 方法绘制手部矩形框

    if lm_list:hand_type = detector.get_hand_type(0)img = detector.draw_bounding_box(img, bbox, hand_type)# 绘制某一个关键点# if len(lm_list) > 8:#     cv2.circle(img, (lm_list[8][1], lm_list[8][2]), 5, (255, 0, 255), cv2.FILLED)

get_hand_type方法实现如下，调用 mediapipe 的接口获取左手 or 右手

    def get_hand_type(self, idx=0):if not self.results.multi_hand_landmarks:return Noneif idx >= len(self.results.multi_handedness):return None# Get hand type from classificationhand_type = self.results.multi_handedness[idx].classification[0].labelreturn hand_type

draw_bounding_box 方法实现如下，绘制矩形框，写上左手 or 右手标签

    def draw_bounding_box(self, img, bbox, hand_label="Hand"):x_min, y_min, x_max, y_max = bboxcv2.rectangle(img, (x_min, y_min), (x_max, y_max), (0, 255, 0), 2)cv2.putText(img, hand_label, (x_min, y_min - 10),cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 255, 0), 2)return img

最后，展示检测结果，保存检测结果，退出后关闭所有窗口

    cv2.imshow("Hand Detector", img)cv2.imwrite("result.jpg", img)cv2.waitKey(0)cv2.destroyAllWindows()

3、效果展示

输入图片

输出结果

需要绘制两个手的话改改代码

    detector = HandDetector()img = cv2.imread("2.jpg")img, results = detector.find_hands(img)for i in range(2):lm_list, bbox = detector.find_positions(img, hand_index=i)if lm_list:hand_type = detector.get_hand_type(i)img = detector.draw_bounding_box(img, bbox, hand_type)# 绘制某一个关键点# if len(lm_list) > 8:#     cv2.circle(img, (lm_list[8][1], lm_list[8][2]), 5, (255, 0, 255), cv2.FILLED)cv2.imshow("Hand Detector", img)cv2.imwrite("result.jpg", img)cv2.waitKey(0)cv2.destroyAllWindows()

输入图片

输出图片

4、完整代码

import cv2
import mediapipe as mpclass HandDetector:def __init__(self, static_mode=False, max_hands=2, detection_confidence=0.5, tracking_confidence=0.5):self.static_mode = static_modeself.max_hands = max_handsself.detection_confidence = detection_confidenceself.tracking_confidence = tracking_confidenceself.mp_hands = mp.solutions.handsself.hands = self.mp_hands.Hands(static_image_mode=static_mode,max_num_hands=max_hands,min_detection_confidence=detection_confidence,min_tracking_confidence=tracking_confidence)self.mp_drawing = mp.solutions.drawing_utilsself.mp_drawing_styles = mp.solutions.drawing_stylesdef find_hands(self, img, draw=True):img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)self.results = self.hands.process(img_rgb)if self.results.multi_hand_landmarks and draw:for hand_landmarks in self.results.multi_hand_landmarks:self.mp_drawing.draw_landmarks(img,hand_landmarks,self.mp_hands.HAND_CONNECTIONS,self.mp_drawing_styles.get_default_hand_landmarks_style(),self.mp_drawing_styles.get_default_hand_connections_style())return img, self.resultsdef find_positions(self, img, hand_index=0):h, w, c = img.shapelandmark_list = []bbox = [0, 0, 0, 0]  # x_min, y_min, x_max, y_max# Check if any hands detectedif not self.results.multi_hand_landmarks:return landmark_list, bbox# Check if requested hand index existsif hand_index >= len(self.results.multi_hand_landmarks):return landmark_list, bbox# Extract hand landmarkshand = self.results.multi_hand_landmarks[hand_index]# Initialize bounding box coordinatesx_min, y_min = w, hx_max, y_max = 0, 0# Process each landmarkfor id, lm in enumerate(hand.landmark):# Convert normalized coordinates to pixel coordinatescx, cy, cz = int(lm.x * w), int(lm.y * h), lm.zlandmark_list.append([id, cx, cy, cz])# Update bounding boxx_min = min(x_min, cx)y_min = min(y_min, cy)x_max = max(x_max, cx)y_max = max(y_max, cy)# Add padding to bounding boxpadding = int((y_max - y_min + x_max - x_min) * 0.1 / 2)bbox = [max(0, x_min - padding),max(0, y_min - padding),min(w, x_max + padding),min(h, y_max + padding)]return landmark_list, bboxdef draw_bounding_box(self, img, bbox, hand_label="Hand"):x_min, y_min, x_max, y_max = bboxcv2.rectangle(img, (x_min, y_min), (x_max, y_max), (0, 255, 0), 2)cv2.putText(img, hand_label, (x_min, y_min - 10),cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 255, 0), 2)return imgdef get_hand_type(self, idx=0):if not self.results.multi_hand_landmarks:return Noneif idx >= len(self.results.multi_handedness):return None# Get hand type from classificationhand_type = self.results.multi_handedness[idx].classification[0].labelreturn hand_typeif __name__ == "__main__":detector = HandDetector()img = cv2.imread("1.jpg")img, results = detector.find_hands(img)lm_list, bbox = detector.find_positions(img, hand_index=0)if lm_list:hand_type = detector.get_hand_type(0)img = detector.draw_bounding_box(img, bbox, hand_type)# 绘制某一个关键点# if len(lm_list) > 8:#     cv2.circle(img, (lm_list[8][1], lm_list[8][2]), 5, (255, 0, 255), cv2.FILLED)cv2.imshow("Hand Detector", img)cv2.imwrite("result.jpg", img)cv2.waitKey(0)cv2.destroyAllWindows()

5、参考

• https://github.com/Sxhail/Hand-Detection-Model/blob/main/hand_detector.py
• 【python】OpenCV—Hand Landmarks Detection

6、其它手部检测和手势识别的方案

手检测：深度图，Tiny YOLOv3

https://github.com/LadaOndris/hand-recognition

It consists of hand detection, hand pose estimation, and gesture classification.

---

手检测：yolov3、yolov4

https://github.com/cansik/yolo-hand-detection

数据集： CMU Hand DB dataset + Egohands dataset

---

手检测：检测，朝向

This project utilizes a modified MobileNet in company with the SSD framework to achieve a robust and fast detection of hand location and orientation.

https://github.com/yangli18/hand_detection

---

手检测：yolov4

https://github.com/ehsainit/yolo-hand-detection

训练数据集 http://vision.soic.indiana.edu/projects/egohands/

---

手检测：yolov5

https://github.com/siriusdemon/hand-yolov5/tree/main

---

手检测：多边形矩形框，yolov7，COCO-Hand data.

https://github.com/nuwandda/yolov7-hand-detection?tab=readme-ov-file

https://www3.cs.stonybrook.edu/~cvl/projects/hand_det_attention/

---

手检测多边形矩形框：https://github.com/SupreethN/Hand-CNN

论文 Contextual Attention for Hand Detection in the Wild, International Conference on Computer Vision (ICCV), 2019. 的源码

---

忍法：大坝谁修哈

https://github.com/Kazuhito00/NARUTO-HandSignDetection

---

手势检测：火影忍者，yolov11

https://github.com/Jannat-Javed/Naruto-Hand-Seals-Detection

---

更多有趣的代码示例，可参考【Programming】