Vizion Kompjuterik Jobs

I want to see a working proof-of-concept that can watch a live webcam feed in an indoor setting and reliably decide whether someone is merely holding a phone or actively using it. The prototype must process the video stream in real time, recognise the presence of a smartphone, then look for behavioural cues—hand placement, posture and, ideally, gaze direction—to confirm active usage. Whenever the model judges that the phone is being used, it should trigger an audible or visible alarm on the host machine instantly; no other logging or alert channels are required for this first iteration. I am happy for you to choose your preferred computer-vision stack (e.g. OpenCV, MediaPipe, PyTorch, TensorFlow, ONNX) as long as the end result runs on a typical workstation without specialise...

I want to see a working proof-of-concept that can watch a live webcam feed in an indoor setting and reliably decide whether someone is merely holding a phone or actively using it. The prototype must process the video stream in real time, recognise the presence of a smartphone, then look for behavioural cues—hand placement, posture and, ideally, gaze direction—to confirm active usage. Whenever the model judges that the phone is being used, it should trigger an audible or visible alarm on the host machine instantly; no other logging or alert channels are required for this first iteration. I am happy for you to choose your preferred computer-vision stack (e.g. OpenCV, MediaPipe, PyTorch, TensorFlow, ONNX) as long as the end result runs on a typical workstation without specia...

Title: AI Developer Needed – Simple Art Image Analysis Web App (Prototype) Project Description: I am looking for an AI developer to build a simple prototype (MVP) of a web application that analyzes images of artworks. The application should allow a user to upload an image of a painting or artwork and receive a basic AI-generated analysis. This is an early-stage prototype, so the solution can use existing AI models or APIs. The goal is speed and simplicity. Core Features: - Upload artwork image - Image analysis using an AI model - Detect artistic style or possible artist - Generate a short explanation about the artwork Examples of artworks: - The Starry Night – Vincent van Gogh - Mona Lisa – Leonardo da Vinci Preferred Technologies (flexible): - Python ...

I'm seeking an experienced ROS2 developer to implement navigation and path planning for a robot in mixed environments (both indoor and outdoor). The project is urgent and needs to be completed as soon as possible. Key Requirements: - Develop robust navigation algorithms - Ensure reliable path planning in mixed environments - Integrate with existing ROS2 framework - Test and validate in real-world scenarios Ideal Skills: - Proficiency in ROS2 - Strong background in robotics navigation - Experience with mixed environment challenges - Ability to meet tight deadlines - experience with clear path jackal robot is good Please provide examples of similar work done and your estimated timeline for completion.

I need a YOLOv8 model trained to detect and classify approximately 12 types of fishing vessels from provided images. The dataset will be in YOLO/COCO format. Requirements: - Target accuracy: ~90%+ - Input image resolution: 1280x1280 - Performance metrics: Precision, Recall, F1 Score - Inference optimization: Balanced between speed and accuracy Deliverables: - Trained weights (.pt) - Training script - Inference code Ideal Skills & Experience: - Expertise in YOLOv8 and PyTorch - Experience with object detection and model training - Familiarity with performance metrics and optimization techniques

I'm seeking a Python RPA expert specializing in computer vision-based (Offline) web scraping for a web search and document download project. You'll scrape sites, download/classify documents (e.g., public records via CV/NLP), design neural networks for extraction, and build scalable workflows. Patience for alpha testing, finetuning iterations is key. Key Requirements: • Pure Python RPA, with the core orchestrator, no third part tool. • Web navigation/ scraping with Selenium/Playwright: document download, classification, OCR/text extraction. • Build/train neural networks (e.g., CNNs for image doc classification). • NLP expertise with spaCy for entity extraction. • Computer vision using TensorFlow/OpenCV (offline Vision Libraries preferre...

I’m building a proof-of-concept layer that intercepts any image or video delivered through a web browser and automatically replaces detected humans or animals with a neutral “shadow” placeholder. The aim is to strip away elements that might provoke irrational responses while keeping the surrounding media unchanged. Here’s what I need you to deliver: • A working browser-based solution (extension, local proxy, or another approach you propose) that processes both static images and streaming video in real time. • Reliable detection of people and animals using modern computer-vision tools (e.g., TensorFlow, OpenCV, YOLO, or alternatives) and seamless substitution with a non-identifying silhouette or blurred overlay. • A simple toggle UI so users can...

