Google tomonidan taqdim etilgan mediapipe kutubxonasi haqida xabariz bormi?
Bu kutubxona yordamida kupgina real world muammolarni yechsa buladi.
Shunchaki pip packet menegeridan

pip install mediapipe opencv-python

urnating .

import cv2
import mediapipe as mp

mp_drawing = mp.solutions.drawing_utils
mp_holistic = mp.solutions.holistic

holistic = mp_holistic.Holistic(min_detection_confidence=0.5, min_tracking_confidence=0.5)

cap = cv2.VideoCapture(0)

cap.set(cv2.CAP_PROP_FRAME_WIDTH, 640)
cap.set(cv2.CAP_PROP_FRAME_HEIGHT, 480)

frame_count = 0

while cap.isOpened():
    ret, frame = cap.read()
    if not ret:
        break

    frame_count += 1
    if frame_count % 3 != 0: 
        continue

    image_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
    results = holistic.process(image_rgb)
    mp_drawing.draw_landmarks(frame, results.pose_landmarks, mp_holistic.POSE_CONNECTIONS)
    cv2.imshow('MediaPipe', frame)

    if cv2.waitKey(1) & 0xFF == 27:
        break

cap.release()
cv2.destroyAllWindows()

Ayni paytda ijtimoiy tarmoqlarrda juda katta muhokamalarga sabab bulmoqda.
Miyasiga chip urnatgan shaxs fikr bilan shaxmat uynamoqda.

Speed Estamation?
Bu obektni harakat tezligiga doir muammolarning AI va Computer Vision bilan
yechimi.
Aslida bu siz uylaydigandek murakkab emas bu juda oson.
tezlig va mexanik kattaliklarni aniqlash uchun maxsus o'q joylashtiriladi
va geometrik almashtirishlar asosida topiladi.

from ultralytics import YOLO
from ultralytics.solutions import speed_estimation
import cv2

model = YOLO("yolov8n.pt")
names = model.model.names

cap = cv2.VideoCapture("..../test_speed.mp4")
assert cap.isOpened(), "Uqishda xatolik"
w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))

# Video writer
video_writer = cv2.VideoWriter("speed_estimation.avi",
                                cv2.VideoWriter_fourcc(*'mp4v'),
                                fps,
                                (w, h))

line_pts = [(0, 360), (1280, 360)]

# tayor sinfni yuklash
speed_obj = speed_estimation.SpeedEstimator()
speed_obj.set_args(reg_pts=line_pts,
                    names=names,
                    view_img=True)

while cap.isOpened():

    success, im0 = cap.read()
    if not success:
        print("Qayta ishlanmoqda....")
        break

    tracks = model.track(im0, persist=True, show=False)

    im0 = speed_obj.estimate_speed(im0, tracks)
    video_writer.write(im0)

cap.release()
video_writer.release()
cv2.destroyAllWindows()

Sinab ko'ring!!! Albatta do'stlaringizga tarqating.

https://github.com/corfyi/UCMCTrack
Kimdir motion detector tez ishlatishni suragandi
Pythondagi tezligi uncha bulmasligi mumkin
C++ versiyasi 1000 FPS bu degani bir sekunda 1000 kadr qayta ishlaydi
https://github.com/LSH9832/UCMCTrack-cpp/tree/main

Hayit odoblari

9-aprel, seshanba (30-kun)
Iftorlik vaqti: 18:59 (Toshkent vaqti)

#hadis #ramazon

Abu Hurayra roziyallohu anhu aytadi:

«Rasululloh sollallohu alayhi vasallam dedilar: «U (Ramazon)ning oxirgi kechasida ro‘zadorlarning gunohlari kechiriladi», dedilar. Ular: «Ey Allohning  Rasuli, u Qadr kechasimi?», deb so‘rashdi.

Rasululloh sollallohu alayhi vasallam: «Yo‘q, lekin ishchi ishini ado etganidan so‘ng ajri – haqi to‘la qilib beriladi», dedilar.

Imom Ahmad rivoyat qilgan.

Diniy manbalarimizda hayit kunlariga doir odob va ahkomlar batafsil bayon qilingan. Biz hozir faqat Ramazon hayitiga tegishli odob va ahkomlar haqida so‘z yuritamiz.

