Yolo trabalhos

...sólida em Kotlin, Jetpack Compose e integração com modelos de inteligência artificial e OCR (reconhecimento óptico de caracteres), para dar continuidade a um aplicativo Android já funcional voltado à leitura automatizada de dados visuais em tempo real. Tecnologias já implementadas: Kotlin + Jetpack Compose (Material 3) Clean Architecture + MVVM TensorFlow Lite + ML Kit (OCR) Modelos do tipo YOLO (formato TFLite) CameraX / Camera2 API Retrofit + OkHttp + DataStore Escopo da Atuação: Manutenção e evolução do projeto existente Aprimoramento da precisão da leitura visual (OCR/IA) Integração com APIs já estruturadas Otimizações de dese...

...(preferencial), C++. Frameworks de IA/Deep Learning: Experiência comprovada com pelo menos um dos seguintes: TensorFlow, PyTorch, Keras. Bibliotecas de Visão Computacional: Forte domínio de OpenCV para processamento de vídeo e imagens. Algoritmos de Tracking: Experiência com algoritmos de rastreamento de objetos (ex: CSRT, KCF, SORT, DeepSORT, YOLO com tracking, etc.). Detecção de Objetos: Conhecimento em modelos de deteção de objetos (ex: YOLO, SSD, Faster R-CNN) para identificação inicial das aeronaves. Processamento de Vídeo em Tempo Real: Capacidade de trabalhar com streams de vídeo ao vivo (RTSP, ONVIF ou similar). Otimização de Desempenho: Habilidade para otim...

Resumo da necessidade. Iremos Ler uma Foto e preciso informar qual é o documento que está na foto. Não é extração de texto, e sim informar qual é o documento. A ideia é utilizar e treinar o YOLO para poder realizar essa tarefa. Vamos imaginar que tenho um: - RG - CPF - Conta de luz Preciso que o YOLO identifique e informe qual é o documento que está na foto.

...dispatched quickly. I’m flexible about the imagery source—NASA, ESA, Google Earth, or any other free feed is fine as long as it delivers cloud-free, high-resolution scenes. You can use the tool to capture screenshots by moving in circles around the selected location. The detector has to work at desert scale, so please build it with an established computer-vision framework (e.g., TensorFlow, PyTorch, YOLO, or a similarly robust model) and output the findings in both human-readable (an image with bounding boxes or a simple web map) and machine-readable form (CSV/GeoJSON with lat/long, time stamp, confidence score). Once I apply the tool to a new location and receive a list of car and truck pictures and coordinates automatically reflected on the map, no manual clicks&...

...the head centered) • Auto zoom / smart cropping (keeping head size consistent) • Smooth motion and transition logic At this stage, we do not yet have final hardware or SDK access, so we are asking the freelancer to: Phase 1 – Prototype (on your own hardware) • Build a working demo using your own Android device / webcam / test camera • Use open-source tools (MediaPipe / TensorFlow Lite / OpenCV / YOLO, etc.) • Demonstrate: 1. Live head tracking 2. Auto zoom in real time 3. Stable performance (≥15 FPS) Deliverables • Full source code • Build instructions • Short demo video showing real-time performance • Explanation of how this will later integrate with a custom camera SDK Once validated, this prototype will be integrated i...

...actualmente estoy desarrollando mi tesis de maestría en Sistemas de Información Geográfica (SIG). El objetivo del proyecto es desarrollar un modelo de visión computacional capaz de detectar y contar plantas de palma aceitera a partir de imágenes RGB obtenidas con dron, con fines de análisis agrícola y generación de información geoespacial. Busco apoyo para el desarrollo del modelo de detección basado en YOLO (YOLOv5, YOLOv8 u otra arquitectura similar justificada técnicamente), utilizando un conjunto de imágenes proporcionado por mí. El enfoque es académico y aplicado al sector agrícola. Alcance del trabajo Preparación y/o validación del dataset para entrenami...

