YOLO jobs
...Computer Vision developer/researcher to develop an experimental research prototype + research paper on: “AI-Based Low-Cost Video Analytics System for Assisting Grassroots Football Talent Identification.” Project Scope I already have football video footage. The goal is to build a research-level prototype, not a commercial application. Workflow: Football Video → Preprocessing → Player Detection (YOLO) → Player Tracking (ByteTrack/BoT-SORT) → Movement/Position Analysis → Feature Extraction → Player Performance Metrics → Analytical Player Profile Possible metrics include distance, estimated speed, movement intensity, trajectories, field/zone coverage, and other reliably measurable indicators. Experimental Requirements The implemen...
...want something working and reliable rather than over-engineered. Please propose your recommended tech stack (cameras, AI model/service, hosting, alerting method) as part of your bid, and break your price into phases: Camera/sensor integration + live feed AI detection layer (person/vehicle/animal classification) Alerting + dashboard Ideal freelancer: experience with computer vision (e.g. OpenCV, YOLO, or similar), IoT/camera integration, and comfortable working with a non-technical client to explain trade-offs (cost vs. accuracy vs. complexity). We're a small UK-based team moving from traditional in-person security guarding into AI-led monitoring, so real-world reliability matters more than flashy features....
...clear, tightly-fitted bounding boxes around the single object of interest in each frame. These labels will feed directly into a new machine-learning pipeline, so consistency and pixel-accurate placement are essential. You are free to work in any mainstream tool such as LabelImg, CVAT, Supervisely or an equivalent—that choice is yours as long as the final export is delivered in a widely-used format (YOLO, COCO JSON or Pascal VOC). I will supply the class list, detailed annotation guidelines and a small set of fully-labeled examples to make expectations crystal-clear before you begin. Deliverables • Complete set of 5,000 bounding-box annotation files in the agreed-upon format • A brief progress log (image count completed per day) • Final compressed arch...
... The core of the job is a clean, well-documented Python implementation that can take still images or short video clips and return bounding boxes, class labels, and confidence scores for each detected person. I already have test media and the computing environment; what’s missing is the detection logic itself—ideally leveraging familiar libraries such as OpenCV, TensorFlow, PyTorch, or a proven YOLO/SSD variant. Accuracy on varied lighting and crowded scenes is more important to me than sheer speed, but the code should still run in real time on a modern GPU. Deliverables • Python source code with clear inline comments • Pre-trained weights (or training notebook) and instructions for further fine-tuning • Short report outlining model choice, evalu...
...Recommendations for scaling the model to larger areas of Jharkhand Ideal Candidate Please apply if you have demonstrated experience in: * Remote sensing and satellite image processing * Computer vision / deep learning * Tree detection and crown segmentation * Tree species classification * GIS / GeoPandas / Rasterio / Google Earth Engine * Python, PyTorch/TensorFlow * Models such as DeepForest, YOLO, Mask R-CNN, U-Net, SAM or similar * Multispectral/hyperspectral imagery * Geospatial AI Experience with forest/tree species mapping is highly preferred....
Hello, I have been working in data annotation for almost 3 years, gaining extensive experience in annotations. This makes me a valuable addition to your team. In addition, I have much experience in image annotation, segmentation, bounding boxes, polygons, key points, 2D and 3D annotations, and even LIDAR annotations. Tools: C... and even LIDAR annotations. Tools: CVAT Roboflow LabelImg Labelbox VGG Doccano Label Studio Annotation Solutions: Bounding Boxes Image annotation Object labeling/tagging Semantic Segmentation Polygons Annotation/masks Polylines Annotation Key Points annotation Sentiment, Text & Topic Analysis Image classification and categorization Object Tracking Data ...
