OpenCV Jobs

We're building a system that works similarly to sports auto-tracking cameras (e.g. Veo), but with a simpler, classical computer-vision approach — no deep learning or trained models needed. What we need: Camera stitching: Combine footage from two fixed cameras (mounted on one rig, overlapping field of view) into a single panoramic image (~180°), using calibration/homography. The cameras don't move relative to each other, so this should be a one-time calibration applied per frame. Motion-density tracking: From the panoramic feed, detect where players are concentrated (background subtraction / foreground blob density, not per-object classification) and use that to drive an automatic pan/crop — i.e. a virtual camera that follows the action without a human operator. ...

We're building a system that works similarly to sports auto-tracking cameras (e.g. Veo), but with a simpler, classical computer-vision approach — no deep learning or trained models needed. What we need: Camera stitching: Combine footage from two fixed cameras (mounted on one rig, overlapping field of view) into a single panoramic image (~180°), using calibration/homography. The cameras don't move relative to each other, so this should be a one-time calibration applied per frame. Motion-density tracking: From the panoramic feed, detect where players are concentrated (background subtraction / foreground blob density, not per-object classification) and use that to drive an automatic pan/crop — i.e. a virtual camera that follows the action without a human operator. ...

We're building a system that works similarly to sports auto-tracking cameras (e.g. Veo), but with a simpler, classical computer-vision approach — no deep learning or trained models needed. What we need: Camera stitching: Combine footage from two fixed cameras (mounted on one rig, overlapping field of view) into a single panoramic image (~180°), using calibration/homography. The cameras don't move relative to each other, so this should be a one-time calibration applied per frame. Motion-density tracking: From the panoramic feed, detect where players are concentrated (background subtraction / foreground blob density, not per-object classification) and use that to drive an automatic pan/crop — i.e. a virtual camera that follows the action without a human operator. ...

We're building a system that works similarly to sports auto-tracking cameras (e.g. Veo), but with a simpler, classical computer-vision approach — no deep learning or trained models needed. What we need: Camera stitching: Combine footage from two fixed cameras (mounted on one rig, overlapping field of view) into a single panoramic image (~180°), using calibration/homography. The cameras don't move relative to each other, so this should be a one-time calibration applied per frame. Motion-density tracking: From the panoramic feed, detect where players are concentrated (background subtraction / foreground blob density, not per-object classification) and use that to drive an automatic pan/crop — i.e. a virtual camera that follows the action without a human operator. ...

Necesito desarrollar una aplicación para Linux que automatice el procesamiento de imágenes. El objetivo principal es la automatización de tareas, por lo que no requiero una interfaz gráfica compleja; basta con un flujo por línea de comandos o una API sencilla. Alcance funcional: • La app debe tomar imágenes de una carpeta (o ruta indicada) y aplicar una serie de operaciones configurables: redimensionar, convertir formato y ejecutar filtros básicos. • El núcleo de las rutinas de alto rendimiento podrá escribirse en C++ (por ejemplo, usando OpenCV), mientras que la orquestación, configuración y llamadas al sistema estarán en Python. • Quiero un sistema modular para poder añadir nuev...

I want to develop an AI-driven application that takes raw footage and turns it into polished video with minimal manual input. The core idea is to streamline everyday editing tasks—cutting, trimming, colour matching, basic motion graphics—through machine-learning models so I can focus on creative direction instead of button-pushing. Because the exact feature mix is still open, I’m especially interested in solutions that can easily expand to cover automatic scene detection, audio clean-up and smart title/text overlays as the project grows. Feel free to propose a framework you know well—whether that’s Python with OpenCV, a TensorFlow or PyTorch model, or an integration on top of Adobe’s SDK—so long as the final result runs on Windows and outputs stan...

I’m looking for a Python-based workflow that takes my equirectangular photo collection and, for any two images I select, confirms whether they were shot from the same angle. Beyond the yes/no decision, the script must also: - check whether they are connected • calculate the scale ratio between the pair, - the angle yaw and pitch they connected • assign a reliability/confidence score to its assessment. sample dataset : i run the progam using cli, json output is fine All results should be written to a concise text report that I can easily parse or forward—feel free to suggest the most convenient plain-text structure. You’re free to use OpenCV, scikit-image, NumPy, or any other well-supported libraries so long as installation remains straightforward (p...

Security footage requires a detailed forensic examination so the individual captured on-camera can be clearly identified. The raw video contains several moments where the face is partially visible, yet heavy compression, low light, and motion blur currently obscure any reliable match. The task is to enhance the relevant segments, extract the sharpest stills, and annotate each frame with time-codes and clarity notes. Where possible, apply frame-by-frame stabilization, noise reduction, and colour correction so distinguishing facial or clothing features become unmistakable. Deliverables • Up-to-date forensic report (PDF) summarising techniques, enhancement settings, and confidence level for identification • A folder of high-resolution still images (PNG or TIFF) keyed to th...

We need an experienced WebAR / computer vision developer to create a browser-based virtual piercing try-on. Users should open a webpage on iPhone/Android, activate the camera, and see a virtual stud realistically positioned on their ear. The key challenge is reliable ear/eartlobe tracking while the head moves. This is NOT a request to copy existing commercial software. We want an independently developed solution using open-source or approved licensed technology. FIRST MILESTONE – PAID PROOF OF CONCEPT Deliver a working browser demo that: * Uses live mobile camera * Detects/tracks the head and ear * Places a virtual 2–4 mm stud on the earlobe * Keeps the stud reasonably anchored during head movement/rotation * Works on iPhone Safari and Android Chrome Possible stack: Media...

I’m looking for a skilled mobile developer who can deliver a polished face-swap application that runs natively on both iOS and Android. The app must handle two core scenarios: • Real-time face swapping through the camera preview • Face swapping on photos selected from the user’s gallery After a swap, users need a smooth way to share the resulting image or short video straight to their favourite social platforms via the standard system share sheets or integrated APIs. Performance and believability are key; I expect fast, well-aligned swaps that hold up under normal lighting and movement. You’re free to choose the toolkit—OpenCV, MediaPipe, ARKit/ARCore, or another reliable library—as long as the final builds pass store review and run well on cu...

I have a backlog of invoices, receipts and bank statements, all supplied as searchable and non-searchable PDFs. From each document I only need two categories of information pulled out: • the dates and amounts that appear on every page • the full itemised lines (description, quantity, unit price, line total) Customer names or addresses are not required this time, so the workflow can stay tightly focused on these data points. Ideally you will set up an OCR pipeline—Tesseract, ABBYY FlexiCapture, Amazon Textract, or a custom Python script with OpenCV—anything you are comfortable with that gets reliable accuracy. The final output should land in a neatly structured CSV or Excel workbook that I can import straight into my accounting software. Acceptance criteria &...