Closed
Posted
Paid on delivery
I’m building a computer-vision–driven external tool for PC and console games such as Fortnite, NBA 2K27 and Rainbow Six Siege. The system is designed around screen capture and machine vision rather than direct memory access, with a modular overlay, networking/version checks and configurable game profiles. Core pipeline: PS5 / PC game ↓ Remote Play / Capture ↓ Helios / Unity Video Capture ↓ CV frame ↓ Computer Vision ↓ YOLO / Roboflow ↓ Players / heads / objects detected ↓ Tracking + FOV + telemetry ↓ GUI / ESP / Radar Deliverables: • Source-available CV models, overlay renderer and configurable targeting logic • Binary release with self-update and licensing hooks • Performance/testing report across supported games • Setup and API documentation for future game profiles Target requirements: • Stable high-FPS overlay with very low added latency • Runtime-adjustable FOV, smoothing and target/bone priorities • Detailed logs and performance telemetry • Clean, modular code with no hard-coded paths or secrets 1. What Computer Vision is Computer vision (CV) analyzes images or video and extracts information software can reason about. A frame is just pixels. CV converts them into structured data such as: Player: x, y, width, height, confidence Head: x, y, confidence Capture gives you pixels; CV gives those pixels meaning. 2. What Helios does Helios is the host/runtime around the CV pipeline: video frame → CVPython runtime → GCVWorker → Python logic GCVWorker is not the AI. It is the interface between Helios and the Python CV code. A compatible worker exposes methods such as __init__(width, height) and process(frame). 3. What a CV frame is A frame is one image from the live stream. At 60 FPS, each frame is about 16.67 ms apart; at 120 FPS, about 8.33 ms. The system has separate rates: Capture FPS → Inference FPS → Tracking FPS → GUI FPS They do not have to match. 4. What YOLO does YOLO (You Only Look Once) is an object-detection neural network. It can return classes, confidence scores and bounding boxes, which can be converted into center points, head points and distance from the crosshair. 5. Why a game-specific YOLO model matters A generic model may detect “person,” while a game-specific model can be trained for classes such as “player” and “head.” A Fortnite-specific model can therefore provide more useful detections than a generic model. 6. Head detection There are two approaches: • Direct head detection: the model predicts the head location directly. • Head estimation: if only a player box is available, the program estimates the head near the top of that box. Direct head detection is more precise because it uses an actual model output instead of a rough proxy. 7. Target tracking Detection asks, “Where are the players in this frame?” Tracking asks, “Is this the same player I saw before?” Tracking helps reduce target switching and visual jitter. 8. FOV In this CV system, FOV defines how far from the screen center/crosshair a target can be before it is ignored. Smaller FOV: → fewer candidates → less switching → less processing Larger FOV: → more candidates → more choices → potentially more false selections 9. Confidence YOLO returns a confidence value for each detection. A minimum threshold can reject weak detections, but confidence is not a guarantee of correctness; a model can still be confidently wrong. 10. ESP ESP is the visualization layer for CV detections. YOLO finds the target; the ESP renderer draws boxes, head markers, snaplines or other indicators. 11. Radar Radar is another visualization of the same detections, usually as a simplified 2D view rather than an overlay directly on the game image. 12. Visibility checks A simple 2D detector only proves that target pixels are present. It does not reliably prove that a target is visible through the environment. True occlusion analysis can require depth, segmentation, raycasts or game-engine information. A basic YOLO frame alone should not be treated as a true wall/occlusion check. 