Viziune computerizată Jobs

We are developing a custom differential-drive Autonomous Mobile Robot (AMR) / Automated Guided Vehicle (AGV) with a payload capacity of 100kg–200kg. The navigation stack structure is completely in place, but we are facing critical software timing and coordinate frame tracking issues that prevent the local planner from executing smooth velocity commands. We need an experienced ROS Navigation / TF Expert to dive into our launch and configuration files, synchronize our clock sources, and get the robot navigating cleanly. Current Symptoms The Core Error: The robot freezes or stutters violently, throwing continuous Extrapolation Error: Lookup would require extrapolation into the future warnings when looking up transforms from odom to map. Path Following Failures: The local planner keep...

我正在为一套帕德尔球场 AI 视频分析系统寻找长期合作伙伴。第一阶段的目标是用 NVIDIA Jetson Orin Nano 8 GB 搭建一个可以落地演示的边缘推理原型；后续阶段继续协作，完成模型优化、云端集成以及系统调试。 第一阶段核心任务 在 Jetson Orin Nano 上接收两路 PoE IP 摄像头的 RTSP 流，使用 GStreamer 解码并保持稳定帧率 部署 YOLOv8n/s 目标检测模型，并结合 ByteTrack（或等效算法）实现多目标跟踪 同时处理双路输入，验证端到端性能，确保可实时输出球员检测框与轨迹 业务场景 系统需同时生成球员表现报告和精彩集锦，因此算法管线必须兼顾数据完整性与视觉效果。我更倾向在 Jetson 平台上深度利用 GStreamer；如你熟悉 FFmpeg，同样欢迎提出更优方案。 后续合作方向 √ 模型优化 √ 云端集成 √ 系统调试 理想背景 – 有 Jetson（Orin 优先）或同类边缘设备的部署经验 – 熟练搭建 GStreamer / FFmpeg 视频管道 – 熟悉 YOLOv8、ByteTrack 或等价检测+跟踪组合 – 如果你做过体育视频分析、多摄像头同步或者比赛数据可视化，将是加分项 请在提案中附上相关项目链接或 GitHub，简单说明你在 Jetson 或边缘视觉项目中的角色与贡献。期待与你一起把原型快速推进到可上线的完整解决方案。

I want to create an entertaining spokesman video where the on-screen speaker’s face is seamlessly replaced with a custom face taken from a photo I will supply. The final piece should look like a high-end deepfake: natural lip-sync, consistent lighting, and no noticeable artifacts, suitable for sharing purely as entertainment. Here is the flow I have in mind. I will give you: • the raw spokesperson footage (clean, well-lit, 1080p) • one high-resolution photo of the face that needs to be swapped in • any dialogue script or subtitles you might need for alignment You will handle the full deepfake pipeline—face extraction, training, compositing, colour matching, and final render—using whichever tools you are most comfortable with (DeepFaceLab, FaceSwap, St...

We are looking for a contractor with strong experience in computer vision, signal processing, multimedia systems, and Python-based research prototyping. The work involves designing and evaluating algorithms for video analysis, content protection, robustness testing, and experimental research. Ideal candidates should have experience with: Python OpenCV FFmpeg NumPy / SciPy Computer Vision Signal Processing Image / Video Processing Experimental Evaluation Technical Report Writing Selected candidates will be asked to complete a paid technical assessment involving the design and evaluation of a video-processing algorithm.

I am putting together an instructional animation and need a five-person AI task-force to power the technical side of the production. The core roles are Machine Learning Experts, Data Scientists, and Computer Vision Specialists—ideally people who feel at home moving between Python notebooks, TensorFlow / PyTorch stacks, and OpenCV pipelines. Your main focus will be data analysis and algorithm development. Concretely, I’ll count on you to: • Analyse raw video and motion-capture data so we can pinpoint the most engaging sequences to animate. • Develop custom algorithms that automate character rigging, lip-sync, and scene transitions, feeding those outputs directly into our animation software (Blender and After Effects). • Optimise and document the entire workf...

