Imagine a world where sound responds to human connection—where chaotic noise fades, replaced by tranquility, as people come closer together. That’s the vision behind????? ???????? (????), an interactive art installation I created to explore the profound link between affection and well-being. Training and using AI image recognition, and creative problem-solving, I designed a system that detects gestures like holding hands, hugging, or kissing, lowering stress-inducing noise and amplifying calming sounds in response. Here’s how I brought it to life: ???? ????????????????:?I fine-tuned YOLOv8, a fast object detection model, to classify various gestures of affection in real-time using a webcam. ???????????????? ??????????:?When existing image datasets fell short, I used Stable Diffusion to create hundreds of lifelike training images for gestures like hugging or holding hands, ensuring the model’s accuracy. ???????????????? ?????? ?????????????? ????????????????????:?I turned to Suno.ai to generate soothing, custom soundscapes when pre-existing options didn’t quite get the mood right. ???????????????????? ?????? ??????????????????????????:?With OpenVino, I optimized the system to run smoothly on a 2012 (!) MacBook Pro, ensuring interactivity without requiring high-end hardware. The goal of this project was simple but impactful: to encourage people to reflect on how physical connection can reduce stress and bring calm in today’s hectic, tech-driven world. Early feedback from participants confirmed its success, with many reporting they felt more connected and less stressed after engaging with and around the installation. I’ve made the source code publicly available on GitHub, and I hope this project inspires others to think about how we can use technology to enhance, not replace, our shared human experiences. Read more about it on my website: https://lnkd.in/ecZ9WTT6
Marvin Jér?me Stephan的动态
最相关的动态
-
"Haus Designr AI", a realtime demo poking a little fun at the current GenAI trend, won the dynamic demo competition at Alternative Party 2024. In addition to the video I published a "making of" document and the source code, which might be of interest for people working with Unity or realtime demos in general. https://lnkd.in/eaFruydE - video capture https://lnkd.in/eAEsMDwD - "making of" article https://lnkd.in/eBTrv2hx - source code P.S. I'm currently looking for some more programming work! I'm most familiar with Unity, C# and Python. The LinkedIn algorithms serve me mostly irrelevant stuff for some reason, so if you have something relevant to recommend I've most likely missed it - feel free to talk to me about it. ^^ https://lnkd.in/etY3Hxnb
Haus Designr AI
https://www.youtube.com/
-
Generative AI, Prompt Engineering and Full Stack Development. LinkedIn Top Voice. Senior Staff Instructor at LinkedIn, Instructor at Stanford University.
Latest Midjourney image and I got a lot of thoughts about this tool as someone who works in development with a creative background. Such a beautiful tool with an incredible depth of options. Honestly, it feels more like a programming app than an art tool. One of my favorite things is the blending command, character references and style references, which were all used for this piece. When you get to this stage, there's really not a single prompt because it's a combination of a ton of other work. I think this is a good analog to what will happen in the future with AI. Humans become conductors and focusers of the technologies. I also feel like the new artists are going to be more computer programmers that learn to work with the tools. Artists are always able to adopt new tools and this is the next phase. The computers are blending styles and techniques, but getting it to focus on the Octocat-style character that I can repeat (since it's stored as a character), the style as well as the Github forking sort of background means deliberate progression.
-
-
?? ???????????? ?????????? ???? ?????????? ???????? ???? ?? Ever wondered how video game characters make decisions so quickly and accurately? Let’s dive into how binary trees make your gaming experience smoother and more engaging! ??? ????????????????-???????????? ???? ??????????: ??. ???????? ????: Imagine you’re playing a strategy game. Your opponent, controlled by the game AI, seems to anticipate your every move. How does it do that? ?? ??. ???????????? ???????? ??????????????????: The AI uses a binary tree to evaluate possible moves. Each node represents a potential decision, and the branches represent the outcomes of those decisions. ??. ????????????????????: The AI quickly traverses this tree to decide its next move, ensuring it can react in real-time, making your gaming experience seamless and challenging. ?? ?????? ????????: ?????????? ??????????????????: Chess computers, like the famous Deep Blue, use similar structures. They evaluate millions of possible moves and counter-moves to choose the best strategy. It’s like having a super-smart opponent who thinks thousands of steps ahead! ?? ?????? ???????????? ???????????: Binary trees allow for fast searching and decision-making. Instead of evaluating each possible move one by one (which would take forever), the AI can jump through the tree, eliminating many possibilities at once. This efficiency is what makes it possible to have responsive and intelligent game opponents. Want to dive deeper? Check out our course on Trees, taught by ?????????? ??????????????????, to become a master of these foundational concepts! Get FREE access for a limited time: https://bit.ly/dsa_tree What’s your favorite example of tech magic? Share below and let’s geek out together! ?? #TechTuesday #BinaryTrees #DataStructures #GamingAI #TechMagic #LearningWithFun
-
CS Student at SF State | Skilled in Python, JavaScript, Java, C++, SQL | Experienced in Machine Learning (TensorFlow, Scikit-Learn) & Web Development (Node.js, React, Express) | Passionate About AI & Real-World Impact
?? Excited to share my recent project: Volume Gesture Control! KEEP THE VOLUME FULL??!! ?? What my project Does: This project allows users to control their device's volume using hand gestures—no need to touch any buttons! It’s a great example of how innovative tech can make everyday tasks more convenient and interactive. ? How it Works: I used a combination of computer vision and gesture recognition libraries like OpenCV (Computer Vision) and Mediapipe (Hand Detector) to detect hand movements and map them to volume controls using pyCaw (related to System Audio). The system tracks hand positions, interprets gestures, and adjusts the volume accordingly. It’s fast, efficient, and a fun way to explore computer vision as well as human-computer interaction! ???? Building this project was an exciting challenge, and I’m looking forward to developing more such immersive solutions in the future. Feel free to reach out if you'd like to know more or collaborate on future projects! or want to know more about this projects!!! #GestureControl #ComputerVision #OpenCV #Innovation #Python #Tech (I wanted to upload a second video but LinkedIn don't let us.)