13. Roboflow Roboflow can host CV models and multi-step workflows. Conceptually: Frame → Workflow → Processing → Result A workflow may contain a model, filtering, postprocessing and output steps. The actual workflow definition should be used rather than guessing what its outputs are. 14. Roboflow in the live pipeline The intended flow is: Helios frame ↓ Latest frame ↓ Roboflow workflow ↓ Detections ↓ Parse result ↓ Tracking ↓ ESP / Radar / Telemetry Latency matters. If capture runs at 60 FPS but an inference request takes 120 ms, processing every frame synchronously creates a backlog. A better real-time design is “latest frame wins”: keep only the newest frame and discard stale ones. 15. Unity Video Capture UnityCapture is a Windows virtual camera/DirectShow mechanism; it is not Fortnite’s renderer. Conceptually: Video source → UnityCapture → Windows camera device → Helios/OpenCV/other program It is useful only when the game image is actually routed through that capture path. If Helios already provides the frame directly, the direct Helios → CVPython path avoids an unnecessary capture layer. 16. Latest-frame architecture If the game produces 60 FPS but the model can process only 30 FPS, queueing every frame makes detection increasingly stale. Better: New frame arrives → replace old frame → process newest frame That keeps analysis close to the current game state instead of processing frames from hundreds of milliseconds ago. 17. Inference latency Inference latency is the time the AI spends processing one image. At 60 FPS, the frame budget is about 16.67 ms, so lower end-to-end CV time generally allows the system to keep up more easily. 18. End-to-end latency CV latency is only one part of the total chain: Controller input → PS5 → Remote Play → video encoding → network → decode/capture → CV → display Therefore: CV latency ≠ total game latency A CV pipeline cannot reduce Remote Play or network latency to zero. 19. GPU inference On supported NVIDIA hardware, model inference can use CUDA and FP16. This can reduce memory use and improve throughput, but the result depends on the GPU and workload. 20. Image size YOLO input size affects the speed/detail tradeoff: 640×640 → generally faster, less detail 960×960 → generally slower, more detail The goal is to balance accuracy and latency for the actual hardware. 21. ROI ROI means Region of Interest. Restricting detection to a relevant area can reduce the amount of image the model must process. 22. Preprocessing Before inference, the pipeline may: capture → crop → resize → color-convert → normalize → model Poor preprocessing can hurt accuracy even when the model itself is good. 23. Postprocessing After YOLO returns predictions, the program can: • filter by confidence/class • calculate head points • calculate distances • select targets • track targets • apply smoothing/prediction YOLO is only one component of the full CV system. 24. Controller vs CV The controller and CV pipelines are separate. VIDEO SIDE: Helios → CV → YOLO/Roboflow INPUT SIDE: Controller → Remote Play / controller transport → Windows They can share information for telemetry, diagnostics or training, but they are fundamentally different subsystems. 25. Visual target lock vs automated input “Target lock” can mean several different things. Visual lock: detect → choose → highlight target Input correction: detect → calculate delta → change controller/mouse input Fully automated aiming: detect → predict → change input → fire These are different levels of automation. 26. Prediction Prediction estimates where a moving target may be on the next frame. For example, if the head moves 800 → 810 → 820, a simple estimate might place the next position near 830. Prediction works best when combined with tracking and smoothing. 27. Smoothing Smoothing reduces jitter in detected positions. More smoothing: → steadier → more lag Less smoothing: → more responsive → more jitter 28. Why real-game testing matters Different environments can change the visual stream through network delay, Remote Play timing, frame pacing, buffering, resolution, HUD state, motion and compression. Meaningful testing should use the real Remote Play connection, real game mode and real capture path—not only local testing. 29. Important metrics Useful metrics include: • Capture FPS • CV FPS • CV time • Frame age • Dropped frames • Detection confidence • Target switching • Head error X/Y These reveal much more than a simple “AI ON” indicator. 30. The full system The pipeline is not one component: Remote Play ↓ Video transport ↓ Capture ↓ CVPython ↓ Detection ↓ Tracking ↓ Visualization ↓ Controller A problem anywhere in this chain can look like an AI problem. For example, poor capture can create blur, lower confidence and target jumping even when the model itself is fine. Your setup can be summarized as four layers: • Remote Play — PS5 video/controller connection • Helios / CVPython — live frame acquisition and processing • CV / YOLO / Roboflow — understanding the frame • GUI / ESP / Radar — displaying the results
