当前位置： 首页 > news >正文

网站开发自学要多久,php wordpress 配置,求2021没封的良心网址,房源信息网yolov8直接调用zed相机实现三维测距#xff08;python#xff09; 1. 相关配置2. 版本一2.1 相关代码2.2 实验结果 3. 版本二3.1 相关代码3.2 实验结果 相关链接 此项目直接调用zed相机实现三维测距#xff0c;无需标定#xff0c;相关内容如下#xff1a; 1.yolov5直接调… yolov8直接调用zed相机实现三维测距python 1. 相关配置2. 版本一2.1 相关代码2.2 实验结果 3. 版本二3.1 相关代码3.2 实验结果 相关链接 此项目直接调用zed相机实现三维测距无需标定相关内容如下 1.yolov5直接调用zed相机实现三维测距python 2. yolov4直接调用zed相机实现三维测距 3. WindowsYOLOV8环境配置 4.具体实现效果已在哔哩哔哩发布点击此链接跳转 本篇博文工程源码下载麻烦github给个星星 下载链接https://github.com/up-up-up-up/zed-yolov8 附Zed调用YOLOv7测距也已经实现但是3060笔记本6G显存带不动在大现存服务器上可以运行可能是由于YOLOv7网络结构导致的由于不具备普适性就不再写相关文章了有需要的可以仿照这个代码去改写

1. 相关配置 python3.7 Windows-pycharm zed api 具体配置见 (zed api 配置步骤) 由于我电脑之前python版本为3.7yolov8要求python最低为3.8所以本次实验直接在虚拟环境里进行未配置gpu可能看着卡卡的有需要的可以配置一下原理是一样的

2. 版本一 2.1 相关代码 主代码 zed-yolo.py具体放置在yolov8主目录下盒子形式展现可实现测距跟踪 #!/usr/bin/env python3import sys import numpy as npimport argparse import torch import cv2 import pyzed.sl as sl from ultralytics import YOLOfrom threading import Lock, Thread from time import sleepimport ogl_viewer.viewer as gl import cv_viewer.tracking_viewer as cv_viewerlock Lock() run_signal False exit_signal Falsedef xywh2abcd(xywh, im_shape):output np.zeros((4, 2))# Center / Width / Height - BBox corners coordinatesx_min (xywh[0] - 0.5xywh[2]) # im_shape[1]x_max (xywh[0] 0.5xywh[2]) # im_shape[1]y_min (xywh[1] - 0.5xywh[3]) # im_shape[0]y_max (xywh[1] 0.5xywh[3]) # im_shape[0]# A —— B# | Object |# D —— Coutput[0][0] x_minoutput[0][1] y_minoutput[1][0] x_maxoutput[1][1] y_minoutput[2][0] x_maxoutput[2][1] y_maxoutput[3][0] x_minoutput[3][1] y_maxreturn outputdef detections_to_custom_box(detections, im0):output []for i, det in enumerate(detections):xywh det.xywh[0]# Creating ingestable objects for the ZED SDKobj sl.CustomBoxObjectData()obj.bounding_box_2d xywh2abcd(xywh, im0.shape)obj.label det.clsobj.probability det.confobj.is_grounded Falseoutput.append(obj)return outputdef torch_thread(weights, img_size, conf_thres0.2, iou_thres0.45):global image_net, exit_signal, run_signal, detectionsprint(Intializing Network…)model YOLO(weights)while not exit_signal:if run_signal:lock.acquire()img cv2.cvtColor(image_net, cv2.COLOR_BGRA2RGB)# https://docs.ultralytics.com/modes/predict/#video-suffixesdet model.predict(img, saveFalse, imgszimg_size, confconf_thres, iouiou_thres)[0].cpu().numpy().boxes# ZED CustomBox format (with inverse letterboxing tf applied)detections detections_to_custom_box(det, image_net)lock.release()run_signal Falsesleep(0.01)def main():global image_net, exit_signal, run_signal, detectionscapture_thread Thread(targettorch_thread, kwargs{weights: opt.weights, img_size: opt.img_size, conf_thres: opt.conf_thres})capture_thread.start()print(Initializing Camera…)zed sl.Camera()input_type sl.InputType()if opt.svo is not None:input_type.set_from_svo_file(opt.svo)# Create a InitParameters object and set configuration parametersinit_params sl.InitParameters(input_tinput_type, svo_real_time_modeTrue)init_params.coordinate_units sl.UNIT.METERinit_params.depth_mode sl.DEPTH_MODE.ULTRA # QUALITYinit_params.coordinate_system sl.COORDINATE_SYSTEM.RIGHT_HANDED_Y_UPinit_params.depth_maximum_distance 50runtime_params sl.RuntimeParameters()status zed.open(init_params)if status ! sl.ERROR_CODE.SUCCESS:print(repr(status))exit()image_left_tmp sl.Mat()print(Initialized Camera)positional_tracking_parameters sl.PositionalTrackingParameters()# If the camera is static, uncomment the following line to have better performances and boxes sticked to the ground.# positional_tracking_parameters.set_as_static Truezed.enable_positional_tracking(positional_tracking_parameters)obj_param sl.ObjectDetectionParameters()