PROJECT CONTEXT We are building a Computer Vision system for video analysis. We need to hire 2 profiles: 1. ARCHITECT (technical design, decisions, oversight) 2. DEVELOPER (implementation, coding, optimization) This is a 6-8 week MVP project to build the FOUNDATION of our system (foundation + basic detection/tracking). After Phase 1 validation, we may extend with future phases. CRITICAL POINT This project CANNOT be solved with: - LLM (ChatGPT, Claude, Gemini) - Generic vision APIs (Google Cloud, Azure) - Low-code solutions or templates - "Quick solutions" This project REQUIRES: - Real expertise in classical Computer Vision - Deep Learning (PyTorch or TensorFlow) - Proven experience: object detection + video tracking - GPU optimization (NVIDIA CUDA) - Production-grade code ...

I’m assembling a worldwide team to design and deploy next-generation intelligent systems. My own focus is Artificial Intelligence, and every project on our roadmap—from rapid prototypes to production-grade platforms—relies on solid expertise in the field. The core technical stack revolves around: • Machine Learning • Natural Language Processing (NLP) • Computer Vision If you work comfortably across those areas and can demonstrate real-world results, we should talk. Contributions may range from model architecture and data-pipeline design to API integration and performance tuning; exact scopes will be matched to each contributor’s strengths. When you send your proposal, highlight the experience that best proves you can deliver impact quickly (p...

I need an AI-driven solution that will remove the manual grind from our image-heavy data entry and management flow. The end product should pull raw image files from a designated source, read the embedded or visual information, classify or tag each file correctly, and populate our existing database automatically. Accuracy is the top priority; any mislabeled or unprocessed images must be flagged for human review rather than slipping through. Here is what success looks like for me: • A repeatable training pipeline (Python preferred,TensorFlow or PyTorch are both fine) capable of handling new images as the dataset grows. • An inference service that runs on-prem or in the cloud—AWS S3 / Lambda is ideal, but I’m open to workable alternatives—that accepts a batch ...

I need a cross-platform mobile application that lets me snap or upload a customer’s photo, pick a fabric from my catalogue and instantly preview how that cloth will look on the person as a shirt, blazer or pair of trousers. The app must run smoothly on both iOS and Android and deliver realistic, well-lit visualisations in real time, so solid computer-vision and generative AI skills are essential. My workflow in the shop is simple: take the picture, choose the garment type, click another picture of fabric, select male or female body time, day time or night time and app must show a mockup or how that fabric would look on the person. Because this tool will be customer-facing, speed and image quality are non-negotiable; I’m looking for crisp edge detection, natural fall of clot...

AI Agent Evaluator Remote · Contract · Flexible Hours We're hiring evaluators to help assess and benchmark cutting-edge AI agents. This is hands-on work at the frontier of agentic AI — not prompt writing, not basic QA. You will be designing complex real-world tasks, running them across multiple large language models, and producing the structured evaluations that shape how the next generation of AI agents are trained. What You'll Do You will design multi-stage agent tasks across real-world domains including health, finance, productivity, relationships, and personal exploration. Each task must require the agent to coordinate across multiple tools and systems, manage persistent state, handle realistic friction points, and produce a verifiable final artifact. Tas...

I want shoppers on the Laxmi Opticians site to slip on any frame from our catalogue without leaving the page. The idea is a lightweight, 2-D computer-vision overlay that precisely positions sunglasses and prescription glasses on a customer’s face, working fluidly on both desktop and mobile browsers. No full 3-D modelling, no manual prompt engineering—just an instant preview that feels as natural as looking in a mirror. The experience must offer two entry points: • Real-time overlay through the user’s webcam or phone camera. • Photo upload for those who prefer to try glasses on a still image. Accuracy is critical: pupils should align, temple angles should respect head pose, and scaling must stay consistent as users lean closer or farther from the camera. I&...