...application that runs entirely offline. The workflow is straightforward: 1. I open the program, browse my local folders, and pick any .mp4 file. 2. Before the scan starts, I set the frame-sampling rate—this could be every frame, every nth frame, or even a custom decimal rate such as 2.5 fps. 3. The app then performs object detection on those chosen frames. I do not mind which framework you use (YOLO, TensorFlow, OpenCV, ONNX, etc.) as long as everything is bundled so the tool works without an internet connection. 4. When the run finishes, the program produces a plain .txt sheet: one line per analysed frame containing the timestamp and the symbols / class names it detected. No other file formats are required. Deliverables • Stand-alone Windows executable (...
I have hours of CCTV footage from 5-a-s...criteria • Works on at least two full, uncut sample matches I will supply (fixed overhead CCTV angle). • Player identification accuracy ≥90 % over the full match. • Distance error ≤10 % when compared with a manual benchmark. • Goal/shot detection precision ≥80 %, recall ≥75 %. • Outputs the required CSV/JSON files and an optional MP4 with overlays. You will likely lean on tools such as YOLO/Detectron for detection, DeepSORT/StrongSORT for tracking and standard football-model calibration for distance mapping, but I am open to any stack as long as the accuracy targets are met and the code is clean, documented and containerised. If you need extra metadata (team sheets, pitch dimensions) let me kn...
...object-detection pipeline. Every occurrence of the target object in each frame must be boxed precisely—no clipped edges or excessive margins—so the model learns from accurate ground-truth data. You are free to work in any mainstream annotation tool you prefer (LabelImg, CVAT, Labelbox, VGG, makes no difference to me) as long as the final export matches the format I’ll specify before we kick off—COCO JSON or YOLO-style TXT are both fine. Please keep category labels consistent across the entire batch. Deliverables • Fully annotated image set with bounding boxes around every instance of the specified object(s) • Corresponding annotation files in the agreed-upon format • A short note flagging any ambiguous images or edge cases you encoun...
...the final feature set yet, so I’m open to your recommendations on whether to prioritise real-time alerts, historical data analytics, or seamless links to third-party platforms. What matters most is accuracy across various lighting and weather conditions and a design that lets me scale from a single roadside camera to a multi-site installation later on. If you have previous deployments on OpenCV, YOLO, TensorFlow, or similar computer-vision stacks, let me see them. Latency benchmarks or side-by-side comparisons with commercial services are a plus. Deliverables • End-to-end ANPR software (source code + install docs) • Configuration guide for cameras and optimal capture settings • REST or WebSocket interface for external systems • Brief report o...
...yellow-black styles, private and commercial plates). 2. Read the characters on that cropped plate and return the exact registration number as clean text so I can write it straight to my database. The current codebase is independent of language for this new feature, so you are free to deliver a self-contained DLL, EXE, or a callable script—provided it runs reliably on Windows. OpenCV, Tesseract, EasyOCR, YOLO, or similar toolkits are fine as long as they give me accurate results on Indian plates under varied lighting. Acceptance will be based on: • Minimum 90 % recognition accuracy on a sample set of 500 real-world Indian plate images I will supply. • API or command-line call that receives the original JPEG path and returns the detected number in text. &bul...
...yellow-black styles, private and commercial plates). 2. Read the characters on that cropped plate and return the exact registration number as clean text so I can write it straight to my database. The current codebase is independent of language for this new feature, so you are free to deliver a self-contained DLL, EXE, or a callable script—provided it runs reliably on Windows. OpenCV, Tesseract, EasyOCR, YOLO, or similar toolkits are fine as long as they give me accurate results on Indian plates under varied lighting. Acceptance will be based on: • Minimum 90 % recognition accuracy on a sample set of 500 real-world Indian plate images I will supply. • API or command-line call that receives the original JPEG path and returns the detected number in text. &bul...