   obj_param.detection_model sl.OBJECT_DETECTION_MODEL.CUSTOM_BOX_OBJECTSobj_param.enable_tracking Truezed.enable_object_detection(obj_param)objects sl.Objects()obj_runtime_param sl.ObjectDetectionRuntimeParameters()# Displaycamera_infos zed.get_camera_information()camera_res camera_infos.camera_resolution# Create OpenGL viewerviewer gl.GLViewer()point_cloud_res sl.Resolution(min(camera_res.width, 720), min(camera_res.height, 404))point_cloud_render sl.Mat()viewer.init(camera_infos.camera_model, point_cloud_res, obj_param.enable_tracking)point_cloud sl.Mat(point_cloud_res.width, point_cloud_res.height, sl.MAT_TYPE.F32_C4, sl.MEM.CPU)image_left sl.Mat()# Utilities for 2D displaydisplay_resolution sl.Resolution(min(camera_res.width, 1280), min(camera_res.height, 720))image_scale [display_resolution.width / camera_res.width, display_resolution.height / camera_res.height]image_left_ocv np.full((display_resolution.height, display_resolution.width, 4), [245, 239, 239, 255], np.uint8)# # Utilities for tracks view# camera_config camera_infos.camera_configuration# tracks_resolution sl.Resolution(400, display_resolution.height)# track_view_generator cv_viewer.TrackingViewer(tracks_resolution, camera_config.fps, init_params.depth_maximum_distance)# track_view_generator.set_camera_calibration(camera_config.calibration_parameters)# image_track_ocv np.zeros((tracks_resolution.height, tracks_resolution.width, 4), np.uint8)# Camera posecam_w_pose sl.Pose()while viewer.is_available() and not exit_signal:if zed.grab(runtime_params) sl.ERROR_CODE.SUCCESS:# – Get the imagelock.acquire()zed.retrieve_image(image_left_tmp, sl.VIEW.LEFT)image_net image_left_tmp.get_data()lock.release()run_signal True# – Detection running on the other threadwhile run_signal:sleep(0.001)# Wait for detectionslock.acquire()# – Ingest detectionszed.ingest_custom_box_objects(detections)lock.release()zed.retrieve_objects(objects, obj_runtime_param)# – Display# Retrieve display datazed.retrieve_measure(point_cloud, sl.MEASURE.XYZRGBA, sl.MEM.CPU, point_cloud_res)point_cloud.copy_to(point_cloud_render)zed.retrieve_image(image_left, sl.VIEW.LEFT, sl.MEM.CPU, display_resolution)zed.get_position(cam_w_pose, sl.REFERENCE_FRAME.WORLD)# 3D renderingviewer.updateData(point_cloud_render, objects)# 2D renderingnp.copyto(image_left_ocv, image_left.get_data())cv_viewer.render_2D(image_left_ocv, image_scale, objects, obj_param.enable_tracking)global_image image_left_ocv# global_image cv2.hconcat([image_left_ocv, image_track_ocv])# # Tracking view# track_view_generator.generate_view(objects, cam_w_pose, image_track_ocv, objects.is_tracked)cv2.imshow(ZED | 2D View and Birds View, global_image)key cv2.waitKey(10)if key 27:exit_signal Trueelse:exit_signal Trueviewer.exit()exit_signal Truezed.close()if name main:parser argparse.ArgumentParser()parser.add_argument(–weights, typestr, defaultyolov8n.pt, helpmodel.pt path(s))parser.add_argument(–svo, typestr, defaultNone, helpoptional svo file)parser.add_argument(–img_size, typeint, default416, helpinference size (pixels))parser.add_argument(–conf_thres, typefloat, default0.4, helpobject confidence threshold)opt parser.parse_args()with torch.no_grad():main()

