Computer Vision Jobs

3D LiDAR Point Cloud Bounding Box Annotation (Object Detection) Project Description: Overview: We are looking for experienced data annotators to perform high-quality 3D LiDAR bounding box labeling (cuboid annotation) on point cloud datasets for autonomous driving/robotics perception models. Scope of Work: Annotate Objects: Draw tight, precise 3D bounding boxes (cuboids) around target objects in point cloud scenes. Classes to Label: Vehicles (cars, trucks, buses), Pedestrians, Cyclists, and Miscellaneous obstacles. Orientation & Heading: Correctly align the orientation vector (yaw/heading direction) of each bounding box. Temporal Tracking (Interpolation): Track objects across sequential frames, ensuring consistent object IDs and smooth transitions. Strict Quality Control: Adhere...

We are seeking an experienced Computer Vision or Technical Image Sourcing vendor to source, curate, and legally license a large-scale, high-quality, and diverse collection of 50,000 technical images. This dataset will be used for AI model training, evaluation, benchmarking, and dense captioning use cases. The project requires a strict distribution of 5,000 images per domain across the following 10 domains: 1. General Science (Microscopy, lab experiments, molecular diagrams, charts, etc.) 2. Maps & Technical Diagrams (Transit maps, floor plans, network/process flowcharts, etc.) 3. Geospatial / Satellite (Satellite/drone imagery, GIS visualizations, topographic maps, etc.) 4. Agriculture (Crop diseases, plant growth stages, farm machinery, irrigation, etc.) 5. Robotics (Robotic arms, w...

I need an end-to-end AI solution that lets a runway-patrol drone spot even the tiniest foreign object debris (FOD) in real time. The airframe already carries LiDAR, an infrared sensor and an electro-optical (EO) camera; what is missing is the software that fuses those feeds, classifies debris and reports exact GPS position so ground crews can clear it fast. Scope of detection • Metallic pieces, plastic fragments and loose stones—down to roughly 1 mm in size. • Operation must be reliable in both daylight and nighttime conditions. • Accuracy target is set to a high threshold; false positives have to stay low while recall stays near perfect. Key tasks 1. Build or adapt a multi-sensor fusion pipeline that consumes LiDAR point clouds, IR imagery and EO frames. 2...

I need an AI video analytics software that specializes in face detection, person detection, and object detection. Key functionalities required: - **Face Detection:** - Identifying individual faces - Counting number of faces - Emotional analysis - **Person Detection** - **Object Detection** Ideal Skills and Experience: - Proficiency in AI and machine learning - Experience with video analytics and computer vision - Strong programming skills (Python, TensorFlow, OpenCV) - Knowledge in emotion recognition technologies Please provide a portfolio showcasing similar projects.

Please read the following instructions carefully before starting. 1. Sample Images The client has provided 10 sample images. Since all of the samples follow the same annotation standard, I have divided them among the team to save time. Your assigned sample image should be treated as the reference while annotating your assigned batch. 2. Requirements - Draw Polygon annotations for all required objects visible in the image. - Apply Key Segmentation only for Broad Leaf and Weed, exactly as demonstrated in the sample images. - Do not use any different annotation style. Follow the sample as closely as possible. 3. Annotation Quality - Polygon boundaries must be tight and accurate. - Do not include unnecessary background. - Cover the complete visible area of each object. - If multiple obj...

I have mapped out a consumer-facing AI platform that blends natural conversation, real-time insights, and intelligent automation into a single web & mobile experience. The roadmap is clear, the market niche is validated, and I’m now ready to turn the concept into an MVP and beyond alongside a technical cofounder who brings deep expertise in AI. Core vision The product centres on three pillars: seamless user interaction and support through robust NLP, data analysis with intuitive visualisation, and automated decision-making that genuinely helps everyday users, not just enterprises. Under the hood we will combine Natural Language Processing, Computer Vision where it adds tangible value (e.g. image-based recommendations), and classic plus deep Machine Learning models to personalise...