...agreed. so, timeline must adhere - your given timeline + 10 days as grace period for minor issue if arise unexpectedly) Point 4 - Task to Handle & Option to Show on Start Screen on Chat Widget S1 - Home Screen & S2 - Call Back Screen OP1. Book MiniCab – NOW / ASAP OP2. Book MiniCab – LATER OP3. Lost an Item in MiniCab OP4. Make a Complaint OP5. Get Instant Quote OP6. Speak With Yolo Agent OP7. Book Yolo Tour OP8. Track a Driver Here's brief step-by-step guide. Walk through all 8 steps using the nav pills or Next/Back buttons. Here's a quick summary of what's covered: Steps at a glance: 1. Architecture —CodeIgniter4 backend, Claude API, and MySQL, JavaScript 2. API Setup — Develop Secure APIs & Store it securely fo...
We have a trained, working YOLO-based object detection + classification model (Python) that detects and grades apples in tray images as Grade A / Grade B • Need it wrapped into a callable REST API (FastAPI or Flask preferred) that accepts an image and returns grading results • Must be optimized for GPU inference (RunPod, RTX A5000) — not CPU-only • Model loading must be efficient (loaded once, kept warm — not reloaded per request) • Needs to handle real-world phone-camera photos, not just clean training images — proper image preprocessing/normalization required • Robust error handling: bad images, no apples detected, corrupted uploads, timeouts • Must support multiple concurrent requests without performance degradation (10+ concu...
...UI/UX designs using React, TypeScript, Vite, Tailwind CSS, and modern component libraries. - Build interactive websites with cinematic animations, 3D effects, micro-interactions, glassmorphism, and modern design systems. - Integrate APIs and services such as Google Maps, Firebase, authentication, databases, and AI APIs. - Develop computer-vision and machine-learning solutions using Python, OpenCV, YOLO, ResNet, MediaPipe, and related technologies. - Design secure architectures with authentication, RBAC, multi-tenant isolation, database security, and scalable backend systems. - Build and improve projects from idea → UI/UX → development → testing → deployment. - Debug existing applications, resolve frontend/backend issues, optimize performance, and eliminate run...
I need APP developer who can create from Figma artwork - Driver APP front-end Design & its front-end code which can be ready to use or integrate to CodeIgniter 4 PHP framework. Basic Info & Settings for the App Development a. SET - APP Name – Yolo Driver | SKU – YRLGROUP1 | BUNDLE NAME – b. Technology to be used – Flutter - Dart – Kotlin – Swift – firebase – CI4 – PHP framework - API c. Provide Full Source Code + Integrate with Live Server & App Should be able to work on iOS & Android both type of devices. d. All APIs & Controller files store under Controller folders. PATH = app/Controller/YoloDriverAPP/… e. Name - Driver APP Controller file name = f. All css or Splash Screen Design related files ...
I’m looking for an **expert Computer Vision / YOLO specialist** to optimize my existing object detection model. I already have: * PC with NVIDIA GPU * Dataset and annotations * Training environment/setup * Existing YOLO model and baseline results ### What I need I need someone experienced who can **analyze the dataset and model, experiment with training parameters, augmentations, image size, batch size, learning rate, model configuration, etc., and achieve the best possible results.** This is **not just a training job**. I want someone who can analyze false positives/negatives, identify weaknesses, run experiments, compare results, and intelligently tune the model. Remote access to my PC will be provided. **Experience with YOLO, PyTorch, object detection, ...
**Job Title:** Computer Vision / Roboflow Expert – Fine-Tune Model for PPE & Kitchen Hygiene Violations **Project Description:** We are developing an AI-driven restaurant and kitchen safety monitoring system. We need an experienced Computer Vision & Deep Learning Engineer to build, annotate, and fine-tune a high-accuracy object detection/segmentation model (using Roboflow and YOLO models like YOLOv8/v11) to accurately detect specific hygiene violations in real-time CCTV feeds. **Key Challenges & Core Requirements:** 1. **Glove Compliance:** * Detect bare hands vs. gloved hands (handling fine-grained vision tasks on food prep surfaces). * Accurately flag "No Gloves" violations when staff are touching/preparing food. 2. **Proper Mask Wearing:** * Detec...