...generation—all with strict patient privacy, no storage of originals, and human oversight required. Key Requirements: • Clean React/ frontend with drag-and-drop upload, DICOM viewer (e.g., ), annotation overlays & heatmaps. • Python backend (FastAPI preferred) + secure auth, encrypted file handling, and cloud storage (AWS S3/GCP). • PyTorch/TensorFlow ML models (fine-tune YOLO/U-Net/MONAI on open dental datasets) for multi-label detection/segmentation. • Mandatory: Full anonymization on upload (pydicom/deid), end-to-end encryption, audit logs, compliance-ready (HIPAA/GDPR/APP principles), ethical transparency (e.g., explainability features). • Cloud deployment (AWS/GCP/Azure, serverless ideal). NDA required. Bid with experience in medica...

... and push actionable alerts through a cloud-hosted pipeline. Later phases will weave in IoT sensors, GPS data and public-transport schedules, but for now cameras take centre stage and all processing happens in the cloud. Here’s what I need from you: • A complete stream-to-insight workflow: camera feed ingestion → cloud message bus → analytics micro-service. • Computer-vision models (OpenCV, YOLO, TensorFlow—your call) that flag incidents with >90 % precision/recall on my test clips. • A REST API that surfaces live traffic state and returns diversion routes in real time. • Extension hooks so I can sync bus, train and metro timetables and forward delay alerts to commuters. • Containerised or serverless deployment scripts s...

I already have a working Python pipeline that watches a live game feed, runs it through YOLO to carve out short MP4 snippets, and pushes those clips to a monitor in real time. A Flutter front-end then lets fans pull either single clips or concatenated highlight reels to their iPhone or Android devices. In addition, the Yolo feed provides information for other performance calculations that post under each snippet on the monitor. Two pain points are slowing us down: 1. YOLO interference Right now one key smaller object interferes with other objects that are detected because there is no prioritization layer in place. This causes some of the performance calculations to be intermittent resulting in some incomplete calculations. I need logic that decides, on the ...

...is **not optional**. You must design the **AI brain** of the system, including: #### AI Methods * Computer Vision (façade detection, cracks, dirt, dimensions) * SLAM / Visual-Inertial Odometry * Object detection & segmentation * Path planning & autonomous navigation * Reinforcement Learning or Rule-Based Control * Predictive maintenance models #### Software & Coding * AI model architecture (YOLO / Transformer / CNN etc.) * Training data requirements * Edge AI vs Cloud AI decision * APIs & system architecture * Simulation tools (Gazebo, AirSim, ROS2) * Control logic (PX4 / ArduPilot) ⚠️ **You must explain the logic, workflows, and pseudo-code or real code structure.** --- ### 4 Costing & Commercial Feasibility You will deliver: * Prototype cost...

..."narcotics," "arrest," "isolate yourself"). * Flag high-pressure/threatening tones. * Visual Forensics (Computer Vision): * Liveness/Deepfake Detection: Identify if the face in the video is AI-generated (looking for lack of blinking, lip-sync errors, or artifacts). * Uniform/Badge Recognition: Detect if the person is wearing a police uniform or showing a badge (using object detection like YOLO). * Real-Time Risk Dashboard: * A simple UI that displays a "Trust Score." If the score drops below a threshold, it shows a "SCAM ALERT" warning. Preferred Tech Stack: * Language: Python * ML Frameworks: TensorFlow / PyTorch / Keras * Computer Vision: OpenCV, MediaPipe * NLP: Hugging Face Transformers (BERT/RoBERTa for inte...

...hardware required) Optimize for snap, lock, weld, and track behavior with precise joystick control Debug latency, drift, misalignment, and tracking edge cases Required Experience (Must Have) Cronus Zen experience (scripts, HID behavior, real-world tuning) Ownership of Xbox or PlayStation console for live testing Microcontroller experience (Arduino-class or higher) Strong background in computer vision (YOLO or similar real-time detection pipelines) Experience with transparent overlays (Windows overlay windows, layered rendering, etc.) vGamepad / XInput / virtual controller experience Comfortable debugging timing, latency, and signal stability Strongly Preferred Experience with real-time CV + joystick automation Familiarity with Python, C++, or C# in CV or input systems Understandi...