AI Agent Evaluator Remote · Contract · Flexible Hours We're hiring evaluators to help assess and benchmark cutting-edge AI agents. This is hands-on work at the frontier of agentic AI — not prompt writing, not basic QA. You will be designing complex real-world tasks, running them across multiple large language models, and producing the structured evaluations that shape how the next generation of AI agents are trained. What You'll Do You will design multi-stage agent tasks across real-world domains including health, finance, productivity, relationships, and personal exploration. Each task must require the agent to coordinate across multiple tools and systems, manage persistent state, handle realistic friction points, and produce a verifiable final artifact. Tas...

I need a complete system that can turn data written in the ancient Brahmi and Sharda scripts into a scannable, QR-style matrix and then read it back reliably. The work splits into two tightly linked parts: 1) Pattern engine Build an algorithm that takes Brahmi or Sharda text (Unicode strings supplied by me) and outputs a square, high-contrast image resembling a QR code. Include error-correction logic so the pattern survives moderate camera tilt, blur, and 20 % visual noise. A lightweight CLI or library in Python, Java, or C++ is fine as long as I can call it from other projects later. 2) Dual-platform scanner Create an app for both iOS and Android whose main task is to scan and decode these patterns. After scanning, the screen should show an informative read-out: the detected script,...

I am refining the mapping and localisation stack on a mobile robot and need an engineer who lives and breathes SLAM. The sensor mix is still open—camera-only, RGB-D, or a lidar-centric approach could all work—so part of your first task will be to advise on the optimal sensing strategy for real-time, drift-free operation. You will then design or adapt the SLAM pipeline, implement it in C++/Python (ROS2 friendly), and make sure it integrates cleanly with my existing navigation software. Low-latency loop-closure, map optimisation, and robust relocalisation in feature-poor areas are non-negotiable. Once things are running, I expect measurable frame-to-frame accuracy improvements and a clear performance report that includes CPU/GPU utilisation and update rates. Deliverables ...

I want to build a simple yet reliable mobile application that lets my field-workers mark their attendance the moment they snap a photo. The app must run smoothly on both Android and iOS and use face-recognition to validate each selfie automatically. As soon as the match is confirmed, the system should time-stamp the record and tag the exact GPS coordinates so I can verify where the employee was standing when the photo was taken. Core flow 1. Worker opens the app, the camera launches instantly. 2. They take a photo; the face-recognition engine checks it against a stored profile. 3. If the face matches, attendance is logged right away together with latitude, longitude and time. 4. All data syncs to a secure back-end; if the phone is offline it queues the record and uploads once a ...

The goal is to deliver a stand-alone Python desktop application that records classroom or workplace attendance through real-time face recognition. The stack is fixed: Python 3, OpenCV, and the standard Tkinter GUI toolkit. Core flow 1. A compact Tkinter window opens with clearly labelled buttons. The interface must, at a minimum, let a supervisor register new users. 2. During registration the system captures multiple webcam frames per person, automatically saving at least 20 crisp face crops for stronger training data. 3. An LBPH model is trained on those images and stored locally; subsequent launches should reload the latest model without retraining. 4. When recognition mode is active the app checks each detected face against the model and writes a time-stamped entry to a CSV fil...

a) Setting a concrete Rubric-based evaluation criteria (as is formally done in LLMs' response evaluation) such as: - Accuracy - Instruction following - Reasoning quality - Completeness - Clarity - Safety - Coding correctness - Hallucination risk b) To help optimize prompts, prompt engineering frameworks can be employed such as zero-shot prompting, few-shot prompting, chain-of-thought prompting. c) All errors in the model's responses can be segregated into different error types like Factual error, Reasoning error, Instruction failure, Formatting issue, Hallucination, Safety issue, Code bug, etc so that we can deeply analyse the performance so all the models and figure out their specific weaknesses.