...Processing Matrix camera API documentation and RTSP details will be shared after discussion. Demo Dashboard Requirements A simple web dashboard should include: Live Camera View AI Detection Overlay Event Alerts Event History Detection Screenshots Camera Management (Basic) Dashboard Statistics A polished UI is preferred but not mandatory for the demo. Preferred Technology Stack Python FastAPI YOLO OpenCV TensorFlow or PyTorch React.js PostgreSQL Docker Ubuntu Linux NVIDIA GPU Support (CUDA) Equivalent technologies are acceptable if performance and scalability are maintained. Future Scope If the demo is approved, the selected developer/team will continue with the complete platform development, including: Face Analytics Safety Analytics Vehicle Analytics Object Analytics A...
...line no . identify specification break. Acceptance 1. Your extraction script or model must handle multiple P&IDs with different drafting styles without manual re-training. 2. A spot-check on three random areas of the drawing should match the Excel output 100 %. 3. All line breaks must be flagged so that downstream pipe counts reconcile. Feel free to leverage OpenCV, Tesseract, TensorFlow, YOLO, or another approach—just keep the setup reproducible so I can run it again on future packages. A short read-me and sample code are welcome alongside the Excel file....
I’m building a real-time activity analysis pipeline that ingests live streams from well over ten IP cameras and flags everything that matters to my operations team. The focus is threefold: accurate people counting, reliable intrusion detection, and fluid crowd-movement analysis. At the core I expect a YOLO-based model (v5, v7 or v8—you can advise) running through OpenCV that can scale horizontally as additional RTSP streams come online. Low-latency processing, smart use of GPU resources, and clean separation between detection and business-logic layers are crucial because the system will eventually tie into an existing alert dashboard. Deliverables • End-to-end Python (or C++) code that connects to each camera, performs the detections described above, and outpu...
...for an experienced AI engineer or technical architect who can help: * Define the MVP architecture * Recommend the most suitable AI models and frameworks * Design a modular, scalable system * Estimate development phases, timeline, and cost * Help prepare a technical roadmap suitable for investors and future development Experience with any of the following would be valuable: * Computer Vision (YOLO, RT-DETR, etc.) * OCR (PaddleOCR, EasyOCR) * Speech-to-Text (Whisper) * Text-to-Speech (Piper or similar) * LLMs (Gemma, Llama, Qwen, etc.) * Edge AI and embedded systems * AI system architecture **Current Stage** This project is currently at the MVP planning stage. We are actively seeking funding and strategic partnerships before beginning full-scale development. If you've wo...
...requirements (no ROI%/yield/annualised-return framing, RICS development-appraisal terminology only) — the compliance logic is defined; you own making it structurally unbreakable rather than instruction-dependent. - Mentor and technically direct the two existing engineers on infrastructure and ML-adjacent work. ## Requirements **Computer vision** - Production experience with object detection/segmentation (YOLO, Detectron2, Mask R-CNN, or transformer-based segmentation) applied to structured/technical imagery — floor plans, CAD, architectural drawings, or comparable (satellite/aerial, medical, industrial). - Geometric reasoning on top of CV output: polygon extraction, area computation, constraint-based spatial reasoning. - Experience with OCR on low-quality scanned/PD...
...usage, and model retraining Expected Output Example: { "plateNumber": "123456", "country": "Qatar", "plateType": "Private", "confidence": 0.94, "timestamp": "2026-07-07T10:30:00", "cameraId": "CAM-01", "plateImage": "path/to/", "vehicleImage": "path/to/" } Important Requirements: * Developer must have previous experience in ANPR, OCR, object detection, OpenCV, YOLO, PaddleOCR, EasyOCR, TensorFlow, PyTorch, or similar technologies. * The system should be trainable/improvable using our own Qatar/GCC plate dataset. * Accuracy should be tested in day, night, low-light, angled, and moving vehicle conditions. * The fin...
