Visão Computacional Jobs

We are looking for a developer to build an AI Vision analysis pipeline. The system will automatically process multiple types of video and image sources (not limited to any specific platform), perform scene detection, frame extraction, and Vision AI analysis. Experience with FFmpeg-based video processing and Vision AI model integration is preferred. The project scope includes data ingestion, visual analysis, storage, and automation workflow integration. Long-term collaboration is possible, and final scope and timeline will be defined by mutual agreement.

I want to take my livestreams on macOS to the next level with a real-time AI avatar that feels alive on camera and is ready to drop straight into OBS as a virtual source. Here is the core of what I need built: • The avatar must track my face through an ordinary webcam, translate subtle expressions in real time, and lip-sync perfectly to whatever I say on-mic. • I need the voice layer to offer several high-quality, fully licensed synthetic voices that I can switch on the fly. All voice cloning or TTS work has to be ethical and consent-based; no grey-area datasets. • Latency has to stay low enough for professional broadcasting—ideally under 50 ms from camera to virtual camera output. • Everything has to run smoothly on Apple-silicon Macs and slot into OBS wit...

I need a Python application that takes a pretrained YOLO model and turns it into a real-time desktop solution capable of recognising industrial, hand and power tools as they appear in a live camera feed. The workflow should be straightforward for a non-technical operator: launch the program, select the camera (USB or built-in), and immediately see bounding boxes with class names and confidence scores updating on-screen at 30 fps or better. Key details • Model: start with an existing YOLO checkpoint (v5, v7, v8 or YOLO-NAS—whatever you feel offers the best speed / accuracy trade-off). Feel free to fine-tune if that improves precision, but the core must stay YOLO. • Language & libs: Python 3.x, OpenCV for video capture/rendering, torch or ultralytics for inference. ...

I am looking to develop an AI-powered software system that monitors cashier activity in retail stores using CCTV cameras and POS transaction data. The goal is to automatically detect theft, suspicious cash handling, and abnormal cashier behavior. Main Features: Analyze live video from cashier cameras using Computer Vision and AI Detect suspicious actions such as unscanned items, fake refunds, cash drawer misuse, or unusual movements Link video events with POS transaction data for accurate fraud detection Record and store related video clips of suspicious incidents Provide a dashboard for the business owner to review alerts, watch videos, and monitor cashier performance Send real-time notifications when suspicious activity is detected Technical Requirements: Experience in AI, Compu...

I need to build an AI-powered video creator that leans heavily on computer-vision techniques. The goal is a tool that takes raw clips or even still images and, through smart scene understanding, automatically assembles polished videos—essentially an AI video maker that handles the tedious parts of editing and enhancement for me. Core objectives • Train or adapt a computer-vision model that can detect key moments, faces, objects, and scene changes, then use that information to sequence footage intelligently. • Implement automated video generation logic—transitions, basic trimming, and soundtrack alignment—so the user can go from assets to finished output with minimal clicks. • Include real-time or near-real-time preview plus the option for manual twea...

J’ai une séquence vidéo de 1 minute en définition standard dans laquelle la plaque d’immatriculation d’un véhicule reste illisible. Mon unique objectif est d’en extraire, si possible, les caractères exacts de cette plaque. Je fournirai le fichier original (format MP4) ainsi que le time-code approximatif où le véhicule apparaît. J’attends en retour : • l’image ou le court extrait optimisé où la plaque est lisible, • la transcription claire des caractères, • un court mémo sur les techniques utilisées (par exemple : stabilisation, upscaling IA via Topaz Video Enhance AI, filtres OpenCV, traitement Adobe After Effects, etc.) afin que je comprenne...

My MP4 clip is under one minute long, shot on a poor-quality security camera, and shows just one car. I must know its licence plate with absolute certainty for an insurance claim, so anything less than 100 % accuracy is of no value to me. I am looking for someone who routinely works with forensic video tools such as Amped FIVE, VideoCleaner, OpenCV pipelines, Topaz Video AI or comparable software to extract a crystal-clear, fully readable still. De-blurring, super-resolution, frame stacking—whatever it takes—is expected, provided the end result is court-defensible. Deliverables • A high-resolution still image of the plate (PNG or TIFF) • The enhanced video segment in a lossless format • A brief technical report (PDF) describing the methods and settings used...

