คอมพิวเตอร์วิทัศน์ Jobs

We're looking for engineers and other STEM professionals to help push the limits of AI reasoning. Each task is simple in shape but hard in substance: you take a real image from your area of expertise and pair it with a challenging problem that a non-expert couldn't solve. What you'd do: - Choose or take a real, copyright-clear image with no annotations or markups - Write a difficult question about it that draws on your professional knowledge - Provide a clear, correct answer and reasoning Who this is for: - Working engineers (mechanical, civil, electrical, structural, software, etc.) and other STEM professionals - People who can spot the details in an image that only an expert would notice - Strong written English and attention to detail

I am looking for an experienced Python developer with OCR, OpenCV, real-time screen monitoring, and Indian stock-broker API integration experience to develop a Windows-based automated trading application. The application will continuously monitor a selected rectangular area of my computer screen, where an NSE options tick table is displayed. The software must identify newly appearing tick rows, extract the information from the screen, convert it into structured market data, apply predefined trading conditions, and place trades through the broker's official API when all conditions are satisfied. The screen contains information such as: Time Instrument/Name Expiry CE/PE Strike price Reference value shown in brackets Rate Diff Quantity Value (Lk) For example: NIFTY 15 Sep 2026 PE 23...

I'm looking for an experienced AI trainer to conduct a course on Computer Vision. The training will be for intermediate learners and will cover the following topics: - Image Classification - Object Detection - Image Segmentation Ideal Skills and Experience: - Proficiency in Computer Vision techniques and tools - Experience in teaching or training, especially at an intermediate level - Strong understanding of Image Classification, Object Detection, and Image Segmentation - Ability to create structured, engaging, and informative training materials - Patience and good communication skills Please provide a portfolio or examples of previous training conducted. Looking forward to your bids!

Looking for an AI/Deep Learning developer to develop a research project for skin lesion classification using dermoscopy images. The project combines Diffusion Models for hair removal, Vision Transformer (ViT) for classification, and Explainable AI using Grad-CAM/Attention Maps. The dataset will be based on the ISIC Archive. Required: Python, PyTorch/TensorFlow, Deep Learning, Computer Vision, ViT, Diffusion Models, and Explainable AI.

I need a complete computer-vision pipeline that lets me watch multiple indoor and outdoor cameras and immediately know who is where. The core goal is security surveillance, so every component has to run in real time without noticeable lag. Here is what the system must do: • Detect every person entering the frame, day or night, in varied lighting and weather. • Track each individual seamlessly across several overlapping or non-overlapping cameras (multi-object tracking). • Re-identify the same person when they reappear on a different camera, even after minutes out of view. • Expose a live stream API or dashboard that shows bounding boxes, unique IDs, and confidence scores as events unfold. I am open to the specific model stack—YOLO, Detectron2, DeepSORT, St...

The Goal: I need an expert Python/OpenCV developer to build a fast and precise card recognition bot for Pot Limit Omaha (PLO). The script will read all cards from a single application window. What I Will Provide: Marked-Up Screenshots: You will receive clear screenshots where I have visually marked the exact locations of: The 4 skewed hole cards. The 5 flat community cards. The target areas for mouse clicks. A Complete Card Template Library: A full set of 52 clean card images for perfect matching. Your Technical Responsibilities: 1. Data Extraction (Your First Task): Based on my screenshots, you will extract all necessary (X, Y) pixel coordinates and create a clean JSON configuration file. This is the data foundation for the script. 2. Hole Card Recognition (4 Cards - Perspective Task)...

I’m looking for reliable help with the image side of an AI training project that revolves entirely around photographs. Your main focus will be preparing and managing those photos so our models learn accurately and efficiently. Here’s what I need from you: • Organise incoming photo batches, check for duplicates or corrupted files, and file them in the agreed folder structure. • Annotate or label images when required—bounding boxes, masks, or simple classification tags depending on the current sprint—using common tools such as CVAT, Labelbox, or a platform you’re comfortable with. • Track progress in a shared spreadsheet so dataset coverage, class balance, and outstanding tasks are always clear. • Flag edge-cases or low-quality shots...

# Micro1 Generalist Project — Looking for an Experienced Freelancer I’m looking for a freelancer who has experience with **AI generalist work, data annotation/data labeling, video analysis, and following detailed guidelines** to help me with a Micro1 Generalist project. ### Skills Required * AI/ML generalist knowledge * Video annotation and video analysis * Data labeling/annotation * Strong attention to detail * Ability to identify errors and inconsistencies in videos * Understanding and following detailed instructions and guidelines * Good written English and communication * Ability to work independently * Comfortable using online annotation/AI tools * Good time management * Ability to maintain consistent quality across multiple tasks ### What You Will Do The work may invo...

