正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

lite visual inertial odometry for edge devices... getting there!

ud

1,636 subscribers

15,193 次观看 • 3 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

I am really impressed by how easy Spectacular AI makes visual-inertial odometry with an OAK camera. Just "pip install spectacularAI" and run a Python script. Running VIO/SLAM used to be much harder in my opinion.

I am really impressed by how easy Spectacular AI makes visual-inertial odometry with an OAK camera. Just "pip install spectacularAI" and run a Python script. Running VIO/SLAM used to be much harder in my opinion.

Yu Xiang

70,481 次观看 • 5 个月前

The C-100 heavy-lift quadcopter from the company PDW can carry and deploy not just smaller drones like FPVs, but also small unmanned ground vehicles up to 13.5kg. It has object detection capability, and can use visual inertial odometry to determine its location. 1/2

The C-100 heavy-lift quadcopter from the company PDW can carry and deploy not just smaller drones like FPVs, but also small unmanned ground vehicles up to 13.5kg. It has object detection capability, and can use visual inertial odometry to determine its location. 1/2

Roy🇨🇦

163,753 次观看 • 2 年前

MAC-VO: Metrics-Aware Covariance for Learning-based Stereo Visual Odometry TL;DR: learning-based stereo; learned metrics-aware matching uncertainty for dual purposes: selecting keypoint and weighing the residual in pose graph optimization.

MAC-VO: Metrics-Aware Covariance for Learning-based Stereo Visual Odometry TL;DR: learning-based stereo; learned metrics-aware matching uncertainty for dual purposes: selecting keypoint and weighing the residual in pose graph optimization.

Alexandre Morgand

17,367 次观看 • 1 年前

GPS-free visual-inertial navigation in real time on Raspberry Pi 5 with a consumer-grade IMU and camera (and this is not even the slowest CPU this runs on!)

GPS-free visual-inertial navigation in real time on Raspberry Pi 5 with a consumer-grade IMU and camera (and this is not even the slowest CPU this runs on!)

Otto Seiskari

264,553 次观看 • 1 年前

Microsoft has brought back the uBlock Origin extension in Edge Dev for Android (it's not uBlock Origin Lite, it's the full version of uBlock Origin!!):

Microsoft has brought back the uBlock Origin extension in Edge Dev for Android (it's not uBlock Origin Lite, it's the full version of uBlock Origin!!):

Leopeva64

20,408 次观看 • 1 年前

First demo of our new aerial Visual-Inertial Positioning System (VIO+VPS): 40m positioning accuracy (CEP) in a 50 kilometer flight using a camera, consumer-grade IMU and a barometer! No GPS

First demo of our new aerial Visual-Inertial Positioning System (VIO+VPS): 40m positioning accuracy (CEP) in a 50 kilometer flight using a camera, consumer-grade IMU and a barometer! No GPS

Otto Seiskari

101,510 次观看 • 1 年前

DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding TL;DR: DINO-X Pro: sota model with enhanced perception capabilities for various scenarios; DINO-X Edge: model optimized for faster inference speed and better suited for deployment on edge devices

DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding TL;DR: DINO-X Pro: sota model with enhanced perception capabilities for various scenarios; DINO-X Edge: model optimized for faster inference speed and better suited for deployment on edge devices

Alexandre Morgand

60,720 次观看 • 1 年前

Can an inexpensive, off-the-shelf IMU be the only sensor to estimate the full state (position, velocity, orientation) of a quadrotor flying through a track at high speed and even be on-pair with vision-based localization? The answer is yes, within certain limitations! In this #RAL2023 paper, we propose a learning-based odometry algorithm that couples a model-based filter driven by the inertial measurements with a learning-based module with access to the control commands. Our system outperforms by a large margin the state-of-the-art visual-inertial odometry (#VIO) algorithms and the state-of-the-art learned-inertial odometry algorithm, #TLIO, for the task of drone racing. Additionally, we show that our system is as accurate as a VIO algorithm that uses a camera to localize to a known map of the racing track. The main limitation of our approach is that it cannot generalize to trajectories that have not been seen at training time. However, in drone racing competitions, the track is known beforehand. Human pilots spend hours or even days of practice on the race track before the competition. Similarly, our system can be trained with the data collected during practice time and deployed during the competition. Future work will investigate how to generalize to trajectories not seen at training time. The code is released! Paper: Video: Code: Kudos to Giovanni Cioffi Leonard Bauersfeld Elia Kaufmann European Research Council (ERC) University of Zurich UZH Science UZH Space Hub NCCR Robotics Aerial Core #RAL2023 #IROS2023 #SLAM

Can an inexpensive, off-the-shelf IMU be the only sensor to estimate the full state (position, velocity, orientation) of a quadrotor flying through a track at high speed and even be on-pair with vision-based localization? The answer is yes, within certain limitations! In this #RAL2023 paper, we propose a learning-based odometry algorithm that couples a model-based filter driven by the inertial measurements with a learning-based module with access to the control commands. Our system outperforms by a large margin the state-of-the-art visual-inertial odometry (#VIO) algorithms and the state-of-the-art learned-inertial odometry algorithm, #TLIO, for the task of drone racing. Additionally, we show that our system is as accurate as a VIO algorithm that uses a camera to localize to a known map of the racing track. The main limitation of our approach is that it cannot generalize to trajectories that have not been seen at training time. However, in drone racing competitions, the track is known beforehand. Human pilots spend hours or even days of practice on the race track before the competition. Similarly, our system can be trained with the data collected during practice time and deployed during the competition. Future work will investigate how to generalize to trajectories not seen at training time. The code is released! Paper: Video: Code: Kudos to Giovanni Cioffi Leonard Bauersfeld Elia Kaufmann European Research Council (ERC) University of Zurich UZH Science UZH Space Hub NCCR Robotics Aerial Core #RAL2023 #IROS2023 #SLAM

Davide Scaramuzza

37,049 次观看 • 2 年前

Did a fun weekend coding project, a visual zone configurator with real-time tracking info for the Everything Presence Lite inside of Home Assistant What do you think, would this be useful?

