Загрузка видео...

Не удалось загрузить видео

На главную

RoadScan-AI-Automated-Pothole-Detection-Tracking RoadScan AI is a computer vision system built to automatically detect and track potholes in road footage — including dashcam, drone, and fixed-camera video. At its core, the system uses a YOLO11n model fine-tuned on a custom pothole dataset, paired with ByteTrack for multi-object tracking. This enables the...

rsasaki0109's profile picture

Ryohei Sasaki@engineer

10,663 subscribers

97,571 просмотров • 2 дней назад •via X (Twitter)

Наука и технологииОбразование
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

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 просмотров • 5 месяцев назад

Football players detection + tracking using Ultralytics YOLO26 ⚽️ It took me 30 minutes to train the YOLO26 model on a custom dataset using Ultralytics Platform. Later, I used the object tracker (Bytetrack) for tracking the players; tracking could be improved further, and I am working on it this week. More info 👇 #soccer #football #MachineLearning
0:18

Football players detection + tracking using Ultralytics YOLO26 ⚽️ It took me 30 minutes to train the YOLO26 model on a custom dataset using Ultralytics Platform. Later, I used the object tracker (Bytetrack) for tracking the players; tracking could be improved further, and I am working on it this week. More info 👇 #soccer #football #MachineLearning

Muhammad Rizwan Munawar

42,586 просмотров • 3 месяцев назад

The new AIOZ AI Challenge: Pothole Detection has LAUNCHED! Potholes mean increased danger and maintenance costs. Your mission: Build a model that finds and boxes them in real road images. Registration opens today, December 3rd, 2025! 4,500 AIOZ tokens up for grabs. Real AI. Safer streets. Who’s fixing the roads with us? Register now:
0:16

The new AIOZ AI Challenge: Pothole Detection has LAUNCHED! Potholes mean increased danger and maintenance costs. Your mission: Build a model that finds and boxes them in real road images. Registration opens today, December 3rd, 2025! 4,500 AIOZ tokens up for grabs. Real AI. Safer streets. Who’s fixing the roads with us? Register now:

AIOZ Network

829,521 просмотров • 9 месяцев назад

App Showcase!✨ Introducing Tower Stack—A 3D arcade game crafted with Alchemist AI, Tower Stack showcases our platform’s ability to combine advanced generation capabilities with essential game mechanics for a polished and engaging experience. • Physics-Based Gameplay: Advanced physics simulations, including collision detection and object dynamics drive every block's movement and placement. • Dynamic Camera Movement: A responsive camera system ensures smooth tracking and adapts fluidly to gameplay, keeping the focus on key actions for an optimized player experience. • Progressive Difficulty: As players progress, stacking speed increases and block variations evolve, creating a scalable challenge. • High Score Tracking: Scores are saved across sessions allowing players to compete and track their achievements.
0:15

App Showcase!✨ Introducing Tower Stack—A 3D arcade game crafted with Alchemist AI, Tower Stack showcases our platform’s ability to combine advanced generation capabilities with essential game mechanics for a polished and engaging experience. • Physics-Based Gameplay: Advanced physics simulations, including collision detection and object dynamics drive every block's movement and placement. • Dynamic Camera Movement: A responsive camera system ensures smooth tracking and adapts fluidly to gameplay, keeping the focus on key actions for an optimized player experience. • Progressive Difficulty: As players progress, stacking speed increases and block variations evolve, creating a scalable challenge. • High Score Tracking: Scores are saved across sessions allowing players to compete and track their achievements.

ALCHEMIST AI 🔮

23,127 просмотров • 1 год назад

The future of agriculture lies in optimization. A system like this costs very little: a drone with a camera and a computer vision system accurate enough to count and identify plants or diseases. It's so easy that anyone can make it at home for their own crops.
0:10

The future of agriculture lies in optimization. A system like this costs very little: a drone with a camera and a computer vision system accurate enough to count and identify plants or diseases. It's so easy that anyone can make it at home for their own crops.

