Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Experimenting with super lightweight moving object detection No model, just one pass through a 40x30 10fps monochrome video. Plenty easy for most MCUs to handle

dankuntz's profile picture

Daniel Kuntz

12,368 subscribers

11,887 Aufrufe • vor 1 Jahr •via X (Twitter)

GamingWissenschaft & TechnologieBildung
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Moondream 3: world's best open-vocab object detection, packed in a fast, open model.
0:11

Moondream 3: world's best open-vocab object detection, packed in a fast, open model.

moondream

52,595 Aufrufe • vor 9 Monaten

Train a TensorFlow object detection model – then deploy it on a robot 🤖 Iulia Feroli (Iulia Feroli) shows how to turn a notebook into a real-time object detection app. This tutorial works for any project – though we demonstrate the deployment on (and assisted by!) the #ReachyMini, an open-source robot from Pollen Robotics. Built with PyCharm + Claude Code. 👉 Watch it in action:
0:17

Train a TensorFlow object detection model – then deploy it on a robot 🤖 Iulia Feroli (Iulia Feroli) shows how to turn a notebook into a real-time object detection app. This tutorial works for any project – though we demonstrate the deployment on (and assisted by!) the #ReachyMini, an open-source robot from Pollen Robotics. Built with PyCharm + Claude Code. 👉 Watch it in action:

PyCharm, a JetBrains IDE

34,908 Aufrufe • vor 2 Monaten

E no go pass one Benin boy lavishing money on her! Dem plenty for TT
0:15

E no go pass one Benin boy lavishing money on her! Dem plenty for TT

Minister For Ashawo

111,859 Aufrufe • vor 3 Monaten

Real-time object detection will never be the same. Traditional YOLO needs NMS to remove duplicate boxes; it's slow and inconsistent. YOLO26 skips it entirely: single-pass predictions, faster inference and up to 300 detections per image. Download model:
0:10

Real-time object detection will never be the same. Traditional YOLO needs NMS to remove duplicate boxes; it's slow and inconsistent. YOLO26 skips it entirely: single-pass predictions, faster inference and up to 300 detections per image. Download model:

Akshay 🚀

373,913 Aufrufe • vor 4 Monaten

Pothole detection on the road in real time using Ultralytics YOLO26! 🕳️ Manual road inspections are slow, costly, and hard to scale. With object detection, potholes can be identified directly from street-level images or video feeds, enabling faster and more consistent road condition monitoring. How I built this demo: ✅ Trained a segmentation model on a custom dataset. ✅ Generated mask contours for each pothole. ✅ Leveraged the onnx-exported model for faster processing. #Pothole #RoadDamage #AI
0:15

Pothole detection on the road in real time using Ultralytics YOLO26! 🕳️ Manual road inspections are slow, costly, and hard to scale. With object detection, potholes can be identified directly from street-level images or video feeds, enabling faster and more consistent road condition monitoring. How I built this demo: ✅ Trained a segmentation model on a custom dataset. ✅ Generated mask contours for each pothole. ✅ Leveraged the onnx-exported model for faster processing. #Pothole #RoadDamage #AI

Muhammad Rizwan Munawar

30,677 Aufrufe • vor 3 Monaten

Excited to share our ICRA’23 IEEE ICRA work by Adithya Murali We scale up neural collision detection for object rearrangement with procedurally generated synthetic data. Project: Video: 🧵👇
0:15

Excited to share our ICRA’23 IEEE ICRA work by Adithya Murali We scale up neural collision detection for object rearrangement with procedurally generated synthetic data. Project: Video: 🧵👇

NVIDIA AI Developer

26,238 Aufrufe • vor 3 Jahren

SOTA object detection with powerful visual reasoning: "skateboarder wearing checkered shirt".
0:10

SOTA object detection with powerful visual reasoning: "skateboarder wearing checkered shirt".

moondream

60,524 Aufrufe • vor 9 Monaten

Easy trick to secure a shovel handle with wire.
0:13

Easy trick to secure a shovel handle with wire.

LifeHaxx101

227,233 Aufrufe • vor 7 Monaten

Most of the doors don't fit me, so I go through walls instead. It's just too easy for me to break them, just one push, and I'm through. And you get to film behind your goddess before you sigh and call the insurance.
0:15

Most of the doors don't fit me, so I go through walls instead. It's just too easy for me to break them, just one push, and I'm through. And you get to film behind your goddess before you sigh and call the insurance.

Diana Jones | 20'

13,042 Aufrufe • vor 2 Monaten

Nowadays it seems way too easy for someone to alter a video subs and for everyone to just believe it, with NO ONE bothering to check the original source. So here is the real subs: Weverse live, July 23, 2025.
0:17

Nowadays it seems way too easy for someone to alter a video subs and for everyone to just believe it, with NO ONE bothering to check the original source. So here is the real subs: Weverse live, July 23, 2025.