Project ID: 40727779
87 proposals
Remote project
Active 3 days ago
Set your budget and timeframe
Get paid for your work
Outline your proposal
It's free to sign up and bid on jobs
87 freelancers are bidding on average $189 USD for this job
⭐⭐⭐⭐⭐ Create a Computer Vision Tool for Gaming with High Performance ❇️ Hi My Friend, hope you are doing well. I just checked all your project requirements and I can see you are looking for a computer vision tool for games. You have no need to look any further as Zohaib is here to help you! My team has completed over 50 similar projects for gaming tools. I will create a system that captures screens and processes images using the latest technology, ensuring high performance and low latency. ➡️ Why Me? I can easily build your computer vision tool as I have 5 years of experience in game development and computer vision. My expertise includes image processing, machine learning, and software development. I also have a strong grip on technologies like YOLO, Unity, and API integration. ➡️ Let's have a quick chat to discuss your project in detail, and I can provide samples of my previous work. Looking forward to discussing this with you! ➡️ Skills & Experience: ✅ Computer Vision ✅ Image Processing ✅ Machine Learning ✅ YOLO Framework ✅ Unity Development ✅ API Integration ✅ Video Capture ✅ Performance Optimization ✅ Modular Code Design ✅ Telemetry Logging ✅ Game Development ✅ Debugging Waiting for your response! Best Regards, Zohaib
$150 USD in 2 days
7.9
7.9
Hello, I trust you're doing well. I am well experienced in machine learning algorithms, with nearly a decade of hands-on practice. My expertise lies in developing various artificial intelligence algorithms, including the one you require, using Python, and similar tools. I have worked with pytorch, and tensorflow to develop DL models, .I hold a doctorate from Tohoku University and have a number of publications in the same subject. My portfolio, which showcases my past work, is available for your review. Your project piqued my interest, and I would be delighted to be part of it. Let's connect to discuss in detail. Warm regards. please check my portfolio link: https://www.freelancer.com/u/sajjadtaghvaeifr
$350 USD in 7 days
7.3
7.3
Hi, I’m Dev Singh, a Principal Software Engineer with 20+ years in computer vision and AI development. I have gone through your specific requirement for a game CV overlay. I would use a latest-frame-wins pipeline instead of queuing every frame, since stale detections can make a live overlay lag behind the game. I will build the Python CV processing layer around Helios GCVWorker and use YOLO for detection, with tracking and overlay rendering kept modular. And I’ll log frame age, inference time and dropped frames so performance issues can be traced across the capture path. I can send relevant project details and technical examples privately. Which games and capture paths are required for the first test, including PS5 Remote Play? Do you already have trained YOLO or Roboflow models, and what classes do they detect? Is the overlay strictly for visual feedback, or should it also send controller input? Free for a quick call? Or answer here and I’ll map out the first version. Dev Singh
$250 USD in 3 days
6.6
6.6
I have experience building computer-vision and AI systems using Python, YOLO, real-time video processing, object detection, tracking, and performance-focused pipelines. I can develop a modular CV pipeline with configurable game profiles, low-latency frame processing, ESP/radar visualization, telemetry, logging, and clean documentation. I’m comfortable working with capture pipelines and GPU-accelerated inference, and can structure the system so new game profiles and models can be added easily.
$140 USD in 7 days
5.6
5.6
The right first step is validating the Helios/CVPython frame path, inference latency and latest-frame processing before expanding to multiple games. I work with Python, OpenCV, YOLO, tracking pipelines and low-latency CV systems. I can inspect the supplied Helios runtime/module, build the detection/tracking/ESP/radar pipeline, add telemetry and configurable profiles, and benchmark capture/inference/frame age under real conditions. I’d suggest discussing scope first so we separate the CV/visualization layer from any automated input-control features and define a realistic first milestone.