Marco Franzon

119,920 просмотров • 3 месяцев назад

In Germany, after more than four years of war in Europe and daily Russian spy drones, the current debate is about who is responsible for countering drones: the police, the army, gardeners, caretakers, or no one. Meanwhile in China: China has developed a new acoustic-optical system for countering UAVs. The Chinese company Beijing Ribri Technology has unveiled an integrated drone defense system. The system operates using a multi-stage algorithm: acoustic sensors detect the sound of an approaching drone, artificial intelligence recognizes and identifies the target, and thermal imaging cameras and laser rangefinders determine the precise coordinates and lock onto the object for continued tracking. Once the object is acquired, the system initiates targeted jamming, causing the drone to lose control and either make a forced landing or crash to the ground.
0:11

In Germany, after more than four years of war in Europe and daily Russian spy drones, the current debate is about who is responsible for countering drones: the police, the army, gardeners, caretakers, or no one. Meanwhile in China: China has developed a new acoustic-optical system for countering UAVs. The Chinese company Beijing Ribri Technology has unveiled an integrated drone defense system. The system operates using a multi-stage algorithm: acoustic sensors detect the sound of an approaching drone, artificial intelligence recognizes and identifies the target, and thermal imaging cameras and laser rangefinders determine the precise coordinates and lock onto the object for continued tracking. Once the object is acquired, the system initiates targeted jamming, causing the drone to lose control and either make a forced landing or crash to the ground.

Jürgen Nauditt 🇩🇪🇺🇦

45,624 просмотров • 13 дней назад

A guy from China just built a system that reshapes thousands of glowing particles into a jellyfish, a dragon, a statue, and a samurai. Just by moving his hands in front of a camera. Just a webcam reading his hand position. Every particle recalculates in real time. 60 frames per second. Not pre-rendered. Not a recording. Live. Clench both fists and the entire thing collapses into nothing. The whole setup runs on a regular camera and a GPU particle system. No special hardware. This is where hand tracking, computer vision, and real-time graphics have gotten. And most people haven't noticed.
0:14

A guy from China just built a system that reshapes thousands of glowing particles into a jellyfish, a dragon, a statue, and a samurai. Just by moving his hands in front of a camera. Just a webcam reading his hand position. Every particle recalculates in real time. 60 frames per second. Not pre-rendered. Not a recording. Live. Clench both fists and the entire thing collapses into nothing. The whole setup runs on a regular camera and a GPU particle system. No special hardware. This is where hand tracking, computer vision, and real-time graphics have gotten. And most people haven't noticed.

Vaibhav Sisinty

18,319 просмотров • 1 месяц назад

NEW: Walmart has begun rollout of a new AI-powered visual recognition system for produce lookup at self-checkout stations All you have to do is place a piece of produce on the self checkout. The system will automatically recognize the item and ask you to confirm This system will be expanding to all US stores
0:10

NEW: Walmart has begun rollout of a new AI-powered visual recognition system for produce lookup at self-checkout stations All you have to do is place a piece of produce on the self checkout. The system will automatically recognize the item and ask you to confirm This system will be expanding to all US stores

Wall Street Apes

64,671 просмотров • 3 месяцев назад

🇮🇱🇦🇪 Israel quietly provided the UAE with a compact drone-detection system named “Spectro” during the Iran war to enhance its early-warning capabilities, according to the Financial Times. The assistance also involved deploying advanced air defense systems including Iron Beam and Iron Dome, along with Israeli personnel and real-time intelligence sharing, which allowed detection of incoming drones from distances of up to around 20 kilometers. Video is made by grok AI
0:10

🇮🇱🇦🇪 Israel quietly provided the UAE with a compact drone-detection system named “Spectro” during the Iran war to enhance its early-warning capabilities, according to the Financial Times. The assistance also involved deploying advanced air defense systems including Iron Beam and Iron Dome, along with Israeli personnel and real-time intelligence sharing, which allowed detection of incoming drones from distances of up to around 20 kilometers. Video is made by grok AI