...Android developer to help build AI-powered mobile applications. The work involves integrating machine learning models for real-time detection and analysis, both running locally on-device (offline) and via cloud APIs. Note: Your task will be integration of AI models in app architecture but its nice to have knowledge about AI models. What You'll Be Working On Integrating custom detection models (YOLO, TensorFlow Lite, ONNX) into Android apps Implementing on-device inference for offline functionality Connecting apps to AI APIs for cloud-based processing Optimizing model performance for android mobils(Snapdragon 6 cpus etc.) Building clean UI to display detection results in real-time Required Skills Strong Android development experience (Kotlin/Java/Flutter) Hands-on exp...

I need a piece of software that plugs straight into the video stream coming from existing, off-the-shelf CCTV cameras and immediately adds deep-learning smarts. The core ...Deliverables • Installable software (source + compiled package) that connects to standard RTSP/ONVIF camera feeds • Model training or transfer-learning pipeline that achieves high accuracy on my sample footage • Real-time alert module covering email, SMS, in-app and monitor popups • Setup guide and brief user manual I’m comfortable if you leverage frameworks such as Python, OpenCV, TensorFlow or YOLO, as long as performance remains near real-time on 1080p streams. Let me know your approach, estimated turnaround time and any prerequisites you’ll need from my side (e.g., l...

Healthcare AI Chatbot with Document Detection and CCTV Emergency Monitor...Fire or smoke Crowd congestion Abnormal situations: Person lying on floor Sudden group gathering Visual Output Bounding boxes for people Circles or highlights for danger zones Annotated frames Chatbot Alerts Text-based alerts inside chat: “Crowd detected in corridor” “Fire detected near patient area” Tech Stack (Expected) Backend: Python Computer Vision: OpenCV Detection Models: Pretrained YOLO OCR: Tesseract Tracking: SORT or centroid tracking Chatbot: Rule-based or LLM API Output: JSON + annotated images Deliverables Appointment booking chatbot logic Document detection and OCR pipeline CCTV analysis module Emergency detection rules Chatbot responses for all modules Source code ...

... and push actionable alerts through a cloud-hosted pipeline. Later phases will weave in IoT sensors, GPS data and public-transport schedules, but for now cameras take centre stage and all processing happens in the cloud. Here’s what I need from you: • A complete stream-to-insight workflow: camera feed ingestion → cloud message bus → analytics micro-service. • Computer-vision models (OpenCV, YOLO, TensorFlow—your call) that flag incidents with >90 % precision/recall on my test clips. • A REST API that surfaces live traffic state and returns diversion routes in real time. • Extension hooks so I can sync bus, train and metro timetables and forward delay alerts to commuters. • Containerised or serverless deployment scripts s...

... and push actionable alerts through a cloud-hosted pipeline. Later phases will weave in IoT sensors, GPS data and public-transport schedules, but for now cameras take centre stage and all processing happens in the cloud. Here’s what I need from you: • A complete stream-to-insight workflow: camera feed ingestion → cloud message bus → analytics micro-service. • Computer-vision models (OpenCV, YOLO, TensorFlow—your call) that flag incidents with >90 % precision/recall on my test clips. • A REST API that surfaces live traffic state and returns diversion routes in real time. • Extension hooks so I can sync bus, train and metro timetables and forward delay alerts to commuters. • Containerised or serverless deployment scripts s...

I want a desktop-based vision solution that watches any TV, computer monitor, or public display in real time and notifies me the moment someone steps in front of it and tries to take a photo. The core may rely on YOLO or straight OpenCV or Any—whichever gives the fastest, most reliable detection. How it should work • A camera connected to my desktop continuously analyses the scene. • When a person holding up a phone (or clearly preparing to photograph) is detected, the system must: – Crop the frame (or short clip) so the person is centred. – Timestamp it. – Dispatch the alert simultaneously to Telegram, WhatsApp, and Email or Any platform. Key expectations • Sub-second latency between detection and alert. • Clean, wel...