...two camera feeds, you'll detect and track four players, hold a stable identity for each across a full match, map their movement into real court coordinates, and turn that motion into meaningful output — highlight clips and per-player stats. You own the models and the data they produce; our team builds the player-facing page on top. What you'll build: Player detection + multi-object tracking — YOLO-class detection with ByteTrack/DeepSORT-style tracking, maintaining stable per-player identity across occlusion and crossover Pose estimation — for gesture-based highlight triggers (e.g. a player holding a T-pose) Court mapping — homography from image plane to real court coordinates (OpenCV); auto-calibration from court lines is a plus Movement analy...
... The model must work across DIFFERENT monitor brands and layouts (Philips, GE, Drager, Mindray, Nihon Kohden, SLE, etc.) — not just one fixed brand. It must understand that different labels mean the same vital (e.g. "HR", "PR", "Pulse", "Heart Rate" all mean heart rate). This is a semantic understanding problem, NOT a simple OCR or bounding-box detection task. Please do not propose Roboflow / YOLO / Tesseract-only solutions — they cannot generalize across unseen layouts. WHAT THE MODEL MUST DO - Input: one image of a patient monitor (often in a cluttered real-world hospital scene, with staff/equipment in frame) - Output: clean JSON, e.g. { "hr": 142, "spo2": 98, "rr": 45, "bp_sys": 70...
Hello, I have been working in data annotation for almost 3 years, gaining extensive experience in annotations. This makes me a valuable addition to your team. In addition, I have much experience in image annotation, segmentation, bounding boxes, polygons, key points, 2D and 3D annotations, and even LIDAR annotations. Tools: C... and even LIDAR annotations. Tools: CVAT Roboflow LabelImg Labelbox VGG Doccano Label Studio Annotation Solutions: Bounding Boxes Image annotation Object labeling/tagging Semantic Segmentation Polygons Annotation/masks Polylines Annotation Key Points annotation Sentiment, Text & Topic Analysis Image classification and categorization Object Tracking Data ...
Educational demonstration that showcases how state-of-the-art YOLO models can spot and differentiate bees, wasps, and other insects directly from video streams.
...want to surface. The very first sport you will tackle is Football, but I want the parameters, event types, and metric catalogue structured so that the same codebase can be extended later to basketball, hockey, and any other field-based sport without rewriting core logic. Core objectives • Multi-camera alignment, calibration, and frame syncing • Real-time player and ball detection / tracking (YOLO, DeepSort, OpenPose, or comparable frameworks) • Automated event recognition so the system can compile full highlight reels—the highest visual priority right now—alongside goal-only, defensive-moment, and candid stills without manual editing (FFmpeg, OpenCV for the assembly pipeline) • Per-player stat extraction focused first on Distance Covered, ...
I’m spearheading an educational demonstration that showcases how state-of-the-art YOLO models can spot and differentiate bees, wasps, and other insects directly from video streams. The ambition is two-fold: create a high-performing detector and produce a concise yet rigorous review of current research, ending with ideas that push the field forward. Here’s the landscape you’ll step into: • Source material: raw, unlabeled videos shot in varied lighting and environments. • Label status: none—so the first milestone is to design and execute an efficient annotation workflow (CVAT, Roboflow, Label Studio, or your preferred stack). • Primary tooling: YOLO26/YOLOv5/YOLOv8 on PyTorch, paired with OpenCV for preprocessing and potential real-time demos. ...
Hello, I have been working in data annotation for almost 3 years, gaining extensive experience in annotations. This makes me a valuable addition to your team. In addition, I have much experience in image annotation, segmentation, bounding boxes, polygons, key points, 2D and 3D annotations, and even LIDAR annotations. Tools: C... and even LIDAR annotations. Tools: CVAT Roboflow LabelImg Labelbox VGG Doccano Label Studio Annotation Solutions: Bounding Boxes Image annotation Object labeling/tagging Semantic Segmentation Polygons Annotation/masks Polylines Annotation Key Points annotation Sentiment, Text & Topic Analysis Image classification and categorization Object Tracking Data ...