NSTRIKE

26,924 просмотров • 4 месяцев назад

this creator just built a zero-delay auto-aim system on an $8 microcontroller he deployed a custom local AI algorithm on a cheap ESP-32 to track human movement with absolute 0-pixel accuracy. the system completely eliminates standard computation delay. it processes the bounding box and moves the sniper reticle instantly, locking onto the target in real time. the next step is hooking it up to a physical robotic arm. it proves you don't need a massive GPU rig to run complex computer vision. 1. runs locally on a microcontroller 2. local AI inference for zero latency 3. 100% targeting precision when an eight-dollar chip can track movement with zero latency, AI becomes dangerous local infrastructure. this article breaks down exactly how the ESP-32 is powering this physical hardware shift.
0:10

this creator just built a zero-delay auto-aim system on an $8 microcontroller he deployed a custom local AI algorithm on a cheap ESP-32 to track human movement with absolute 0-pixel accuracy. the system completely eliminates standard computation delay. it processes the bounding box and moves the sniper reticle instantly, locking onto the target in real time. the next step is hooking it up to a physical robotic arm. it proves you don't need a massive GPU rig to run complex computer vision. 1. runs locally on a microcontroller 2. local AI inference for zero latency 3. 100% targeting precision when an eight-dollar chip can track movement with zero latency, AI becomes dangerous local infrastructure. this article breaks down exactly how the ESP-32 is powering this physical hardware shift.

ard

1,183,968 просмотров • 1 месяц назад

Released: major updates to the network dashboard, including a new live graph and a leaderboard. It is time to run a node and earn points. This network currently runs the world’s most advanced incentivized system for any AI network, and it is also the largest in the world.
0:18

Released: major updates to the network dashboard, including a new live graph and a leaderboard. It is time to run a node and earn points. This network currently runs the world’s most advanced incentivized system for any AI network, and it is also the largest in the world.

Hyperspace

10,836 просмотров • 1 год назад

OpenClaw setup made me $23,472 Literally overnight my $100 turned into $2,411 Average bot win rate 71% Copytrade: Here is the full strategy: The system builds automated workflows for trading by turning domain expertise into structured skills that activate automatically when specific market conditions appear Skill architecture Each skill is a modular package that includes instruction scripts and reference data This allows the system to apply specialized workflows without needing manual input for every trade Progressive context loading Skills use a three layer structure Only minimal metadata loads at first Full instructions historical data and supporting resources load only when required This reduces resource usage while keeping advanced trading capability Trigger detection Skills activate automatically when market conditions match predefined triggers such as volatility levels orderflow behavior or news sentiment This ensures the right workflow is used at the right time without manual action Workflow execution Once activated each skill runs a predefined multi step process including Real time price tracking and order book analysis Factor generation and backtesting Signal aggregation from machine learning models news sentiment and orderflow Risk assessment and capital allocation Trade execution with retries and position splitting Consistency and reliability All workflows are embedded directly into the system which ensures consistent execution instead of random decision making Every factor signal and risk rule is applied in a structured way Testing and iteration Skills are continuously improved using historical backtesting simulated trading and live performance tracking to maintain reliability in real market conditions Automation edge Instead of creating new strategies every time the system repeatedly uses optimized workflows This reduces complexity increases consistency and scales performance across thousands of trades Performance snapshot Started one month ago with $500 Current daily profit $2,300 per day Morning profit today $71,452 The system runs fully autonomously constantly scanning markets generating signals auditing trades managing risk and executing orders to maximize compounding returns
0:14

OpenClaw setup made me $23,472 Literally overnight my $100 turned into $2,411 Average bot win rate 71% Copytrade: Here is the full strategy: The system builds automated workflows for trading by turning domain expertise into structured skills that activate automatically when specific market conditions appear Skill architecture Each skill is a modular package that includes instruction scripts and reference data This allows the system to apply specialized workflows without needing manual input for every trade Progressive context loading Skills use a three layer structure Only minimal metadata loads at first Full instructions historical data and supporting resources load only when required This reduces resource usage while keeping advanced trading capability Trigger detection Skills activate automatically when market conditions match predefined triggers such as volatility levels orderflow behavior or news sentiment This ensures the right workflow is used at the right time without manual action Workflow execution Once activated each skill runs a predefined multi step process including Real time price tracking and order book analysis Factor generation and backtesting Signal aggregation from machine learning models news sentiment and orderflow Risk assessment and capital allocation Trade execution with retries and position splitting Consistency and reliability All workflows are embedded directly into the system which ensures consistent execution instead of random decision making Every factor signal and risk rule is applied in a structured way Testing and iteration Skills are continuously improved using historical backtesting simulated trading and live performance tracking to maintain reliability in real market conditions Automation edge Instead of creating new strategies every time the system repeatedly uses optimized workflows This reduces complexity increases consistency and scales performance across thousands of trades Performance snapshot Started one month ago with $500 Current daily profit $2,300 per day Morning profit today $71,452 The system runs fully autonomously constantly scanning markets generating signals auditing trades managing risk and executing orders to maximize compounding returns