I want to see a working proof-of-concept that can watch a live webcam feed in an indoor setting and reliably decide whether someone is merely holding a phone or actively using it. The prototype must process the video stream in real time, recognise the presence of a smartphone, then look for behavioural cues—hand placement, posture and, ideally, gaze direction—to confirm active usage. Whenever the model judges that the phone is being used, it should trigger an audible or visible alarm on the host machine instantly; no other logging or alert channels are required for this first iteration. I am happy for you to choose your preferred computer-vision stack (e.g. OpenCV, MediaPipe, PyTorch, TensorFlow, ONNX) as long as the end result runs on a typical workstation without specia...

I’m building an MVP that inspects coal quality from both photos and short videos. The system must return a simple breakdown—e.g., “Coal 75 % / Stone 25 %”—and lay the groundwork for optional size-distribution analysis in later releases. What you’ll have to work with • A batch of truck-loading videos and corresponding lab quality reports. Phased scope Phase 1 – Extract still frames from the supplied videos and organise them into a clean, labelled image set. Phase 2 – Train a computer-vision model (YOLO or a comparable CNN in Python) able to distinguish coal from stone. Baseline accuracy is sufficient for now; we can iterate later. Both real-time and batch inference modes should be supported. Phase 3 – Wrap the model in...

We are looking for a web designer to create a corporate website (14 pages) for a company specializing in construction material installation and public facility construction. Requirements: Responsive design (PC / Tablet / Mobile) Clean and modern design Attention to detail -We Provide: Text and images Preference: Female designers preferred. Please send: Portfolio Estimated timeline Your price. reference site:

OpenCV Hill Climb Project – Description Project Title: Autonomous Hill Climbing Robot using OpenCV Project Description: Developed an AI-based computer vision system using OpenCV and Python that enables a robot/vehicle to automatically detect and climb slopes or hills. The system processes real-time camera input to analyze terrain conditions such as slope direction, obstacles, and surface edges. Implemented image processing techniques like edge detection, contour detection, and gradient analysis to determine the steepest safe path for climbing. Applied the Hill Climbing optimization algorithm to continuously choose the best next movement direction based on terrain analysis. Integrated real-time decision making so the robot adjusts movement dynamically while climbing uneven surf...

I have 15 security-camera videos recorded at a petrol pump, each running for roughly 10 hours (about 150 hours of footage in total). For every vehicle that appears, I need two key pieces of information captured: • the half-hour time-slot in which it arrived (e.g., 09:00–09:30, 09:30–10:00, etc.) • how long that vehicle remained on the premises Within each 30-minute bin, please provide a count of vehicles in the following hierarchy: Broad classes – 2 Wheeler – 3 Wheeler – 4 Wheeler – Truck / Bus / Tractor / other special vehicles Detailed 4-wheeler breakdown (as requested via the form) SUV, Sedan, Hatchback, Pickup Truck, Van Heavy & special-vehicle breakdown Truck, Bus, Tractor, JCB, or any other special vehicle you...

We are looking for native Hindi-speaking freelancers in India to participate in a simple image capture from smatphones for daily items project. The goal of this project is to help improve Hindi text recognition systems. 1- Task Description You will take photos of real-life objects that contain visible text using your smartphone camera. Examples: Business cards, contact cards, name tags etc Real Receipts , Bills etc Real Schedules or timetables etc Other everyday items with printed text For each object: Take 3 photos Use different angles and lighting Image Requirement: 1 Asset = 3 Images (Front/Center, Left, and Right angles) Make sure the images are clear and not duplicated 2- Hindi Image Categories to Collect from Smartphone Manually Please capture images of the following ...

We are hiring remote contributors to create photo-based language data using everyday materials found around you. This project focuses on collecting natural, real-life text captured through a phone camera. What You’ll Do - Photograph common objects that contain written text (printed or handwritten). - Provide three unique shots per item, changing position, distance, or lighting. - Ensure content is original and varied. - Most of the visible text (minimum 75%) must be in your local language. Eligibility - Fluent in the target language (native or near-native). - Physically located in a country where the language is used. - Own a smartphone capable of taking clear photos. How It Works - Upload images through a Google Form. - Submissions are reviewed individually. - Only valid, clear, ...

