Intelligent Robot

작물 생장 측정을 위한 데이터 수집 1. 사용 카메라 Intel Realsense D435i (Active IR Stereo camera) Zed2 (Stereo camera) PMD pico monstar (ToF camera) 2. 야간 촬영을 위해 조명을 조절해주는 usb relay 3. 설치 모습 설정한 주기마다 모든 카메라의 데이터를 저장 데이터는 pc에 저장과 동시에 cloud에 올라감 데이터를 찍을 때가 만약 지정한 시간대(저녁)라면, relay를 통해 조명 on 데이터 획득 그리고 조명 off https://github.com/jstar0525/RGBD-Data-Collection jstar0525/RGBD-Data-Collection Get data from "Intel Realsense..

3D 도면 2D 도면

import pyrealsense2 as rs pipeline = rs.pipeline() config = rs.config() config.enable_device('xxxxxxxxxxxx') config.enable_all_streams() config.enable_record_to_file('./test.bag') profile = pipeline.start(config) for _ in range(100): frames = pipeline.wait_for_frames() pipeline.stop() * 여기서 만들어진 bag파일은 ROS의 bag파일과 연동되지 않는다.

import os import cv2 from pathlib import Path from datetime import datetime path = Path('/home/ubuntu/data/') path.mkdir(parents=True, exist_ok=True) src = '/dev/video0' W, H, fps = 1920, 1080, 6 cap = cv2.VideoCapture(src) fourcc = cv2.VideoWriter_fourcc('H','2','6','4') cap.set(3, W) cap.set(4, H) cap.set(5, fps) cap.set(6, fourcc) t = datetime.now().strftime('%Y-%m-%d_%H-%M-%S_%f') f_name = o..

Install and reboot $ sudo -H pip install -U jetson-stats if don't have pip ($ sudo apt install python-pip) $ sudo reboot Run $ jtop ref. https://pypi.org/project/jetson-stats/#jetson_release jetson-stats Interactive system-monitor and process viewer for all NVIDIA Jetson [Xavier NX, Nano, AGX Xavier, TX1, TX2] pypi.org

import pyrealsense2 as rs pipeline = rs.pipeline() pipe_profile = pipeline.start() frames = pipeline.wait_for_frames() depth_frame = frames.get_depth_frame() color_frame = frames.get_color_frame() depth_intrin = depth_frame.profile.as_video_stream_profile().intrinsics color_intrin = color_frame.profile.as_video_stream_profile().intrinsics depth_to_color_extrin = depth_frame.profile.get_extrinsic..

import os import cv2 from pathlib import Path from datetime import datetime path = Path('/home/ubuntu/data/') path.mkdir(parents=True, exist_ok=True) src = '/dev/video0' interval = 0.3 # sec def set_camera(src): cap = cv2.VideoCapture(src) cap.set(3, 1920) cap.set(4, 1080) return cap def save_image(cap, interval, show_info=True): t1 = datetime(1000, 1, 1) while(True): t2 = datetime.now() dt = (t..

Check the Camera $ ls /dev/video* Show video import cv2 src = '/dev/video0' W, H, fps = 1920, 1080, 30 cap = cv2.VideoCapture(src) cap.set(3, W) cap.set(4, H) cap.set(5, fps) while(True): ret, frame = cap.read() if ret: cv2.imshow('video', cv2.resize(frame, dsize=(960, 540))) if cv2.waitKey(1) & 0xFF == ord('q'): break else: break cap.release() cv2.destroyAllWindows()

Respeaker 6채널 또는 1채널의 마이크 입력 소리가 발생하는 방향을 알 수 있음 (아래의 프로그램을 활용, resoultion : 1 degree) Update Firmware Firmware Channels Note 1_channel_firmware.bin 1 processed audio for ASR 6_channels_firmware.bin 6 channel 0 : processed audio for ASR, channel 1-4 : 4 microphones' raw data, channel 5: playback（factory firmware） $ sudo apt-get update $ sudo apt-get install python-usb $ sudo pip install pyusb cl..

Install v4l-utils $ sudo apt-get install v4l-utils Supports Camera format $ v4l2-ctl --list-formats ioctl: VIDIOC_ENUM_FMT Index : 0 Type : Video Capture Pixel Format: 'MJPG' (compressed) Name : Motion-JPEG Index : 1 Type : Video Capture Pixel Format: 'YUYV' Name : YUYV 4:2:2 Support Camera format, resolution and fps $ v4l2-ctl --list-formats-ext ioctl: VIDIOC_ENUM_FMT Index : 0 Type : Video Cap..