-
THIS developed augmented reality system turns simple and many people, boring math textbooks into interactive learning tools through which the underlying mathematics can be actively manipulated to support the learning curve. Just wonderful! #augmentedreality #computervision #ocr #futureisnow #math
???????????????????????? ???????? ???????????????? ???????? ?????????????????? ?????????????? This system uses optical character recognition (OCR) and computer vision to extract mathematical formulas and figures from any document. These elements are then turned into interactive animations that can be viewed through mobile AR interfaces. Now, teachers and students can create engaging, explorable math explanations without needing any programming skills! Read the full report here -> https://lnkd.in/dPA8GJAV Video credit to YT/ Ryo Suzuki ______________ ?? Want to boost your AI app? Contact us: https://lnkd.in/d5VZ-W8H #AR #AI #Innovation
-
The way tech is transforming equation learning these days is game-changing! Visuals, simulations, interactive tools - it's making those abstract concepts so much more tangible and intuitive for students. Loving how this is sparking more STEM engagement and showing the real-world applications. Technology is a total game-changer for making math and science make sense.
???????????????????????? ???????? ???????????????? ???????? ?????????????????? ?????????????? This system uses optical character recognition (OCR) and computer vision to extract mathematical formulas and figures from any document. These elements are then turned into interactive animations that can be viewed through mobile AR interfaces. Now, teachers and students can create engaging, explorable math explanations without needing any programming skills! Read the full report here -> https://lnkd.in/dPA8GJAV Video credit to YT/ Ryo Suzuki ______________ ?? Want to boost your AI app? Contact us: https://lnkd.in/d5VZ-W8H #AR #AI #Innovation
-
Anthropic introduces Claude 3.5 Sonnet Anthropic has launched Claude 3.5 Sonnet, the first in its new Claude 3.5 model family, which outperforms previous models in intelligence, speed, and cost-efficiency. Claude 3.5 Sonnet, available for free on Claude.ai and the Claude iOS app, and for Pro and Team subscribers with higher rate limits, excels in reasoning, knowledge, and coding, and integrates NVIDIA technologies to enhance AI capabilities. The new Artifacts feature allows users to interact with generated content in real-time, promoting collaborative work environments. Claude 3.5 Sonnet emphasizes safety, privacy, and continuous improvement, with upcoming models and features to further enhance user experience. Read more here: https://lnkd.in/eddane8F #AI #Claude35Sonnet #GenerativeAI #Anthropic #NVIDIA #AIInnovation #TechLaunch #DataPrivacy #MachineLearning #ArtificialIntelligence #GenAI #Claude #Sonnet #ClaudeSonnet #Claude35
-
This Al thinks I'm a different person when I open my mouth wide open. This made me ponder Am I really the same person when I'm silent vs when speaking? ... Hmm... I believe I am different! Are YOU a different person when you open your mouth? How many different versions of you do you have? And what is this video about? Well I'm helping a humble Raspberry Pi (World's favourite Single Board Computer) learn how to detect faces, then capture it's unique features, store them with their name and other details, then instantly go into face recognition mode using the saved face features, as well as instant registration for more unknown ( not yet registered) faces. .. this demo is on laptop but the intended use on Raspberry Pi #AI #TensorFlow #FaceDetection #FaceRecogbition #Javascript #RaspberryPi #SingleBoardComputer #raspi #raspi4
-
???????????????????????? ???????? ???????????????? ???????? ?????????????????? ?????????????? This system uses optical character recognition (OCR) and computer vision to extract mathematical formulas and figures from any document. These elements are then turned into interactive animations that can be viewed through mobile AR interfaces. Now, teachers and students can create engaging, explorable math explanations without needing any programming skills! Read the full report here -> https://lnkd.in/dPA8GJAV Video credit to YT/ Ryo Suzuki ______________ ?? Want to boost your AI app? Contact us: https://lnkd.in/d5VZ-W8H #AR #AI #Innovation