## Job Title Computer Vision Engineer: Custom Multi-Camera Kitchen Automation System (YOLO + Cloud Sync) ## Job Description## Project Overview We operate a commercial kitchen with 8 cooking stations and are looking to build a custom, hands-free quality control system. The goal is to automatically capture a 3-second video clip every time a cook adds a new ingredient into a cooking pot or pan. To make this highly accurate and lightweight, we are standardizing our prep containers. Cooks will transfer ingredients into uniform, highly visible, color-coded prep bowls. The AI needs to track these specific containers, detect when they hover and tilt over a cooking zone, crop a 3-second video clip (1 second before the tilt, 2 seconds after), and upload it to a cloud dashboard. ## System Arch...
...Application Integration 15. Security Personnel Management ________________________________________ Advanced Features (Preferred) AI Learning Capability Multi-Camera Support Night Vision Optimization Edge AI Processing License Plate Recognition (Optional) GIS & Location Mapping (Optional) ________________________________________ Technical Requirements Preferred Technologies: • Python • OpenCV • YOLO (Latest Version) • TensorFlow / PyTorch • Deep Learning Models • Face Recognition Frameworks • FastAPI / Django / Flask • React.js / Vue.js • Android (Flutter or Native) • MySQL • Docker • Cloud Deployment Support • REST API Development ________________________________________ Deliverables 1. Complete Source Code 2. ...
My current YOLO 26 model struggles with Eurobox and bread-crate detection, hovering below 50 % accuracy. With only ~100 training images (each holding 30–40 crates), I need to push performance past 94 % without relying on power-hungry cloud instances. I’m open to every practical angle—tighter algorithmic tuning, smart preprocessing and creative data augmentation—so long as the final solution can run locally on a mid-range GPU or even CPU if possible. Feel free to experiment with lighter YOLO variants, pruning, quantisation, mosaic augmentation, rotation/flip tricks, colour tweaks or any other ideas you trust; I care about the end result and the ability to reproduce it on my hardware. Acceptance criteria • Provide the updated model weights, trai...
...together—jersey numbers and face recognition—so that each bounding box you draw really belongs to the right person. I need that tagging to be accurate at least 90 % of the time under normal HD broadcast footage. The program should accept a YouTube URL or live stream, process the frames on-the-fly, and overlay the player’s name or squad number with minimal latency. A GPU-friendly pipeline using OpenCV, YOLO/Detectron, TensorFlow or similar frameworks is perfectly fine as long as it delivers the required accuracy and keeps the frame rate smooth. For clarity, here is what I expect you to hand over: • A Windows executable (or installer) that runs locally without cloud dependence • Source code with clear build instructions • A short user guide s...
...server, mini PC, or cloud processing * Reliable internet connection * Optional GPU device for faster AI processing * POS integration if available ### Software * Camera feed connection * AI video analysis engine * Web dashboard * Alert system * Video clip storage * User login system * Reporting module * Admin settings ## 11. Suggested Technology The development team may use: * Python * OpenCV * YOLO object detection model * Pose estimation model * Deep learning framework such as PyTorch or TensorFlow * Web dashboard using React, , or similar framework * Backend using Node.js, Python FastAPI, or Django * Database such as PostgreSQL or MongoDB * Cloud storage or local encrypted video storage ## 12. Development Phases ### Phase 1: Research and Planning * Study store layout an...
...the images captured and preventive steps can be taken to reduce machine downtime/breakdowns. Scope - Capture images from Camera - Annotate and Classify images - Select and Deploy AI model - Train model - Run the Images through - Provide the feedback from anomalies Activities - Setup image transfer from camera to cloud - Setup the cloud AI solution with Image processor - Setup cloud AI model(s) (YOLO?) - Train model with images - Execute and collect Condition monitoring feedback Out of scope: - image classification and annotation will be done by other team - Robot and HiRes camera is already covered and not needed in this scope. Other: For pilot, first 1-2 weeks on site to make solution run. After pilot: build the Industrial Ready solution, with EDGE AI device, tuned model, ...