I want a desktop-based vision solution that watches any TV, computer monitor, or public display in real time and notifies me the moment someone steps in front of it and tries to take a photo. The core may rely on YOLO or straight OpenCV or Any—whichever gives the fastest, most reliable detection. How it should work • A camera connected to my desktop continuously analyses the scene. • When a person holding up a phone (or clearly preparing to photograph) is detected, the system must: – Crop the frame (or short clip) so the person is centred. – Timestamp it. – Dispatch the alert simultaneously to Telegram, WhatsApp, and Email or Any platform. Key expectations • Sub-second latency between detection and alert. • Clean, wel...

My in-house Video Management System already ingests live H.264 streams from multiple IP cameras positioned around large industrial sites. The next step is to embed two real-time analytics modules directly into th...for now—just accurate detection and high-quality face capture that I can archive or pass to other systems later. Acceptance criteria 1. ≥95 % plate read accuracy on my provided test set of Indian vehicles. 2. Face box IoU ≥0.8 against ground-truth on the same streams. 3. End-to-end latency (frame in ➜ metadata out) ≤300 ms at 1080p30. If you have prior deployments of OpenCV + TensorRT, YOLO-based detectors, EasyOCR, PaddleOCR or similar on Indian road footage, mention them when you respond; sample screenshots or short demo clips will help me sho...

I have a mixed set of still photos and short video cl...care as much about keeping a unique ID on each instance across frames as I do about tight, well-placed boxes or polygons. You will receive the raw media in batches. For each image or video frame, mark every visible person, vehicle and animal, assign the correct class label, then keep the same ID on that object until it leaves the scene. I’m happy with standard output formats such as COCO JSON, YOLO TXT, or a simple CSV so long as coordinates, class names and tracking IDs are included. Before we start the full set, I’ll provide a small sample; your annotations on that sample will serve as the acceptance test for quality and consistency. Once approved, you can move on to the remaining files and deliver them in agree...

Practical AI tooling for defect detection in a manufacturing use case

• build a realistic-looking synthetic dataset from our video, • generate controlled synthetic defects on top of clean frames, • train a detector and see how far we can get using synthetic-only or mostly synthetic data.

Necesito implementar detección de objetos en tiempo real utilizando OpenCV + YOLO sobre el video que llega desde el dashboard de mi sistema. El objetivo es que cualquier elemento que aparezca en la escena —vehículos, peatones, señales u objetos imprevistos— sea identificado y se muestre con su respectivo bounding box y etiqueta de clase mientras el video corre sin interrupciones perceptibles. El proyecto consiste en el desarrollo de un motor de inferencia de alta performance para la detección, clasificación y seguimiento de múltiples clases de objetos en entornos dinámicos complejos, utilizando hardware dedicado. Implementación de arquitecturas de detección (YOLO/RT-DETR) y algoritmos de tracking.&bul...

Busco un/a especialista en Computer Vision / Deep Learning para desarrollar un modelo de detección de objetos con YOLO orientado a la detección de bolsones de procesionaria del pino (Thaumetopoea pityocampa) en imágenes naturales. El objetivo es entrenar un modelo capaz de localizar y detectar bolsones en imágenes RGB, principalmente procedentes de fotografías de campo y/o dron, en entornos forestales reales (pinares). Alcance del proyecto Entrenamiento de un modelo YOLO (v8 o similar) con dataset personalizado Detección de una clase principal: bolsón de procesionaria Trabajo con objetos pequeños y visualmente ambiguos Enfoque en alto recall (es preferible detectar de más que perder bolsones) Procesamiento ...

...clip of the incident 20s for example. Channels: Integration with WhatsApp API (e.g., Twilio or Meta API) OR a custom Mobile App (Flutter/React Native) for security staff. Dashboard: A simple web-based or local interface to view live logs, replay detected incidents, and manage sensitivity settings. Technical Requirements: Programming Language: Python. Frameworks: PyTorch, TensorFlow, OpenCV, YOLO (v8/v10), or MediaPipe. Hardware Compatibility: Must be optimized for NVIDIA CUDA cores / TensorRT. Scalability: The code should support multiple camera streams simultaneously. Deliverables: Full Source Code (well-documented). Setup Guide (How to install on the NVIDIA device and connect cameras). A working prototype/MVP demonstrating the detection of basic theft actions. Ideal...