winkle.

44,158 просмотров • 5 месяцев назад

Introducing Magic Orb🔮 Step into a new era of control with Magic Orb, an advanced tool that empowers alchemists to fine-tune AI generation settings to meet their specific needs. Designed for precision and adaptability, it allows unparalleled customization of outputs to ensure every creation aligns with your vision. Looking ahead, updates to the Multi-AI system will unlock granular control over individual AI configurations. Users will soon be able to manage and tweak multiple specialized AI entities within their applications, each optimized for a distinct function. Now, that’s Magic!🪄✨
0:12

Introducing Magic Orb🔮 Step into a new era of control with Magic Orb, an advanced tool that empowers alchemists to fine-tune AI generation settings to meet their specific needs. Designed for precision and adaptability, it allows unparalleled customization of outputs to ensure every creation aligns with your vision. Looking ahead, updates to the Multi-AI system will unlock granular control over individual AI configurations. Users will soon be able to manage and tweak multiple specialized AI entities within their applications, each optimized for a distinct function. Now, that’s Magic!🪄✨

ALCHEMIST AI 🔮

39,055 просмотров • 1 год назад

three GitHub projects show how much vision can fit inside an ESP32-S3 esp32-camera handles the first layer: sensor data, JPEG frames, PSRAM, and frame buffers 🖇️ once the camera pipeline works, esp-who adds ready-made vision tasks such as face detection, pedestrian detection, and QR recognition 🖇️ the third project explores a smaller but more ambitious setup: training and deploying a custom vision model directly on the microcontroller 🖇️ put the pieces together and the loop becomes straightforward: capture an image run the model turn the result into a decision trigger something in the physical world a light, a servo, an MQTT event, or a local log the useful part is the short path from something the camera sees to something the hardware does
0:19

three GitHub projects show how much vision can fit inside an ESP32-S3 esp32-camera handles the first layer: sensor data, JPEG frames, PSRAM, and frame buffers 🖇️ once the camera pipeline works, esp-who adds ready-made vision tasks such as face detection, pedestrian detection, and QR recognition 🖇️ the third project explores a smaller but more ambitious setup: training and deploying a custom vision model directly on the microcontroller 🖇️ put the pieces together and the loop becomes straightforward: capture an image run the model turn the result into a decision trigger something in the physical world a light, a servo, an MQTT event, or a local log the useful part is the short path from something the camera sees to something the hardware does

ard

20,658 просмотров • 11 дней назад

U.S. company Mara has presented its Spike counter-drone system, designed to defend against FPV drones. The system consists of two main components: the Spotter detection module, which uses visual and acoustic sensors to identify incoming drones, and the Seeker interceptor UAV. The Seeker reportedly has a maximum speed of up to 200 km/h (124 mph) and an operational range of approximately 1.5 km (0.9 miles). Mara estimates the complete Spike system will cost between $30,000 and $100,000, depending on the number of Seeker interceptors included. A single system can reportedly accommodate up to 48 interceptors. The company says the interceptor itself is intended to cost approximately the same as its target, or up to twice as much. A stationary version of Spike is planned for late 2026, while vehicle-mounted and portable versions using manual launch are expected in 2027. The system reportedly underwent testing in Ukraine in July 2026. #USA #Mara #Spike #CounterUAS #CounterDrone #FPV #Drones #DroneWarfare #Interceptor #MilitaryTechnology #Defense
0:04