I need a small .NET library for real-time object detection using YOLO and ONNX Runtime. The work should be done from scratch. The library will load ONNX weights, run inference on images, and return bounding boxes with class labels and confidence scores. Acceptance criteria -Library detects objects in a sample image with correct boxes and labels -Sample app runs end-to-end and saves an annotated image -README explains setup and basic usage -Code builds without errors on a standard Windowsdev machine
We are developing...AI Accelerator. The system must: Detect another drone using the camera feed Track the detected drone in real time Generate guidance commands to keep the target centered in view Support autonomous follow behavior Preprocess camera images for AI inference Train and optimize object detection models Optimize performance for low latency and high FPS on Raspberry Pi Required Skills: Python OpenCV YOLO/Object Detection Object Tracking (ByteTrack, DeepSORT, etc.) Raspberry Pi Edge AI Deployment Drone Systems and Navigation Preferred Experience: Drone vision projects Autonomous tracking systems Real-time AI inference on embedded devices Raspberry Pi AI accelerator deployment This is a guidance and development support project. Please share similar projects you have ...
I have a single 40-second MP4 clip that shows two motorcycles circulating the same track. Each bike can be separated at a glance because they are painted different colours. What I need is a reliable, frame-accurate measurement of the time interval between the first and the second motorcycle as they pass a chosen reference line on the circuit. Please use YOLO (or an equivalent real-time object detector) to: • detect both bikes throughout the whole sequence, • define a consistent reference line or region on the track, • timestamp the exact moment each bike crosses that reference, and • burn a clear visual overlay onto the video that displays the calculated gap in seconds. The finished deliverable is the processed video with the overlay already embedded; no...
I need a lean, working proof-of-concept that automatically counts foot traffic using a single 360-degree camera. The goal is to drop the unit into busy conference halls, festival entrances, or outdoor promotional zones and have it return reliable head-counts without manual intervention. Here is what matters to me: • Vision logic: Please build or integrate computer-vision models (OpenCV, YOLO, TensorFlow Lite or similar) that detect and track people moving through the camera’s full 360° field of view. The algorithm must distinguish unique passes so that every person is counted once. • Edge or cloud flexibility: I am fine with the model running on a Raspberry Pi 4, Jetson Nano, or a small cloud instance—as long as latency is low and setup remains simple. ...
...from images or video captured by a camera. This project is the first step toward developing a larger industrial inspection platform. ## Scope of Work * Develop a computer vision model for defect detection. * Use YOLO, PyTorch, TensorFlow, or a similar framework. * Train the model using provided sample images. * Create a simple interface/dashboard showing: * Product status (Pass/Fail) * Defect confidence score * Defect image capture * Support live camera feed processing. * Provide source code and documentation. ## Preferred Skills * Computer Vision * Python * OpenCV * YOLO (v8/v11 preferred) * PyTorch or TensorFlow * Real-time video processing * Industrial inspection experience is a plus ## Deliverables 1. Working defect detection prototype. 2. Source code and ...
...and computer vision to build a mobile visual analysis and object-tracking prototype for FPS-style environments. Project Requirements Real-time object/player detection using YOLO (v8 or v10 preferred) Visual overlay system displaying bounding boxes and tracking information Smooth real-time inference with low latency Support for multiple configurable environments via external config files Android overlay UI with stable performance Compatibility with modern Android devices Clean and optimized architecture Optional: Audio event visualization or directional indicator system Required Skills Strong experience deploying YOLO models on Android (NCNN, TFLite, TensorRT, etc.) Android screen capture and overlay rendering Performance optimization for mobile AI inference Experience w...