...new bullet hole, and then calculates the shooter’s score according to standard concentric-ring values. Once the session ends, the system should compile everything into a clear, detailed report that can be downloaded. Scope of work • Detect the target board in every frame, even if lighting changes or smoke drifts across the lens. • Technical preferences I am comfortable with Python, so OpenCV, YOLO, TensorFlow, or a similar stack will fit well. If you prefer another language or library, just make sure the final solution runs on Windows 10 and can be triggered by a simple command or scheduled task. Deliverables 1. Well-commented source code and any trained weight files. 2. A small sample dataset for verification. 3. Step-by-step setup guide. 4. Example ou...

I’m putting together a real-time inspection line that must catch both subtle textural defects and broader anomalies as products move past a USB industrial camera. The vision stack is Python-based, with YOLO as the starting architecture in PyTorch, and the finished model needs to run on an NVIDIA Jetson under tight latency constraints. Here’s the core flow I need help completing: continuous frame acquisition through the camera’s SDK (not a generic webcam wrapper), on-device preprocessing, YOLO inference accelerated with TensorRT, and immediate feedback—either through GPIO or a lightweight web dashboard—so operators can see the live image, bounding boxes, confidence scores, and flag any misses. Training scripts should let me fine-tune the...

...Web page (HTML/CSS/JS or a simple framework like Flask, Django, Node.js, etc.) - Google Maps integration with API key placeholder - Documentation for setup and usage --- ### **5. Skills Required** - Python (PyTorch, Ultralytics YOLO) - Machine Learning / Computer Vision - Web development (basic front‑end + simple backend) - Experience with Google Maps API - Metadata extraction (EXIF, GPS tags) --- ### **6. Additional Notes** - Dataset will be provided after project award. - Clean, well‑commented code is required. - Preference for someone who has worked with YOLO models before. --- ...

I need a lightweight mobile application that can automatically locate faces in both photos and live video, running smoothly on iOS and Android. The core detector must be YOLO; however, you’re free to combine it with OpenCV or MediaPipe for preprocessing or post-processing as long as overall inference stays fast on mid-range devices. The front end can be built in Flutter or React Native—whichever lets you reach 60 fps video preview without draining the battery. A minimal, clean UI is enough: pick an image from the gallery, record or stream video, and immediately see bounding boxes appear in real time. You will train or fine-tune the model yourself, document the training pipeline, and include the final weights in the repo. Optimisation for size and speed (quantisat...

...complete, camera-ready body-emotion detection pipeline that runs in real time on a standard classroom CCTV feed. The end goal is to monitor student engagement continuously, flagging moments of happiness, surprise, confusion, fear, frustration and closely related states so that teaching staff can react while the lesson is still in progress. Scope of work • Model exploration: start with CNN-BiLSTM and YOLO-based approaches, experiment with any other architecture you feel can outperform them, then select and justify the single best model for live deployment. • Data: restrict training to publicly available body-language datasets (for instance, CMU Panoptic, PKU-MMD, Kinetics-Skeleton, or similar) plus any augmentations you create yourself. No private data collection wi...

...for too long By tracking hand, head and eye direction the system should outperform human observers and keep false positives low. It will be deployed across supermarkets, boutique stores, electronics stores and must remain adaptable to any other retail layout without requiring new cameras. The workflow I have in mind: incoming feed → OpenCV (or equivalent) preprocessing → deep-learning model (YOLO, Detectron2, TensorFlow/PyTorch—whichever you favour) → real-time overlay that highlights the suspect and pops a visual alert in the guard’s monitoring software. No audible alarm is needed right now. Deliverables 1. Trained model and reproducible training pipeline 2. Low-latency inference service that runs on standard Windows or Linux hardware 3. Ope...