Did a fun weekend coding project, a visual zone configurator with real-time tracking info for the Everything Presence Lite inside of Home Assistant What do you think, would this be useful?

Everything Smart Home

18,553 次观看 • 1 年前

.RunAnywhere (YC W26) makes it easy for app developers to run AI models directly on phones and edge devices — fast, private, offline — with a single SDK and a dashboard to manage everything across user devices. Congrats on the launch Sanchit monga and Shubham Malhotra!

.RunAnywhere (YC W26) makes it easy for app developers to run AI models directly on phones and edge devices — fast, private, offline — with a single SDK and a dashboard to manage everything across user devices. Congrats on the launch Sanchit monga and Shubham Malhotra!

Y Combinator

69,411 次观看 • 4 个月前

Try your best to monitor your children's devices. There are hyenas out there😨😨

Try your best to monitor your children's devices. There are hyenas out there😨😨

Banned Videos

28,290 次观看 • 5 个月前

Getting ready for the show in Tokyo 2026/1/8 (Thu.) at Shinagawa Club eX “The Beyond”in Tokyo Tickets link #LITE #TheBeyond

Getting ready for the show in Tokyo 2026/1/8 (Thu.) at Shinagawa Club eX “The Beyond”in Tokyo Tickets link #LITE #TheBeyond

LITE

10,958 次观看 • 5 个月前

🚨🗡️🩸 BLOOD ON MY KNIFE AT MIDNIGHT !!! 📹🗡️🩸Visual Premiering Tomorrow at Noon !!! 🍷🗡️🩸SEE YALL THERE Just getting Started !!!

🚨🗡️🩸 BLOOD ON MY KNIFE AT MIDNIGHT !!! 📹🗡️🩸Visual Premiering Tomorrow at Noon !!! 🍷🗡️🩸SEE YALL THERE Just getting Started !!!

The Glorious Dead

16,228 次观看 • 9 个月前

- if SAM3 is so good, do we still need other models? - yes. SAM3 is too large for low compute edge devices and too slow for real-time use. we still need light and fast models for edge workloads. distill SAM3 into smaller model and deploy it in seconds with Roboflow rapid

- if SAM3 is so good, do we still need other models? - yes. SAM3 is too large for low compute edge devices and too slow for real-time use. we still need light and fast models for edge workloads. distill SAM3 into smaller model and deploy it in seconds with Roboflow rapid

SkalskiP

93,025 次观看 • 6 个月前

The demand for Litecoin was always there. The ETF and Lite Strategy solved the access problem. 🗣️: Charlie Lee Ⓜ️🕸️ on Real Vision

The demand for Litecoin was always there. The ETF and Lite Strategy solved the access problem. 🗣️: Charlie Lee Ⓜ️🕸️ on Real Vision

Lite Strategy

15,764 次观看 • 4 个月前

In Mexico, AI & cloud are helping to protect endangered jaguars & other species with online & offline audio and visual monitoring devices. Stay tuned for more TECH4ALL initiatives at HUAWEI CONNECT EUROPE 2025.

In Mexico, AI & cloud are helping to protect endangered jaguars & other species with online & offline audio and visual monitoring devices. Stay tuned for more TECH4ALL initiatives at HUAWEI CONNECT EUROPE 2025.

TECH4ALL

2,608,632 次观看 • 7 个月前

If ever there was a classic commercial, this one would be it in my book. Mr. Baseball, Bob Uecker's Front Row commercial for Miller Lite

If ever there was a classic commercial, this one would be it in my book. Mr. Baseball, Bob Uecker's Front Row commercial for Miller Lite

BaseballHistoryNut

38,821 次观看 • 4 个月前

Missing biggest game of season for getting sent off for this there getting away with murder

Missing biggest game of season for getting sent off for this there getting away with murder

Ads

414,235 次观看 • 2 个月前

Introducing LlamaEdge — lightweight & portable LLM tools for your local, edge & server devices. Based on WasmEdge, LlamaEdge apps are <5 MB, self-contained (no complex dependencies), sandboxed (cloud ready), and can be orchestrated by container tools. LlamaEdge apps are portable across diverse CPUs, GPUs, and OSes. It is super easy to build on them, test locally and then deploy to different devices on the edge or cloud. Try them today! 🚀

Introducing LlamaEdge — lightweight & portable LLM tools for your local, edge & server devices. Based on WasmEdge, LlamaEdge apps are <5 MB, self-contained (no complex dependencies), sandboxed (cloud ready), and can be orchestrated by container tools. LlamaEdge apps are portable across diverse CPUs, GPUs, and OSes. It is super easy to build on them, test locally and then deploy to different devices on the edge or cloud. Try them today! 🚀

wasmedge

18,094 次观看 • 2 年前