$30 USD in 7 days
5.5
5.5
Dear Sir, I'm an expert in web design and development using Html, CSS, JavaScript, Angular, React js, JSP, Servlet, Java, Spring boot, Spring securities, Webflux, MySQL, MongoDB, Jira, bitbucket, GitHub, aws, docker, Jenkins, etc. My Technical skills are as follows:- Frontend: HTML, CSS, JavaScript, Angular, React js Backend: Node js, Core Java, J2EE (Advance java), Spring boot (Framework) Database: Mysql and MongoDB Web Application: Frontend: HTML, CSS, JavaScript, Angular, React js | Backend: Java (J2EE, Spring boot), Node js Mobile Application: Android (using Java), React Native (Android and IOS) Desktop Applications: Java (JavaFX, AWT, and SWING) Please ping me so we can discuss your project in more detail and can start immediately. Looking forward! Thanks & Regards
$4,000 USD in 7 days
6.6
6.6
Hello Sir, Would you like to see a demo of our advanced game analysis tool before making any commitments? Our solution leverages cutting-edge computer vision technology to enhance gameplay insight, offering precise tracking and real-time telemetry tailored to specific games like Fortnite and NBA 2K27. Let's discuss how we can make this tool a game-changer for your development needs, and I'll be happy to present a detailed plan along with the demo. Regards, Smith
$140 USD in 7 days
5.7
5.7
Hi there, The main challenge is building a low-latency, latest-frame computer-vision pipeline that keeps capture, inference, tracking, and overlay rendering synchronized across PC and PS5 streams. I have strong hands-on experience with Python, Deep Learning, CUDA, and Machine Learning (ML), and have solved similar problems involving real-time object detection, GPU inference optimization, and telemetry-driven pipelines. My approach would be to: * Review the existing Helios runtime, attached binary interfaces, architecture, logs, and current implementation. * Identify the root cause of latency, stale frames, detection jitter, or integration issues and determine what can be reused versus what needs to be changed. * Implement a clean, maintainable solution using Python, CUDA-accelerated inference, modular tracking, and configurable game profiles. * Test edge cases, reliability, performance, security, and integration behavior across capture rates, resolutions, model sizes, and supported hardware. * Deploy or integrate the fix without disrupting the existing system. A latest-frame-wins design with separate capture, inference, tracking, and GUI rates will prevent backlog; CUDA with FP16 can then be benchmarked against the real end-to-end latency budget. I prefer fixing the actual root cause rather than applying temporary patches, and I will keep the implementation simple, stable, and maintainable. I can start by reviewing the Helios executable, binary module behavior, reposit
$155 USD in 4 days
4.8
4.8
Hi, I have 10+ years of experience building low-latency full-stack systems with Python, automation, and real-time telemetry. You need a modular computer-vision pipeline with latest-frame processing, stable high-FPS overlays, YOLO/Roboflow inference, and runtime FOV smoothing with detailed logs. I’ve delivered similar CV/streaming tooling with clean, configurable code and dependable release packaging. Best, Razmik
$150 USD in 2 days
4.8
4.8
Hello sir, Did go through your job description and glad to share that I have enormous experience in I'm a seasoned programmer and Engineer with quality experience in Flutter, React, Node.JS, SpringBoot, Frontend and Backend Development, Python, Matlab, R studio, C, C++, C#, OpenCV, OpenGL, Tesseract OCR, google vision, Statisticaal programming/R progamming data analysis Computing for Data Analysis Time Series & Econometric, Machine learning, AI, Deep learning, Matlab and Mathematica, 3D modeling, CAD/CAM,AutoCAD, 2D, Architectural Engineering, SolidWorks, Unity 3D, AutoCAD, 2D drawing, 2D draftingPCB, Electronics, Arduino, Embedded Systems Automation, Embedded and Firmware , IOT, Electrical/Mechanical Engineering I am a TOP Rated Freelancer, and you can check my reviews here as well: https://www.freelancer.com/u/mzdesmag. Looking forward to potentially working together on this project. Thanks and Best regards, Adekunle.