I need an end-to-end solution that lets growers upload aerial JPEG, PNG or TIFF shots taken from drones and immediately receive two key pieces of information: the total number of pineapples visible in each image and the average radius of every fruit detected. The work breaks down into three tightly-linked components: 1. Model creation • Build and train a computer-vision model (YOLO, Detect-RON, Mask-RCNN or any comparable deep-learning stack you prefer in PyTorch or TensorFlow) that reliably identifies individual pineapples from top-down drone imagery. • Include a second head or post-processing step that converts pixel dimensions to real-world radius, using the drone’s altitude and sensor data or a calibration grid that I will supply. • Deli...

...adult students (20+). The task is to build two separate pipelines that estimate emotion from both facial cues and body language, then benchmark their performance: • Pipeline 1 – CNN-BiLSTM: extract spatial features frame-by-frame, pass temporal sequences through a BiLSTM, and classify the five basic emotions (happiness, sadness, anger, fear, surprise). • Pipeline 2 – YOLO-based: detect faces and upper-body regions with YOLO, feed cropped sequences to an emotion head, and output the same five-class predictions. After training on the videos, compare accuracy, F1, and real-time throughput. Once the stronger approach is confirmed, deploy it for live testing (webcam or external camera) so emotions can be displayed or logged in real time. Deliverables m...

...to track 100+ equine keypoints with sub-pixel precision. Temporal Analysis: Develop spatio-temporal understanding of the jump phases (Approach, Take-off, Flight, Landing) using VideoMAE or TimeSformer. Data Correlation: Translate biomechanical outputs into performance scores and predictive potential markers. Required Technical Stack Languages/Frameworks: Python, PyTorch (Advanced). Vision: YOLO v8-v11, RT-DETR, Ultralytics, DeepLabCut, SLEAP. Spatio-Temporal: VideoMAE, Video Swin Transformer, TimeSformer. Deployment/Optimization: ONNX Runtime, TensorRT, MLOps (Weights & Biases / MLflow). Mandatory Candidate Qualifications We are looking for a top-tier expert. Please only apply if you meet the following criteria: Serious References: You must provide verifiable case s...

...to track 100+ equine keypoints with sub-pixel precision. Temporal Analysis: Develop spatio-temporal understanding of the jump phases (Approach, Take-off, Flight, Landing) using VideoMAE or TimeSformer. Data Correlation: Translate biomechanical outputs into performance scores and predictive potential markers. Required Technical Stack Languages/Frameworks: Python, PyTorch (Advanced). Vision: YOLO v8-v11, RT-DETR, Ultralytics, DeepLabCut, SLEAP. Spatio-Temporal: VideoMAE, Video Swin Transformer, TimeSformer. Deployment/Optimization: ONNX Runtime, TensorRT, MLOps (Weights & Biases / MLflow). Mandatory Candidate Qualifications We are looking for a top-tier expert. Please only apply if you meet the following criteria: Serious References: You must provide verifiable case s...

...AI-enabled cameras • Analyze time spent on work-related and non-work-related activities • Provide visual evidence (captured images) with AI-generated comments • Generate accurate time-based reports for management review Key Features 1. Computer Vision & AI Analysis • Real-time video processing using PyTorch-based deep learning models • Human detection and tracking using models such as: • YOLO / Faster R-CNN (object detection) • DeepSORT (person tracking) • Action recognition models (CNN + LSTM / Transformers) • Face and posture recognition (optional and configurable) 2. Behavior Classification The system classifies employee behavior into predefined categories, such as: • Working at desk • Coffee break &bull...

...them must also be supplied in JSON so I can generate either static or interactive charts later. Key statistics that must appear in the output: 1. Player positions and movement traces throughout the match 2. Types of shots taken and whether they resulted in winners, forced errors or unforced errors 3. Rally durations paired with their outcomes Technology preferences are Python with OpenCV, YOLO-based detection, pose estimation for finer tracking, and GPU-accelerated processing on AWS or GCP (or a local CUDA setup if you prefer). A clean, well-documented codebase and brief setup script are part of the hand-off. When you reply, please show: • Examples of previous computer-vision or sports-analytics projects you’ve delivered • A concise outline of the approac...