Title: Senior Android Developer: Multimodal AI Pipeline (Real-time Video & Audio) **Project Description:** We are seeking a Senior Android Engineer to develop a modular, high-performance infrastructure for **real-time Multimodal capture (Video + Audio)**. The core of the project is a "Hybrid AI Routing Engine" that intelligently switches between on-device local processing and cloud analysis using Gemini 2.0. This application is an R&D prototype that must be **Play Store Ready**, with a heavy focus on background stability and thermal management. **Important:** The ultimate goal is to port this architecture to an Android-based smart glasses OS (AugmentOS), so the code must be hardware-agnostic. **Technical Specifications:** **1. Multimodal Pipeline (Camera + Audio):** ...

I want to turn a standard RC chassis into a smart, self-aware toy that can do far more than just follow joystick commands. The end goal is a prototype car that: • Detects obstacles in real time • Plans an optimal path around them • Switches between full autonomous driving and classic “manual” mode on demand Everything should be directed from a single mobile app that works seamlessly on both iOS and Android. From that app I need to: 1. Watch a live video feed (low-latency) 2. Toggle between autonomous and manual modes 3. See a simple map of the car’s planned path and any detected hazards 4. Push OTA firmware updates when new AI models are trained Hardware is already on hand (Raspberry Pi 4, camera module, ultrasonic sensors, ESC, and an ESP...

I am starting from a blank page and need a complete, publication-ready review paper in the field of Computer Science, focused on Artificial Intelligence. The final manuscript must meet the formatting, citation, and methodological standards of Scopus-indexed and UGC-approved journals. Your work will include a comprehensive literature survey, critical synthesis, clear research gaps, and a well-structured discussion that positions the paper for quick peer-review acceptance. While the overarching topic is Artificial Intelligence, we can fine-tune the scope together—whether it ultimately leans toward Machine Learning, Natural Language Processing, Computer Vision, or an interdisciplinary blend. Deliverables • 6,000–8,000-word review article (editable DOCX) • Abstr...

Ronia Raw Photo Collection - United States We are currently looking for contributors for our Ronia Raw Photo Collection Project. What is the project about? We invite photographers, photo hobbyists, visual creators, and anyone passionate about photography to participate in our RAW Photo Collection project. Do you regularly capture high-quality photos in RAW format to expand your photo library? If the answer is yes, this project allows you to earn extra income by contributing your photos to the development of advanced AI and computer vision technologies. Your images can have a real-world impact beyond your personal library. Task Description: Participants may submit both existing photos from their personal archives and newly captured images in RAW format. We’re looking for a wide va...

I am building a web-based SaaS that lets estheticians quickly scan a client’s photo, receive an instant professional skin analysis, book the appropriate facial treatment, and sell the products the scan recommends—all in one place. Core analysis: The algorithm must reliably detect acne or blemishes, dryness or oiliness, wrinkles or fine lines, combination skin, redness, and visible pores or texture issues. Accuracy and consistency are critical because treatment plans and sales will hinge on the results. Workflow vision 1. Client uploads or snaps a photo during an online consultation or in-spa visit. 2. The system runs the analysis, displays condition scores, and explains each finding in easy language. 3. Based on those scores it lists the facial services I pre-configur...

I need a solution to detect the presence of solar panels on existing roofs using satellite images. The primary analysis required is basic presence detection. I also need the addresses of each building to be able to send them mail regarding their solar panels. Requirements: - Detect solar panels using satellite imagery - Provide analysis on the presence of solar panels Ideal Skills and Experience: - Experience with image analysis and machine learning - Proficiency in handling and analyzing satellite images, especially in formats like GeoTIFF - Familiarity with GIS software would be an advantage Please provide guidance on the satellite images required for this task. Pilot project starting in community of Tuscany in Calgary, Alberta, Canada. There are about 6,500 buildings. We want to st...

Necesito ayuda para desarrollar y optimizar un modelo de detección y segmentación en tiempo real basado en YOLO11n que procese videos de ultrasonido de resolución media. El foco principal es localizar con alta precisión la aguja, aunque también deben marcarse venas y arterias para dar contexto al operador. Alcance del trabajo • Entrenamiento y ajuste fino del modelo YOLO11n con un dataset de ultrasonido que aportaré. • Implementación de segmentación y tracking cuadro a cuadro para mostrar contornos superpuestos en vivo. • Optimización de velocidad de inferencia a nivel de GPU/CPU para mantener latencia mínima. • Entrega de código limpio en Python (PyTorch o framework equivalente), pesos ...

