为何黑色图像上绘制的人体坐标点无法自动消失？技术求助

问题描述 #

我在黑色窗口上绘制人体坐标点，但当画面中没有人体时，这些坐标点仍会保留，无法正常消失。相关代码如下：

import cv2
import numpy as np
import mediapipe as mp
# Create a VideoCapture object and read from input file
# If the input is the camera, pass 0 instead of the video file name
cap = cv2.VideoCapture('show.mp4')
height,width=480,852
blank_image = np.zeros((height,width,3), np.uint8)

mp_drawing = mp.solutions.drawing_utils
mp_pose = mp.solutions.pose
with mp_pose.Pose(min_detection_confidence=0.5, min_tracking_confidence=0.5) as pose:
    while (cap.isOpened()):

        ret, frame = cap.read()
        if ret :
            image = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
            image.flags.writeable = False
            results=pose.process(image)
            image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
            mp_drawing.draw_landmarks(blank_image, results.pose_landmarks, mp_pose.POSE_CONNECTIONS,
                                      mp_drawing.DrawingSpec(color=(245, 117, 66), thickness=2, circle_radius=2),
                                      mp_drawing.DrawingSpec(color=(245, 66, 230), thickness=2, circle_radius=2)
                                      )
            cv2.imshow("",image)
            cv2.imshow(" ",blank_image)
            if cv2.waitKey(25) & 0xFF == ord('q'):
                break

        # Break the loop
        else:
            break

# When everything done, release the video capture object
cap.release()

# Closes all the frames
cv2.destroyAllWindows()

效果截图：

经测试，原视频帧窗口上的关键点会随画面刷新消失，但黑色窗口上的点始终残留。

问题原因 #

blank_image是在循环外部初始化的，每次调用draw_landmarks都是在同一个图像上叠加绘制，即使没有检测到人体，之前的绘制内容也不会自动清除。而原视频帧窗口每次都会加载新的帧画面，所以关键点能正常消失。

解决方案 #

每次循环时重新创建黑色背景图，并且仅在检测到人体关键点时执行绘制操作：

import cv2
import numpy as np
import mediapipe as mp

cap = cv2.VideoCapture('show.mp4')
height, width = 480, 852

mp_drawing = mp.solutions.drawing_utils
mp_pose = mp.solutions.pose

with mp_pose.Pose(min_detection_confidence=0.5, min_tracking_confidence=0.5) as pose:
    while cap.isOpened():
        ret, frame = cap.read()
        if ret:
            # 每帧都重新生成纯黑背景
            blank_image = np.zeros((height, width, 3), np.uint8)
            
            image = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
            image.flags.writeable = False
            results = pose.process(image)
            image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
            
            # 仅当检测到人体关键点时才绘制
            if results.pose_landmarks:
                mp_drawing.draw_landmarks(blank_image, results.pose_landmarks, mp_pose.POSE_CONNECTIONS,
                                        mp_drawing.DrawingSpec(color=(245, 117, 66), thickness=2, circle_radius=2),
                                        mp_drawing.DrawingSpec(color=(245, 66, 230), thickness=2, circle_radius=2)
                                        )
            
            cv2.imshow("", image)
            cv2.imshow(" ", blank_image)
            if cv2.waitKey(25) & 0xFF == ord('q'):
                break
        else:
            break

cap.release()
cv2.destroyAllWindows()

修改说明 #

• 将blank_image的初始化移到循环内部，确保每帧都使用全新的纯黑背景，避免旧的绘制内容残留
• 添加if results.pose_landmarks:判断，只有检测到人体关键点时才执行绘制，无人体时直接显示纯黑背景

内容的提问来源于stack exchange，提问作者459zyt