✅ Ramazon hayiti kuniga eson-omon yetib kelgan har bir musulmon kishi quyidagi amallarni bajaradi:

1. Iyd kechasini ibodat bilan o‘tkazish;

2. Hayit namozi uchun g‘usl qilish;

3. Tishlarni misvok yoki tish pastalari yordamida tozalab olish;

4. Iyd uchun yasanish;

5. Xushbo‘ylik surtish;

6. Namozga chiqishdan oldin biror yegulik tanovul qilib olish;

7. Fitr sadaqasini berish (2024-yil uchun fitr miqdori);

8. Takbir aytish (takbir aytish deganda, «Allohu akbar», deyish tushuniladi);

9. Hayit namoziga chiqish;

10. Iyd namoziga ertaroq, piyoda, viqor bilan, takbir aytgan holda borish;

11. Hayit namozga bir yo‘l bilan borib, boshqasidan qaytish;

12. Xonadon ahliga kengchilik, serobchilikka sharoit yaratish;

13. Qarindosh-urug‘, qo‘ni-qo‘shnilarni ziyorat qilish, beva-bechoralarning holidan xabar olish, ularga xursandchilik ulashish;

14. Bolajonlarga hayitlik berish, ularga ushbu bayramning shukuhini ko‘rsata bilish;

15. Tanish-bilish, yoru do‘st va har bir ko‘ringan musulmon kishini hayit bilan tabriklab, ularga xursandchilik va shodlik izhor qilish;

16. Hayit kuni odob doirasida, harom va man qilingan narsalarni aralashtirmagan holda ayrim ko‘ngilxushi ma’nosidagi o‘yin-kulgilar ham qilish mumkin;

❌ Hayit kuniga doir odoblar to‘la-to‘kis bo‘lishi uchun, ushbu kunda qilish durust bo‘lmagan ayrim narsalar haqida ham to‘xtalib o‘tish darkor.

Iyd kuni quyidagi ishlardan saqlanish lozim:

1. Ro‘za tutish.
2. Iyd namozidan oldin yoki keyin nafl o‘qish.
3. Gunoh sodir qilish.
4. Hayit kunlari ayollarning qabristonlarga borishi yaxshi emas.
5. Hayit kunlarini azaga aylantirib olish.


Manba: "Hayit odoblari", Hasanxon Yahyo Abdulmajid, IslomUz portali.


👉 @xushnudbek 👈

😁😁😁.
Linuxga qarelar

RoboFlow jamoasi tomonidan AI based Computer Vision real World muammolarni hal qilishga qaratilgan
supervision kutubxonasi ishlatishga juda oson.
Unda deyarli ayni paytdagi barcha muammolar yechimi mavjud.

Annotate Video with Traces

import numpy as np
import supervision as sv
from ultralytics import YOLO

model = YOLO("yolov8n.pt")
tracker = sv.ByteTrack()
box_annotator = sv.BoundingBoxAnnotator()
label_annotator = sv.LabelAnnotator()
trace_annotator = sv.TraceAnnotator()

def callback(frame: np.ndarray, _: int) -> np.ndarray:
    results = model(frame)[0]
    detections = sv.Detections.from_ultralytics(results)
    detections = tracker.update_with_detections(detections)

    labels = [
        f"#{tracker_id} {results.names[class_id]}"
        for class_id, tracker_id
        in zip(detections.class_id, detections.tracker_id)
    ]

    annotated_frame = box_annotator.annotate(
        frame.copy(), detections=detections)
    annotated_frame = label_annotator.annotate(
        annotated_frame, detections=detections, labels=labels)
    return trace_annotator.annotate(
        annotated_frame, detections=detections)

sv.process_video(
    source_path="people-walking.mp4",
    target_path="result.mp4",
    callback=callback
)

https://www.gazeta.uz/uz/2024/04/25/girls-in-ict/
Shogirdamizni kelgusi ishlariga omad.

Formula recognation based OpenVino pre trained tools.

#Computer_Vision
Kelajakda kuzlarimiz va undan keyinroq fikrlarimiz bilan uynaymiz.

🏆 O'zbekistonda mukofot jamg'armasi 50 000 000 so'm bo'lgan Hackathon bo'lib o'tadi

1-5 may kunlari Toshkent shahridagi Turin politexnika universitetida yo‘l harakati xavfsizligi sohasida innovatsion tizimlarni joriy etish maqsadida mukofot jamg‘armasi 50 000 000 so‘m bo‘lgan Hackathon musobaqasi bo‘lib o‘tadi va unda O‘zbekistonning istalgan yoshdagi barcha xohlovchilari ishtirok etishlari mumkin.

Tanlov talablari

Roʻyxatdan oʻtish shakli

Kimdir shu Hackatonga qatnashyotgan bulsa AI buyicha yaxshi yordam oladi.
Yosh chegarasi yuq ekan kechroq kuribman

https://telegra.ph/C-da-funksiyalarga-murojaat-turlari-04-29

Assalomu alaykum, shu mavzuda maqolacha yozgandim, feedbacklar/savollar bo'lsa guruhga yozaverasizlar