takminの書きっぱなし備忘録 @はてなブログ

主にコンピュータビジョンなど技術について、たまに自分自身のことや思いついたことなど

2024/07/07第61回CV勉強会@関東「CVPR2024読み会」(前編)

本日第61回コンピュータビジョン勉強会@関東「CVPR2024読み会」(前編)をLINEヤフー様の会場をお借りして開催いたしました。

以下、資料やリンク等をまとめておきます。

登録サイト

kantocv.connpass.com

Togetter

togetter.com

YouTube

www.youtube.com

コンピュータビジョン勉強会@関東

sites.google.com

資料まとめ

発表者 発表内容 資料
takmin State Space Models for Event Cameras https://speakerdeck.com/takmin/state-space-models-for-event-cameras-di-61hui-cvmian-qiang-hui-at-guan-dong-fa-biao-zi-liao
tereka114 Harnessing Large Language Models for Training-free Video Anomaly Detection https://speakerdeck.com/tereka114/harnessing-large-language-models-for-training-free-video-anomaly-detection
onixwr MLP Can Be A Good Transformer Learner https://speakerdeck.com/safie/mlp-can-be-a-good-transformer-learner
alfredplpl ・Polos: Multimodal Metric Learning from Human Feedback for Image Captioning
・Streaming Dense Video Captioning
・Rich Human Feedback for Text-to-Image Generation
・Improved Baselines with Visual Instruction Tuning
https://www.docswell.com/s/alfredplpl/KLL7M9-2024-07-07-125154
sei_shinagawa Iterated Learning Improves Compositionality in Large Vision-Language Models https://www.docswell.com/s/sei_shinagawa/ZNREYL-iterated_learning
frkake Correlation-aware Coarse-to-fine MLPs for Deformable Medical Image Registration https://speakerdeck.com/frkake/corrmlp-correlation-aware-coarse-to-fine-mlps-for-deformable-medical-image-registration
ttyszk BioCLIP: A Vision Foundation Model for the Tree of Life https://speakerdeck.com/x_ttyszk/di-61hui-konpiyutabiziyonmian-qiang-hui-bioclip-a-vision-foundation-model-for-the-tree-of-life
Godel ・MemoNav: Working Memory Model for Visual Navigation​
・SchurVINS: Schur Complement-Based Lightweight Visual Inertial Navigation System​
https://speakerdeck.com/godel/navigation-and-slam-at-cvpr2024
ykamikawa LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding https://speakerdeck.com/ykamikawa/layoutllm-layout-instruction-turning-with-large-language-models-for-document-understanding

私の発表資料

"State Space Models for Event Cameras"を読みました

speakerdeck.com

ろくに電子工作もしたことない人間がIoT用ミドルウェアを作った話


IoT! IoTLT vol.112

 speakerdeck.com

IoT

AITRIOS



IoT LTArduino使


PySerial経由でArduinoが動かずに苦戦した件


Arduino

Arduino Windows11Python3.12
#include <Servo.h>

Servo myservo;  // create servo object to control a servo

int pos = 0;    // variable to store the servo position

void setup() {
  Serial.begin(9600);
  myservo.attach(9);  // attaches the servo on pin 9 to the servo object
  myservo.write(pos);
}

void move_servo(int angle){
  if(angle < 0){
    for(int i = 0; i > angle && pos > 0; i -= 1){
      pos -= 1;
      myservo.write(pos);              // tell servo to go to position in variable 'pos'
      delay(15);                       // waits 15ms for the servo to reach the position
    }
  }
  else{
    for(int i=0; i < angle && pos < 180; i +=1){
      pos += 1;
      myservo.write(pos);              // tell servo to go to position in variable 'pos'
      delay(15);                       // waits 15ms for the servo to reach the position
    }
  }
}

void loop() {
  if(Serial.available()){
    int angle = Serial.parseInt();
    if(angle != 0){
      move_servo(angle);
    }
  }
}

Arduino IDESerial Monitor

PySeriralPython90
import serial
import time

ser = serial.Serial('COM3', 9600)
ser.write("90".encode())  # 角度(文字列)をArduinoに送信
time.sleep(1)  # 1秒待つ
ser.close()

Arduino IDE



Arduino


ser = serial.Serial('COM3', 9600)
time.sleep(2)  # 2秒待つ
ser.write("90".encode())  # 角度(文字列)をArduinoに送信
time.sleep(1)  # 1秒待つ
ser.close()

2

AR探索アドベンチャーのデモ動画


AR

//

www.youtube.com (2024/04/13 ) 



www.overlay-world.com

使使
takmin.hatenablog.com