I need a program that can automatically identify the walking direction of a horse in yearling parade videos, detect the frame where the horse is most perpendicular to the camera, and extract a standardised clip around that moment. Requirements: - Process MP4 yearling parade videos - Use YOLO to detect the horse and SAM2 (or YOLO-seg) to generate a segmentation mask for each frame - Calculate the mask centroid per frame and determine walking direction based on consistent left-to-right X-movement - Select only the frames where the horse is clearly walking left-to-right - From those frames, detect the moment where the horse is most perpendicular to the camera - Extract a standardised segment around this point (e.g., ±75 frames or ±2 seconds depending on FPS) - Exc...

...shotgun apes, bow/sniper swaps, super tracking) • Call of Duty (Warzone/MW3/BO6 – bloom control, perfect movement tracking) • Apex Legends (legend ability detection, ultimate tracking, zip-line prediction) • Battlefield 6 (2042 & next BF – vehicle lock-on, massive player count handling) • Valorant (agent outlines, spike timer sync) • XDefiant + every new shooter that drops Aim Features (all games) • YOLO head/body detection running on Helios 2 • Rage / Legit / Silent / Triggerbot / Memory aim • Humanized smoothing, random offset, bezier curves • Live recoil tables per weapon (drag-drop for noobs, raw values for pros) • FOV circle, priority (closest/head/low HP), bone selection • Prediction for movement, slidi...

...through Frigate (or your proposed alternative) with detections visualised in its UI. 2. n8n receives distinct webhook calls for configured event type, carrying JSON with camera name, event label, and clip URL. 3. Face library is configurable via a simple folder or API. 4. A short README explains how to retrain models, add cameras, or extend n8n flows. If you’ve worked with Frigate, TensorFlow, YOLO, OpenCV, or similar stacks and can demonstrate a working PoC quickly, let’s talk. Your job is to setup, configure, document all of above and help us build, recreate the same using documentation at our end. Also, to fix any issue that is needed to meet above requirements. Acceptance Criteria: Clean repository with clear build/run instructions. Application should w...

I need a reliable partner to go through my image set and draw tight, well-aligned bounding boxes around two classes only—People and Vehicles. Every image must be reviewed, the boxes placed accurately, and the resulting coordinates exported in a consistent file I can feed straight into my training pipeline (JSON, XML or YOLO txt—let me know which you prefer, I’m flexible as long as the formatting is uniform). Deliverables • All original images unchanged • A matching annotation file for each image or one consolidated file, clearly mapping every bounding box to its class label (“person”, “vehicle”). • A quick spot-check report summarising total images processed and any edge cases you encountered. Quality is far more impor...

...closely with product teams for roadmap and feature design REQUIRED TECHNICAL EXPERTISE LLM & NLP: • GPT, LLaMA, Claude, Gemini • RAG pipelines, embeddings, summarization Voice AI: • TTS (Azure, ElevenLabs, Coqui) • ASR (Whisper, NeMo) • SSML, voice cloning, audio DSP Video & Avatar AI: • FFmpeg automation, OpenCV, Whisper • Wav2Lip, SyncNet, avatar generation (D-ID, Synthesia) Computer Vision: • YOLO models, segmentation, OCR, moderation filters MLOps & Architecture: • Kubernetes, Docker, FastAPI • Model serving (Triton, TorchServe) • Vector DBs (Pinecone, Weaviate, FAISS) • Airflow, Temporal, CI/CD Backend Systems: • Distributed systems, microservices • REST & WebSocket services • AW...

...(REQUIRED) AI Clothing Recognition When a user photographs an item, the system should: Automatically remove background Detect item category (hoodie, t-shirt, jeans, blazer, etc.) Identify color, patterns, shapes, textures Detect attributes such as neckline, sleeve type, length Classify overall style (casual, formal, streetwear, business, etc.) AI technologies may include: Segment Anything, YOLO, CLIP, custom CV models, Google Vision, or API integrations. Smart Digital Wardrobe A complete closet interface where all identified clothing items appear with: Categories & tags Filters (color, style, season, frequency, category, etc.) Search Usage statistics (least used items, favorites, recently worn) Clean, premium UI/UX Body Avatar Creation (From 3 Photos) Using...