REPORT FOR SEOKJIN

11,298 Aufrufe • vor 5 Monaten

Meta's SAM 3 is a beast. before: collect data, train custom object detector, use tracker to estimate object motion - days now: track anything with text prompt - seconds real-time object detection will never be the same.
0:15

Meta's SAM 3 is a beast. before: collect data, train custom object detector, use tracker to estimate object motion - days now: track anything with text prompt - seconds real-time object detection will never be the same.

Akshay 🚀

31,412 Aufrufe • vor 7 Monaten

Experimenting with claymation today Kling AI 2.1 handing it like a champ. No prompt for this one I just put in the image to see where kling it would take it. More to come 😎👍
0:10

Experimenting with claymation today Kling AI 2.1 handing it like a champ. No prompt for this one I just put in the image to see where kling it would take it. More to come 😎👍

Captain HaHaa

42,576 Aufrufe • vor 1 Jahr

Experimenting with a multitouch Unity native plugin for the Mac trackpad. I didn’t realize it could handle ten touch points.
0:11

Experimenting with a multitouch Unity native plugin for the Mac trackpad. I didn’t realize it could handle ten touch points.

Keijiro Takahashi

38,980 Aufrufe • vor 10 Monaten

Andrew Ng and his team introduced Agentic Object Detection! No training needed, just describe an object, and AI thinks, plans, and finds it like OpenAI o1/o3. 6 examples (and how to try): 1. Detected occupied table
0:12

Andrew Ng and his team introduced Agentic Object Detection! No training needed, just describe an object, and AI thinks, plans, and finds it like OpenAI o1/o3. 6 examples (and how to try): 1. Detected occupied table

Min Choi

332,461 Aufrufe • vor 1 Jahr

🚨 BREAKING: Video generation just got its biggest upgrade. WAN 2.6 generates complete audiovisual experiences in one pass—no stitching, no external tools, no manual sync. First open-source model to do this. Here are 5 examples:
0:10

🚨 BREAKING: Video generation just got its biggest upgrade. WAN 2.6 generates complete audiovisual experiences in one pass—no stitching, no external tools, no manual sync. First open-source model to do this. Here are 5 examples:

Future Stacked

614,676 Aufrufe • vor 6 Monaten

Seedance 2.0 is now live on invideo for Max, Generative, and Team plan users. BytePlus's most advanced video model — and arguably the most controllable AI video model ever released. Multimodal input. Motion replication from reference videos. Native audio-video generation in one pass. Character consistency that actually holds. Director-level camera control. Real-world physics. This isn't prompt-and-pray. This is a production tool. Only available through business email verification for all regions except US and Japan.
0:12

Seedance 2.0 is now live on invideo for Max, Generative, and Team plan users. BytePlus's most advanced video model — and arguably the most controllable AI video model ever released. Multimodal input. Motion replication from reference videos. Native audio-video generation in one pass. Character consistency that actually holds. Director-level camera control. Real-world physics. This isn't prompt-and-pray. This is a production tool. Only available through business email verification for all regions except US and Japan.

Invideo

5,551,809 Aufrufe • vor 3 Monaten

Awesome week for computer vision Hugging Face🔥 Besides DINOv3 we added support for LLMDet, the SOTA for zero-shot object detection (#CVPR2025 '25 highlight) Detect instances in scenes just via prompting, no training involved.
0:11

Awesome week for computer vision Hugging Face🔥 Besides DINOv3 we added support for LLMDet, the SOTA for zero-shot object detection (#CVPR2025 '25 highlight) Detect instances in scenes just via prompting, no training involved.

Niels Rogge

73,865 Aufrufe • vor 10 Monaten

Probably the most annoying thing for me in animations / scrollable content is how easy it is to just clip the content. Even if there is no border around to clip it with, adding masks is a one-liner in css now. (slowed down transition)
0:11

Probably the most annoying thing for me in animations / scrollable content is how easy it is to just clip the content. Even if there is no border around to clip it with, adding masks is a one-liner in css now. (slowed down transition)

Dima Belyaev

27,653 Aufrufe • vor 6 Monaten

I'm working on a new demo. detection of key points on a soccer field. for now, I need to work through annotating the data I will use to train the model. I'll keep you posted.
0:13

I'm working on a new demo. detection of key points on a soccer field. for now, I need to work through annotating the data I will use to train the model. I'll keep you posted.

SkalskiP

23,719 Aufrufe • vor 2 Jahren