I want to build a small, self-contained charging station that wakes up only when it “sees” a bottle and a can. The core will be an Arduino (any recent 32-bit board is fine) tied to a solar panel and battery pack. A lightweight AI vision module or camera running something like TensorFlow Lite or OpenCV should continuously—or on a duty-cycled basis—look for bottles. The moment a bottle is detected, the system must move straight into the charging routine without waiting for external confirmation; no alerts, no logging, just automatic activation. What I need from you • Complete Arduino firmware that integrates the vision trigger with the charge-controller logic. • A schematic / wiring diagram showing how the camera, solar panel, charge controller, and any...

I have continuous video footage from live inspection of steel flat bars strips our production line and need a complete deep-learning pipeline that flags surface, structural, and functional defects in real time. The raw videos are already labeled by timestamp; frame-level annotation may still be required for optimal accuracy. Scope • Design and train a deep neural network—CNN, transformer, or hybrid model—that detects all three defect categories directly from video streams. • Implement preprocessing (frame extraction, augmentation, ROI isolation) and post-processing (tracking, alert generation) in Python using libraries such as PyTorch/TensorFlow and OpenCV. • Optimise for inference on an on-premise GPU; latency under 200 ms per frame is the target. &bull...

I need a single AI application that can see, hear and speak to the user. Using my own OpenAI key (or, if you prefer, a Gemini or Claude endpoint), I want you to wire conversational logic with the device camera so the assistant can recognise whatever the lens captures—faces, emotions, objects, actions, text, you name it—then hold a natural dialogue about what it sees. The build has to run everywhere: a mobile version for iOS & Android, a web app that works in the browser, and a desktop release for Windows and macOS. Users should be able to create an account, log in, and start interacting immediately. Speech-to-text converts their voice to prompts, vision models process the live feed, and text-to-speech delivers the reply in real time. For LLM calls, default to ChatGPT via ...

I’m building a ROS 2 pipeline that must reliably spot nuts and bolts in a live camera feed and publish their positions to the rest of my stack in real time. Your job is to create the complete vision-detection module—from model training or fine-tuning through to a clean ROS 2 node that subscribes to an image topic and spits out the detected objects with bounding boxes (or masks) and a confidence score. OpenCV, TensorFlow/PyTorch and any of the common ROS 2 image-transport plugins are all fine as long as the final node runs on Humble and stays GPU-agnostic (CUDA acceleration is a bonus, not a requirement). I already have a test rig with a standard USB camera; if you need specific calibration images I can capture them for you. Please deliver: • Source code for the detection...

I would like help finishing a program I started using Cursor AI. I want to be able to use a 3d stl file of the bottom of foot and overlay an image of a foot orthotic to match the bottom of the foot.

我正在为一款工业相机进行 ISP 图像测试与色彩调试，目标是在 1 个月内交付可量产的调试参数。任务仅针对静态图像，核心是通过反复测试和优化，让相机在多种光照与色温条件下都能还原准确、自然的色彩。 主要工作内容 • 制定静态图像测试方案：包括分辨率卡、人像卡、灰阶卡等常规靶标及光源条件 • 采集 RAW 与 YUV / JPEG 对比样张，输出测试报告 • 根据测试结果微调白平衡、色彩矩阵、Gamma 等 ISP 模块参数 • 给出最终可直接烧录的参数表，并附带调试说明书 完成标准 1. 色彩 ΔE 满足既定工业相机参考值 2. 典型场景（室内、室外、弱光）均通过对比评审 3. 提交完整测试数据、调试过程记录及最终参数 时间要求 全部工作须在 1 个月内完成，并支持 1 次远程复测协助。 我更看重相关经验。请在申请中突出您以往做过的相机 ISP、色彩或图像质量调优案例，以及常用工具链（如 IQ Tuning, Imatest, X-Rite 或自研脚本等）。如果能在同行业项目中展示过可衡量的提升效果，将优先考虑。