U.S. company Mara has presented its Spike counter-drone system, designed to defend against FPV drones. The system consists of two main components: the Spotter detection module, which uses visual and acoustic sensors to identify incoming drones, and the Seeker interceptor UAV. The Seeker reportedly has a maximum speed of up to 200 km/h (124 mph) and an operational range of approximately 1.5 km (0.9 miles). Mara estimates the complete Spike system will cost between $30,000 and $100,000, depending on the number of Seeker interceptors included. A single system can reportedly accommodate up to 48 interceptors. The company says the interceptor itself is intended to cost approximately the same as its target, or up to twice as much. A stationary version of Spike is planned for late 2026, while vehicle-mounted and portable versions using manual launch are expected in 2027. The system reportedly underwent testing in Ukraine in July 2026. #USA #Mara #Spike #CounterUAS #CounterDrone #FPV #Drones #DroneWarfare #Interceptor #MilitaryTechnology #Defense

Drone Wars

24,076 просмотров • 1 день назад

The M550i uses a very different logic. Its 4.4-litre twin-turbo V8 N63TU3 produces around 523 hp and is paired with all-wheel drive and an automatic transmission tuned for both speed and refinement. Compared with a full M5, the M550i is not positioned as a flagship. It is positioned as a fast 5 Series that sounds more like a usual V8. The engineering emphasis is on torque delivery, stability and comfort rather than maximum lap time. The M550i shows how BMW used to integrate high output V8 power into its core range instead of isolating it inside a specialist model.
0:14

The M550i uses a very different logic. Its 4.4-litre twin-turbo V8 N63TU3 produces around 523 hp and is paired with all-wheel drive and an automatic transmission tuned for both speed and refinement. Compared with a full M5, the M550i is not positioned as a flagship. It is positioned as a fast 5 Series that sounds more like a usual V8. The engineering emphasis is on torque delivery, stability and comfort rather than maximum lap time. The M550i shows how BMW used to integrate high output V8 power into its core range instead of isolating it inside a specialist model.

Autowelt

78,567 просмотров • 7 месяцев назад

🇷🇺🔥 Russian combat laser destroys drone at 1.5 km distance in tests 🔸The working distance of the Posokh laser system developed by LazerBuzz company has been increased by 0.5 km, its developers state, with a fixed-wing FPV UAV successfully destroyed during a mock attack. 🔸The Posokh system is a Russian laser weapon designed to combat aerial targets to protect industrial and critical infrastructure facilities. 🔸It has an integrated radar system and can destroy targets in less than 0.5 seconds, including in automatic mode. 🔸The system operates by physically impacting the UAV based on focused ytterbium laser radiation technology, with the ray power reaching 80kW.
0:12

🇷🇺🔥 Russian combat laser destroys drone at 1.5 km distance in tests 🔸The working distance of the Posokh laser system developed by LazerBuzz company has been increased by 0.5 km, its developers state, with a fixed-wing FPV UAV successfully destroyed during a mock attack. 🔸The Posokh system is a Russian laser weapon designed to combat aerial targets to protect industrial and critical infrastructure facilities. 🔸It has an integrated radar system and can destroy targets in less than 0.5 seconds, including in automatic mode. 🔸The system operates by physically impacting the UAV based on focused ytterbium laser radiation technology, with the ray power reaching 80kW.

Sputnik

13,362 просмотров • 4 месяцев назад

My OpenClaw bot runs a complete website agency on autopilot: - Finds 100’s of local businesses via Google Maps - AI audits every site → grades them A-D - Builds custom websites for the worst ones - Texts them the preview link - AI voice agent calls to close the deal - Runs 24/7 with zero manual work Most local businesses don't have a website, this system finds them and pitches them automatically Reply “OpenClaw” and I'll send the full system (must be following)
0:10

My OpenClaw bot runs a complete website agency on autopilot: - Finds 100’s of local businesses via Google Maps - AI audits every site → grades them A-D - Builds custom websites for the worst ones - Texts them the preview link - AI voice agent calls to close the deal - Runs 24/7 with zero manual work Most local businesses don't have a website, this system finds them and pitches them automatically Reply “OpenClaw” and I'll send the full system (must be following)

Chris

202,530 просмотров • 5 месяцев назад