$50 USD in 1 day
4.8
4.8
Hello, I’m a 9yrs+ Python/Computer Vision engineer experienced with low-latency video pipelines, YOLO/OpenCV, tracking, telemetry and modular desktop tooling. I can build a clean latest-frame architecture for Helios/CVPython: capture, inference, tracking and GUI rates decoupled, with FOV/confidence controls, game-profile configuration, ESP/Radar visualization, logs, performance metrics, update/licensing hooks and clear API/setup documentation. I’ll validate the real Remote Play/UnityCapture path and report FPS, frame age, dropped frames and end-to-end latency across supported hardware. Clarifying question: should the first release be strictly visual/telemetry-only, and which game, capture path and GPU are the priority for testing? I can start immediately.
$200 USD in 7 days
4.4
4.4
Hi there, I already have relevant experience with Python, OpenCV, YOLO, Roboflow-style inference workflows, real-time video processing, object tracking, GPU inference, overlays, telemetry, and modular desktop tooling. Your architecture makes sense, especially the separation between capture → latest-frame CV processing → detection/tracking → visualization/telemetry. I would avoid processing stale queued frames and use a latest-frame-wins pipeline so inference remains as close as possible to the live game state. My approach would start by stabilizing capture and benchmarking preprocessing/inference latency, then implementing detection filtering, confidence thresholds, player/head tracking, FOV logic, smoothing, radar/ESP visualization, and detailed performance metrics such as CV FPS, frame age, dropped frames, confidence, and target switching. I’d keep game profiles, model parameters, overlays, logging, and version/licensing components separated cleanly so additional games can be added without rewriting the core pipeline. I can also optimize CUDA/FP16 inference where supported and document the tradeoffs between resolution, ROI size, accuracy, and latency. The first milestone should focus on a stable visual-analysis and telemetry pipeline before expanding the supported profiles and features. Best regards, Harrison
$150 USD in 4 days
4.4
4.4
Hello, I checked your "Advanced Game Analysis Tool Development" project description, it looks like the focus is on delivering a clean, responsive website that works well across all devices. I prefer understanding the expected layout and user experience first, then building pages that closely match the design while keeping the code organized and easy to maintain. Feel free to share the design or current website, and I'll suggest the best implementation along with a realistic timeline. Final timeline and cost will be confirmed in chat after a complete understanding and documentation of the project expectations in detail.
$150 USD in 6 days
4.2
4.2
Hello, I’ve reviewed your request for a computer-vision-driven external tool for PC and console games, and I can deliver this efficiently. With extensive experience in computer vision, overlay development, and game integration, I will create a robust system that supports high-FPS overlays with minimal latency. I’ll ensure the implementation of features like runtime-adjustable FOV, detailed logs, and performance telemetry, while maintaining clean, modular code. I propose starting with a detailed review of your project requirements, followed by a structured development plan to ensure timely delivery while maintaining quality. The total cost for this project will be 200 USD. Thank you, Joseph.
$200 USD in 7 days
4.0
4.0
Hi, I understand you're developing a computer-vision-driven external tool for games like Fortnite and Rainbow Six Siege, focusing on screen capture and machine vision. This involves creating a modular overlay and managing networking/version checks with configurable game profiles. The main technical challenge here is ensuring low-latency processing for real-time game analysis while maintaining high accuracy in the computer vision pipeline. My approach would involve first optimizing the capture and processing stages to prioritize stability and performance. Given your requirement for modularity, I'll focus on creating a flexible architecture that can adapt to different game profiles seamlessly. I have extensive experience in Python and have worked on similar projects involving video capture and real-time data processing. My background in computer vision and game development will be directly relevant here. Q1 – What specific metrics or game events are you looking to analyze with the tool? Q2 – Can you clarify the expected interaction or feedback loop between the tool and the user during gameplay? Q3 – Are there any specific performance benchmarks or latency requirements you are targeting? Looking forward to hearing from you.
$30 USD in 7 days
4.2
4.2
Computer vision on Fortnite and NBA 2K means two very different pipelines, fast twitch detection for one, player and ball tracking for the other. I would start with YOLO for object detection and OpenCV for frame capture, then layer tracking logic on top. Can start today, working detector within 4 to 5 days. These numbers are based on the post as written. We will refine them after a quick scope conversation, since multi-game support usually changes the real timeline. Want me to send a quick plan for which game to prototype first?