I have Arabic Multimodal Dataset (Text + Image) designed for Multimodal Aspect-Based Sentiment Analysis (MABSA). Each data point consists of an Arabic review text paired with one or more relevant images. I am seeking an expert LLM Specialist to build a comprehensive, state-of-the-art experimental framework to validate the dataset's learnability and establish standard benchmarks for the scientific community. The project involves task-specific fine-tuning using modern text and vision-language architectures The dataset must be evaluated across two distinct tasks following standard evaluation benchmarks (e.g., SemEval standards): Task 1: Aspect Category Detection (Identifying specific predefined aspect categories mentioned). Task 2: Aspect-Based Sentiment Polarity Classification (Classify...

I am looking for an experienced AI/ML developer to build and integrate an advanced AI video transformation feature into my existing portal. The system should create realistic face movements and body motions to simulate live yoga sessions. I will provide a source video, my visual references, and voice/audio samples. The aim is to replace the source face with mine while preserving natural expressions, head movement, body gestures during yoga poses, as well as lip synchronization with the provided voice. It should convincingly mimic a live session's feel. Applicants should have expertise in AI video generation, face replacement, body motion tracking, voice cloning, and backend integration techniques. I'm open to suggestions on using suitable AI models, APIs, or a self-hosted soluti...

Developed a healthcare AI application for lung disease classification using chest X-ray images, combined with an interactive medical chatbot and voice assistant. The classification component analyzes chest X-ray images and predicts the corresponding lung disease category. Alongside the classification model, I was responsible for developing the AI Chatbot and RAG system, allowing users to ask questions about lung diseases, symptoms, and medical information. I implemented Retrieval-Augmented Generation (RAG) to connect the chatbot with a medical knowledge base, enabling it to retrieve relevant information and generate more informative and context-aware responses. The system also included a Voice Assistant to provide a more natural voice-based interaction with the user. Key Features: Che...

Looking for an experienced developer to build an AI-based UAV detection and tracking system for a custom ArduPilot quadcopter using Raspberry Pi 5 and AI HAT+ 2. Scope includes real-time drone detection, object tracking, MAVLink integration, safe autonomous follow/stand-off navigation, telemetry logging, GCS interface, failsafes, SITL testing, and complete source-code handover.

I have a single video frame captured in daylight that shows the front of a vehicle. Unfortunately, the plate is extremely blurry and all normal sharpening tricks have failed. I need a forensic imaging specialist who can push well beyond routine filters—think de-blurring algorithms, AI-based super-resolution, frame averaging, or any other proven technique—to extract a legible plate number. Source material • One “very blurry” video frame pulled directly from the original recording. • Daytime lighting; no night-vision artifacts to worry about. What I would like back • A cleaned, high-confidence still image that clearly shows the license plate characters. • A brief note (a paragraph or two is fine) outlining the process and software you use...

Merhaba, Kitantik mağazam için basit bir ürün yükleme otomasyonu yaptırmak istiyorum. İstediğim sistem şu şekilde çalışacak: 1. Telefon veya bilgisayardan ürün/kaset fotoğrafını sisteme yükleyeceğim. 2. Fotoğraftaki renkli sticker algılanacak. 3. Sticker rengine göre daha önceden belirlediğim fiyat otomatik atanacak. Örneğin: - Kırmızı = 250 TL - Mavi = 200 TL - Yeşil = 150 TL - Sarı = 100 TL Bu fiyatları daha sonra panelden kendim değiştirebilmeliyim. 4. Yapay zekâ fotoğrafı analiz ederek mümkün olduğunca: - sanatçı - albüm/kaset adı - marka - ürün türü - fotoğrafta görülebilen diğer bilgiler bilgilerini çıkarsın. 5. Fotoğraf...

The goal is to build a small but neatly-structured video dataset that will feed a computer-vision model focused on everyday domestic activities. Each entry in the dataset must show a single household task—cleaning, cooking, or organizing—from two synchronized viewpoints: • First-person: a head-mounted (egocentric) camera capturing what the performer sees. • Third-person: a fixed, tripod-mounted camera giving a clear side or frontal view of the same action. For every recorded task, both clips should start and end together, be labelled with the task name, and be delivered in lossless or high-quality H.264 MP4 at 1080p or better. Natural indoor lighting is fine as long as the objects, hands, and completed result are clearly visible. Acceptance criteria 1. One pair...

I have a collection of 5,000 images that must be annotated with 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 c...

I’m building a computer-vision pipeline focused on reliable detection and recognition of human faces and full-body figures. 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 weig...

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. ...