...Pulp • Canal • Caries • Restoration • Filling • Implant • RCT High-precision contours around Caries, Implant and Restoration areas are the top priority, with equally careful delineation of Pulp and Canal. Please work in the annotation platform of your choice—Labelbox, Supervisely, V7 Darwin, CVAT, or a comparable tool—and export the dataset in COCO JSON (instance segmentation) or YOLO-compatible polygon format. Deliverables 1. A folder of the original X-rays plus their corresponding segmentation files, organised by image ID. 2. A brief QA report that summarises inter-annotator checks or automated validation you employed to guarantee accuracy. All files will be reviewed against clinical ground truth, so consistency ...
I'm seeking a computer vision expert to develop an object detection system specifically for vehicles. This system will be deployed on traffic cameras. Key requirements: - Detect various types of vehicles in real-time - Ens...deployed on traffic cameras. Key requirements: - Detect various types of vehicles in real-time - Ensure high accuracy and reliability - Work in various weather and lighting conditions - Provide a user-friendly interface for monitoring Ideal Skills and Experience: - Proficiency in computer vision frameworks (e.g., OpenCV, TensorFlow) - Experience with real-time object detection algorithms (e.g., YOLO, SSD) - Strong background in machine learning and image processing - Ability to optimize models for edge devices Need to work on site at Gwalior, India...
...NLP pipeline for entity extraction and intent detection. You’re free to choose spaCy, Hugging Face Transformers or a comparable library as long as the final function returns structured JSON with the extracted entities and confidence scores. 2. Object Detection on Images Alongside the text stream, the app receives still-image snapshots that must be analysed for specific objects in real time. A YOLO-v8 or Faster-RCNN model loaded with Torch or TensorFlow is fine, provided inference stays under 150 ms per frame on a mid-range GPU. The detector’s output has to be normalised into the same JSON schema as the NLP results so the downstream service can treat both uniformly. Key expectations • Modular, well-commented Python 3.11 code that drops straight into my FastA...
...detection and OCR recognition Helmet detection for two-wheelers Seatbelt detection Red light violation detection Wrong-side driving detection Over-speed detection Lane violation detection Real-time alerts and logging Store violation data in database Dashboard/Admin panel for monitoring Upload video or use live camera feed Export reports and screenshots of violations Technologies Preferred: Python OpenCV YOLO / TensorFlow / PyTorch OCR for number plates Flask/Django for web dashboard MySQL or MongoDB database Expected Output: The system should detect traffic violations automatically and save: Vehicle image Number plate text Time and date Type of violation Camera/location details Additional Requirements: Clean UI dashboard Proper documentation Source code included Efficient and o...
...detection and OCR recognition Helmet detection for two-wheelers Seatbelt detection Red light violation detection Wrong-side driving detection Over-speed detection Lane violation detection Real-time alerts and logging Store violation data in database Dashboard/Admin panel for monitoring Upload video or use live camera feed Export reports and screenshots of violations Technologies Preferred: Python OpenCV YOLO / TensorFlow / PyTorch OCR for number plates Flask/Django for web dashboard MySQL or MongoDB database Expected Output: The system should detect traffic violations automatically and save: Vehicle image Number plate text Time and date Type of violation Camera/location details Additional Requirements: Clean UI dashboard Proper documentation Source code included Efficient and o...
...project (source code) - APK file - Clear setup instructions: - How to install APK on tablet - How to connect webcam - How to run the app Existing Code (Important) We will provide: - PDF explaining the tracking system (AI + smoothing logic) - Setup guide from previous developer - Existing project files The system includes: - Face tracking (MediaPipe) - Body tracking fallback (YOLO) - Smooth camera motion (PID control) You will need to: - Review and adapt this code for the new webcam input Preferred Tech Stack Developers may use: - Java or Kotlin (Android Studio) - Experience with: - Camera2 API OR USB (UVC) camera integration - MediaPipe / TensorFlow Lite (preferred) - OpenCV (bonus) Important Notes - No backend required - No database required - Foc...