...platform for real-time video analytics. The system will ingest RTSP/ONVIF camera streams, run real-time AI detection (person, vehicle, intrusion, loitering, unattended objects), generate alerts, store snapshots/clips, and provide dashboards, reports, and forensic search. A detailed FRD is ready. Required Skills: Real-time video processing (RTSP, GStreamer, FFMPEG, ONVIF) AI/Computer Vision (YOLO, TensorRT, DeepStream, OpenVINO, CUDA) GPU-accelerated inference pipelines Multi-tenant SaaS backend (Node.js / Python / Go) Cloud deployment (AWS/GCP) Databases: PostgreSQL/MongoDB, Redis Frontend: React or Vue Experience building similar video analytics systems is mandatory Who Should Apply DO NOT APPLY if you don’t have previous experience in video analytics / AI surveillan...

...machine-learning knowledge into a fully working, camera-driven inspection station for printed-circuit boards. The goal is straightforward: from a live feed you will detect wrong resistor values via colour-code reading, spot diode mis-orientation, and flag capacitor polarity errors. Your daily focus will be real-time camera feed processing. That means writing latency-aware OpenCV pipelines, integrating YOLO (or a comparable object-detection network), and pushing frames through a decision layer that raises on-screen alerts and overlays bounding boxes when something is off. You’ll also help with camera calibration, dataset curation and model training so the system improves as new boards come down the line. Deliverables I’ll review for acceptance: • A Python ...

...medium-sized retail chains curb shrinkage without demanding a heavy upfront investment. The first priority is the core system itself: a computer-vision workflow that performs real-time monitoring, triggers instant alert notifications and feeds events into a lightweight analytics dashboard for daily and weekly loss-prevention reports. I’d like you to leverage proven open-source frameworks—think YOLO, OpenCV, TensorFlow or similar—so the software can run on inexpensive IP cameras and modest edge devices. From there, I need the entire go-to-market package wrapped around it: a clear step-by-step marketing playbook that speaks to operations directors and loss-prevention managers at mid-size chains, an onboarding guide that shows them exactly how to wire up cameras, ...

I need a complete camera solution that can sit on a fixed pole beside a 6-a-side turf and automatically keep the football centred in the frame at all times. I am counting on image-recognition tracking, not GPS or external sensors, to find the ball and drive a pair o...6-a-side scenario proving that the ball stays near dead-centre during rapid direction changes. • Setup guide so I can mount the unit on any suitable pole beside a pitch and reproduce your results. I’ll test by running a full 10-minute game: if the ball drifts out of centre for more than two seconds, or the stream drops frames, revisions will be required. Let me know which frameworks (OpenCV, YOLO, TensorRT, etc.) you plan to use; I’m happy to consider alternatives as long as they achieve smooth, r...

...needs more data. The system should ingest standard MP4 files, and produce: Build a detection and classification pipeline using: • Roboflow + YOLO, or • Ultralytics YOLOv8/YOLO11 + MediaPipe, or • MoveNet/SensiAI + classifier • Detect: player, racket, ball, pose, shot type. • Compute timing and technical metrics. • Generate structured JSON: "type_of_shot": "bandeja", "strengths": [], "improvements": [], "score": 82, "overlay_url": "" • Generate human-like feedback using GPT-4o or simirlar. • Benchmark latency + cost per video. • Deliver API or script ready for integration. REQUIRED SKILLS • Computer vision (YOLO, pose es...

...Simple Python API (FastAPI preferred) Accepts uploaded videos Returns processed JSON + snapshot images Store data in lightweight DB (SQLite or Firebase) 3. Simple Dashboard (optional if you can do frontend) View processed data Map with pothole markers Download JSON/CSV You Don’t Need to Build a Full App Just MVP: upload → detect → output. Skills Needed Python + FastAPI Computer Vision (YOLO/Segmentation/Video processing) PyTorch / TensorFlow Basic cloud deployment (AWS/Linode/VPS) Budget ₹60,000 – ₹90,000 (fixed price) Paid in milestones. Small paid test-task will be required (detect 5 potholes in sample video). What to Include in Your Proposal Past work in computer vision (especially object detection) Model you plan to use Delivery timel...