英文:
How to move my crosshair to the bounding box my model creates
问题
我正在参与一个项目，涉及创建一个AI驱动的机器人，可以自己完全玩Counter-Strike。我有一个工作脚本，使用YOLOv8目标检测算法来识别屏幕上的玩家，并在它们周围绘制边界框。
我遇到了一个问题，即当屏幕上检测到敌人时，机器人会一直向下看。我已经尝试调整鼠标移动计算和实施准星调整，但问题仍然存在。我甚至看了一个类似的使用win32的实现，当我尝试将那个代码实现到我的项目中时，机器人仍然会尽量往下看。有人遇到过类似的行为或有关可能原因的建议吗？我将非常感激任何见解、建议或策略，可以帮助我找出并解决问题的原因。
谢谢！
以下是我的代码：
import osimport timefrom ultralytics import YOLOimport cv2import numpy as npfrom windowcap import WindowCaptureimport win32gui, win32ui, win32con, win32apiimport pydirectinputwincap = WindowCapture('Counter-Strike: Global Offensive - Direct3D 9')model_path = os.path.join('.', 'runs', 'detect', 'train10', 'weights', 'last.pt')model = YOLO(model_path)while True:frame = wincap.get_screenshot()H, W, _ = frame.shapethreshold = 0.5results = model(frame)[0]for result in results.boxes.data.tolist():x1, y1, x2, y2, score, class_id = resultif score > threshold:cv2.rectangle(frame, (int(x1), int(y1)), (int(x2), int(y2)), (0, 255, 0), 4)cv2.putText(frame, results.names[int(class_id)].upper(), (int(x1), int(y1 - 10)),cv2.FONT_HERSHEY_SIMPLEX, 1.3, (0, 255, 0), 3, cv2.LINE_AA)box_center_x = (x1 + x2) / 2box_center_y = (y1 + y2) / 2screen_width = win32api.GetSystemMetrics(0)screen_height = win32api.GetSystemMetrics(1)# 将准星移动到模型框target_x = int(screen_width * box_center_x / W)target_y = int(screen_height * box_center_y / H)pydirectinput.moveTo(target_x, target_y)cv2.imshow("COMPUTER VISION", frame)if cv2.waitKey(1) == ord('q'):cv2.destroyAllWindows()
英文:
I am working on a project involving creating an AI-powered bot to full play Counter-Strike by itself. I have a working script that uses the YOLOv8 object detection algorithm to identify players on the screen, and draw a the bounding box around them.
I'm encountering an issue where the bot will consistently look downward when an enemy is detected on the screen. I have tried adjusting the mouse movement calculations and implementing crosshair adjustments, but the issue persists. I even looked at a similar implementation using win32, when I tried implementing that code to my project it still would have the bot look as far down as it could. Has anyone encountered a similar behavior or have suggestions on what might be causing this? I would greatly appreciate any insights, advice, or strategies that could help me pinpoint and address the cause of the issue.
Thank You!
Here is my code below:
import osimport timefrom ultralytics import YOLOimport cv2import numpy as npfrom windowcap import WindowCaptureimport win32gui, win32ui, win32con, win32apiimport pydirectinputwincap = WindowCapture('Counter-Strike: Global Offensive - Direct3D 9')model_path = os.path.join('.','runs','detect','train10','weights','last.pt')model = YOLO(model_path)while True:frame = wincap.get_screenshot()H, W, _ = frame.shapethreshold = 0.5results = model(frame)[0]for result in results.boxes.data.tolist():x1, y1, x2, y2, score, class_id = resultif score > threshold:cv2.rectangle(frame, (int(x1), int(y1)), (int(x2), int(y2)), (0, 255, 0), 4)cv2.putText(frame, results.names[int(class_id)].upper(), (int(x1), int(y1 - 10)),cv2.FONT_HERSHEY_SIMPLEX, 1.3, (0, 255, 0), 3, cv2.LINE_AA)box_center_x = (x1 + x2) / 2box_center_y = (y1 + y2) / 2screen_width = win32api.GetSystemMetrics(0)screen_height = win32api.GetSystemMetrics(1)# moving crosshair to model boxtarget_x = int(screen_width * box_center_x / W)target_y = int(screen_height * box_center_y / H)pydirectinput.moveTo(target_x, target_y)cv2.imshow("COMPUTER VISION",frame)if cv2.waitKey(1) == ord('q'):cv2.destroyAllWindows()
答案1
得分: 0
从xyxy框格式获取框中心坐标：
box_center_x = x1 + (x2 - x1) / 2box_center_y = y1 + (y2 - y1) / 2
或者你可以直接从结果对象中获取它们。对于单个检测，可以这样做：
x_centre, y_centre, w, h = results[0].boxes[0].xywh.tolist()
英文:
The box center coordinates from xyxy box format:
box_center_x = x1 + (x2 - x1) / 2box_center_y = y1 + (y2 - y1) / 2
Or you can get them directly from the results object. For the single detection it will be:
x_centre, y_centre, w, h = results[0].boxes[0].xywh.tolist()
通过集体智慧和协作来改善编程学习和解决问题的方式。致力于成为全球开发者共同参与的知识库，让每个人都能够通过互相帮助和分享经验来进步。
评论