I need a comprehensive book aimed at intermediate users that provides deep insights into the AI industry. The book should cover the following areas in detail: - Machine Learning - Natural Language Processing - Computer Vision The content should be engaging, informative, and reflective of current industry trends and future predictions. Ideal skills and experience: - Strong background in AI - Excellent research and writing skills - Experience writing for an intermediate audience - Ability to analyze and present industry insights

I’m building a cross-platform mobile app that acts as a personal styling and beauty assistant for both men and women. The core of the product is an AI engine that delivers highly-personalized outfit recommendations. Key functionality • The assistant studies three user-supplied inputs—body measurements, skin tone and face shape—and combines them with each person’s stated style preferences, their body type and real-time fashion trend data. • For every request it returns a clear set of outfit suggestions, indicating why each piece flatters the user’s proportions, complexion and current tastes. • A lightweight dashboard lets me update trend data, brand catalogs and style rules without redeploying the app. Technology expectations The re...

I want a single, turnkey application that watches my CCTV feeds, spots shop-lifters in real time, recognises grocery products on the shelves, and keeps a live head-count of customers. The core model must be YOLO, and I need the exact same code-base to compile and run on both Windows (desktop with NVIDIA GPU) and a Raspberry Pi 4. Video sources vary—some cameras stream RTSP over IP while a few older analog units reach the NVR through a capture card—so the program has to accept either type without manual re-configuration. For product recognition I care only about groceries; no clothing or electronics labelling is necessary. The model should be trained (or fine-tuned) on the most common supermarket items so false positives stay low even when shelves are crowded. Key expecta...

I'm looking to develop specialized software for an artillery correction system using a PTZ (pan-tilt-zoom) camera. The software should be capable of detecting and tracking static targets. Additionally, it should provide crucial correction data such as angular position adjustments and elevation adjustments. Key requirements: - Target detection and tracking of static targets - Provide angular position adjustments - Provide elevation adjustments Ideal skills and experience: - Expertise in computer vision and image processing - Experience with PTZ camera integration - Strong background in software development, particularly in real-time systems - Familiarity with artillery systems and requirements is a plus

I need an end-to-end deep-learning model that can pick out identical human faces across images and video in real time. The core requirements are straightforward: • Detect every human face in an image or live stream, draw accurate bounding boxes, then compare each face against a gallery to decide whether it is an identical match. • Serve three environments without extra rewrites: security-grade CCTV feeds, social-media style mobile uploads, and large photo-management archives. • Deliver low latency on a single modern GPU while still running acceptably on CPU-only hardware for lightweight deployments. I’m comfortable with either PyTorch or TensorFlow/Keras; use the framework you know best. A pre-trained backbone such as ResNet, MobileNet, or Vision Transformer is...

I'm looking for someone to develop an App similar to Cal Ai, SnapCalorie and Qalzy. I work in the fitness industry and would like to sell the app to online customers. If you think you can develop something similar, please reach out and we can discuss the details.

I need a Python-based tool that can scan video files, detect Trees, Road, Infrastructure—and leave room for many more object classes as the project grows—then save every relevant frame straight into a MySQL database. Each stored image must be linked to the corresponding frame number and any detection metadata so I can later query, filter, and analyse the results. Once the data is stored, I want a lightweight viewer that steps through the saved frames in order, overlaying the detection boxes so I can visually confirm accuracy. OpenCV for frame extraction and display is acceptable; YOLO, TensorFlow, or another modern model is fine so long as the code is clean, well-commented, and easy for me to retrain with additional classes. To keep the hand-off smooth, please include: •...

I need a researcher who can build a production-ready model that listens to a baby’s cry, watches the paired video, and decides—reliably—whether the cause is hunger, discomfort, or simple attention seeking. Audio and video must be fused inside one architecture; running them in parallel but independently will not satisfy our accuracy goals. You may use the deep-learning stack you trust most (PyTorch, TensorFlow, Keras, OpenCV, torchaudio, etc.) provided the final network can run in real time on an edge device and be exported to ONNX or TFLite. I will share product constraints and a small proprietary data set; you will expand it through public sources or augmentation, perform rigorous cross-validation, and refine the model until we consistently exceed 90 % precision and rec...

I need an image classification AI model to run on a Raspberry Pi 4. This model will detect whether individuals are wearing PPE kits in static images. The primary application will be in industrial sites. Key Requirements: - The model should accurately classify images as 'PPE' or 'No PPE'. - It needs to be optimized for performance on Raspberry Pi 4. - The input will be static images, not live feeds or videos. Ideal Skills and Experience: - Proficiency in AI and image classification techniques. - Experience with model optimization for edge devices, especially Raspberry Pi. - Background in developing AI solutions for industrial applications is a plus. - Ability to deliver a robust and efficient model within budget constraints.