$150 USD in 14 days
3.7
3.7
Nice to meet you , It is a pleasure to communicate with you. My name is Anthony Muñoz, I am the lead engineer for DSPro IT agency and I would like to offer you my professional services. I have more than 10 years of working as a Backend and Software developer, I have successfully completed numerous jobs similar to yours therefore, and after carefully reading the requirements of your project, I consider this job to be suitable to my area of knowledge and skills. I would love to work together to make this project a reality. I greatly appreciate the time provided and I remain pending for any questions or comments. Feel free to contact me. Greetings
$142 USD in 7 days
3.8
3.8
Hello, client — ⭐ I can build your advanced game-analysis tool by combining computer vision, video processing, and structured analytics to turn raw game footage into reliable, actionable data. ⭐ With 10+ years across Python, AI/ML, computer vision, APIs, data pipelines, and full-stack systems, I can design the vision pipeline to detect and track relevant players, objects, events, and game states while keeping results consistent and measurable. I’ll focus on the difficult parts—camera movement, occlusion, varying lighting, frame-rate differences, object identity tracking, event detection, and converting visual observations into structured statistics—then expose the results through a clean analysis interface/API. I’ll validate the pipeline against representative footage, measure detection/tracking accuracy, optimize processing performance, and deliver documented, maintainable code with a foundation for additional analytics. Best regards, Darial
$140 USD in 7 days
3.5
3.5
Hi, This strongly matches my Senior ML/Computer Vision Engineering background in real-time inference, YOLO, OpenCV, tracking, and production software. My ML work spans industrial, sensor, financial, medical, and vision domains, including object detection and tracking. I’d approach this as a complete low-latency pipeline: frame capture - preprocessing/ROI - YOLO inference - detection filtering - tracking/prediction - telemetry - ESP/radar visualization. Special attention will go to latest-frame processing, inference latency, stable IDs, confidence filtering, FOV logic, frame age, dropped frames, and GPU optimization. I’ll benchmark each layer rather than treating every issue as a model problem. My researcher’s approach emphasizes measurable accuracy, latency, failure-case analysis, and real-game testing. The architecture will remain modular for additional models and game profiles, with clean code, logs, documentation, and reproducible performance reports. I take strong ownership of responsible delivery and deadlines. Best, Gustavo
$150 USD in 4 days
3.7
3.7
Hi, I am a software engineer with over 16 years of experience building real-time computer-vision, video-processing, telemetry, and GPU-accelerated applications. I can develop a modular proof of concept around the Helios/CVPython frame pipeline, YOLO or Roboflow inference, latest-frame processing, stable tracking, configurable FOV and confidence controls, plus a low-latency ESP/radar visualization layer. I would begin by validating the actual capture path and workflow outputs, then profile capture, preprocessing, inference, tracking, and rendering independently. This will make bottlenecks and frame age visible rather than treating every issue as a model problem. The code will use clean configuration, structured logging, no embedded secrets, and documented interfaces for adding game profiles. I can also prepare the licensing/update hooks and a concise performance report using representative hardware. The posted budget is suitable for a focused MVP and architecture baseline; the complete multi-game, trained-model, licensing, and production release scope should be delivered in later milestones. My bid covers the first working phase, and I am flexible about defining its exact priorities. Please contact me to discuss details.
$250 USD in 14 days
3.1
3.1
Moosup, United States
Member since Sep 22, 2026
$2-8 USD / hour
$10-30 USD
₹100-400 INR / hour
$10-30 USD
$30-250 USD
₹750-1250 INR / hour
₹250000-500000 INR
$10-30 USD
$10-30 USD
₹600-1500 INR
$50 USD
₹600-1500 INR
$250-750 USD
₹12500-37500 INR
$10-30 USD
₹12500-37500 INR
£10-15 GBP / hour
$500 CAD
$250-750 USD
₹750-1250 INR / hour
$30-250 USD
Freelancer
About
Terms
Partners
Apps