   2.2 实验结果 测距图感觉挺精准的 视频展示: Zed相机YOLOv8目标检测跟踪 3. 版本二 3.1 相关代码 主代码 zed.py具体放置在yolov8主目录下可实现测距跟踪分割 #!/usr/bin/env python3 import math import sys import numpy as np from PIL import Image import argparse import torch import cv2 import pyzed.sl as sl from ultralytics.utils.plotting import Annotator, colors, save_one_box from ultralytics import YOLO from threading import Lock, Thread from time import sleepimport ogl_viewer.viewer as gl import cv_viewer.tracking_viewer as cv_viewerzed sl.Camera()# Create a InitParameters object and set configuration parameters init_params sl.InitParameters() init_params.camera_resolution sl.RESOLUTION.HD720 init_params.coordinate_units sl.UNIT.METER init_params.depth_mode sl.DEPTH_MODE.ULTRA # QUALITY init_params.coordinate_system sl.COORDINATE_SYSTEM.RIGHT_HANDED_Y_UP init_params.depth_maximum_distance 20 # 设置最远距离runtime_params sl.RuntimeParameters() status zed.open(init_params)if status ! sl.ERROR_CODE.SUCCESS:print(repr(status))exit()image_left_tmp sl.Mat() print(Initialized Camera) positional_tracking_parameters sl.PositionalTrackingParameters() zed.enable_positional_tracking(positional_tracking_parameters)obj_param sl.ObjectDetectionParameters() obj_param.detection_model sl.DETECTION_MODEL.CUSTOM_BOX_OBJECTS obj_param.enable_tracking True zed.enable_object_detection(obj_param) objects sl.Objects() obj_runtime_param sl.ObjectDetectionRuntimeParameters()point_cloud_render sl.Mat() point_cloud sl.Mat() image_left sl.Mat() depth sl.Mat()

   Utilities for 2D display

   if name main:model YOLO(./yolov8n.pt)while True:if zed.grab(runtime_params) sl.ERROR_CODE.SUCCESS:# – Get the imagezed.retrieve_image(image_left_tmp, sl.VIEW.LEFT)image_net image_left_tmp.get_data()zed.retrieve_measure(depth, sl.MEASURE.DEPTH)zed.retrieve_measure(point_cloud, sl.MEASURE.XYZRGBA)img cv2.cvtColor(image_net, cv2.COLOR_BGRA2BGR)result model.predict(img, conf0.5)annotated_frame result[0].plot()boxes result[0].boxes.xywhfor i, box in enumerate(boxes):x_center, y_center, width, height box.tolist()point_cloud_value point_cloud.get_value(x_center, y_center)[1]point_cloud_value point_cloud_value * -1000.00if point_cloud_value[2] 0.00:try:point_cloud_value[0] round(point_cloud_value[0])point_cloud_value[1] round(point_cloud_value[1])point_cloud_value[2] round(point_cloud_value[2])distance math.sqrt(point_cloud_value[0] * point_cloud_value[0] point_cloud_value[1] *point_cloud_value[1] point_cloud_value[2] * point_cloud_value[2])print(distance)dis []dis.append(distance)text dis:%0.2fm % distancecv2.putText(annotated_frame, text, (int(x_center), int(y_center)),cv2.FONT_ITALIC, 1.0, (0, 0, 255), 2)except:passcv2.imshow(00, annotated_frame)key cv2.waitKey(1)if key q:breakzed.retrieve_objects(objects, obj_runtime_param)zed.retrieve_image(image_left, sl.VIEW.LEFT)zed.close()3.2 实验结果 可实现测距、跟踪和分割功能这个代码没有加多线程速度够用懒得写了对速率要求高的可以自己写一下实现不同功能仅需修改以下代码具体见 此篇文章 model YOLO(./yolov8n.pt)img cv2.cvtColor(image_net, cv2.COLOR_BGRA2BGR)result model.predict(img, conf0.5)测距功能 跟踪功能
   分割功能 视频展示