We are looking for freelancers to contribute to a large and diverse facial image dataset that will support machine learning research and facial recognition model training. The project focuses on collecting high-quality facial images that represent real-world variations in identity, head poses, appearance, and age progression. Each freelancer will complete four image collection tasks, including front-facing neutral captures, controlled head-pose images, and historical facial images showing natural changes over time. Freelancers are required to submit up to 28 approved images, with a minimum of 11 valid images needed for an approved and billable submission. Images must be authentic, high quality, and reflect natural variations in clothing, hairstyle, lighting, background, facial angles, and...

I have already prepared the full CoppeliaSim scene (.ttt) with the mobile platform, vision sensor and the coloured paths laid out. What I still need is the Python side: a clean, well-commented script that connects through the CoppeliaSim remote API, reads the vision stream, identifies the target colours and drives the robot along each line using a PID controller. Primary task The robot’s job is straightforward line following. Because the scene contains several coloured tracks, it must be able to hop from one to another whenever the target colour changes, staying centred on whichever line it is tracking. Colours to detect • red • green

I need help configuring a Hikrobot camera using python whenever it flags a vehicle incorrectly, drives an external alarm output. In practice that means: • Monitoring the confidence/result coming from the camera (SDK, ONVIF events or RTSP overlay—whatever is most reliable) and deciding when a detection should be considered “wrong”. • As soon as a wrong detection is confirmed, toggling the camera’s I/O port (or a small companion relay module if the onboard I/O proves too limited) to fire the alarm signal. A concise set-up guide and any scripts, firmware tweaks or parameter files you create must be supplied so I can replicate the installation on additional units. Please include short test footage or logs proving that the alarm is triggered only on false...

I have a mobile robot prototype and I need an AI agent that will let it perceive its surroundings, decide on actions, and execute them safely in real time. Because the hardware stack is still flexible, I am open to ROS, a custom embedded setup, or a commercial SDK—whatever you feel will achieve the best balance between performance and maintainability. At a minimum the agent must: • Fuse camera and sensor data to detect obstacles and points of interest. • Plan a collision-free path and update it on the fly. • Expose a clean API so I can add higher-level skills later (object pickup, voice interaction, etc.). Please structure the code in well-documented modules, supply build instructions, and include a short demo video that shows the robot handling a simple naviga...

Project Details Project Title: Wanted: STEM Experts for 20 Original Advanced Problems (Robotics, CV, RL, STEM) Project Description: We are seeking highly skilled researchers, algorithm engineers, and mathematicians to author 20 highly complex, completely original STEM problems. These problems will be used to evaluate the reasoning capabilities of frontier AI models, so they need to be genuinely difficult. The Deliverables (Format depends on your domain): You will deliver 20 original problem tasks. The required format varies based on the subject: For General STEM (Mathematics, Physics): Deliver a clean LaTeX file containing one original, self-contained problem, the uniquely determined correct final answer, and a step-by-step rigorous proof/worked solution. For Computer Science Domains (...

I need a small Windows-only desktop tool that sits quietly in the background, keeps an eye on a two application window, and reads any numbers or short text that appear there. Each time fresh data is detected, the script should run a mathematical calculation that I will supply (simple formula, nothing exotic). The moment the result meets my condition, I want to know right away through both a pop-up notification and a short sound. Technology-wise, I am already comfortable working with Python, so please build it in Python using screen-capture libraries such as MSS, OpenCV for basic computer-vision handling, and either PaddleOCR or Tesseract for the text recognition. The solution must continue monitoring for as long as the program is open; no browser automation or auto-clicking is involved&md...

Project Title: AI based – Production Grade Smart Forest Monitoring System We are looking for an experienced Full Stack AI developer/team to build a production-grade AI platform for real-time forest monitoring and wildlife protection. The solution will use Edge AI devices, AI-enabled Swarm Drones, and environmental sensors to detect wild animals, humans, fire, and smoke, collect real-time environmental data, and securely transmit it to AWS Cloud. A Flutter mobile application will provide live monitoring, intelligent alerts, GIS mapping, analytics, drone management, and remote device management. The system should be scalable, secure, modular, and support OTA updates for both edge devices and drones. Tech Stack - Edge AI: Raspberry Pi 4 / Industrial Edge Computer, Python, OpenCV, ONNX...

I need a small, accurate program that accepts two medium-resolution JPEG photographs of a finished metal assembly and automatically presents them side-by-side, with every visual difference clearly highlighted on the right-hand image. The purpose is simple: help our fabrication team spot mis-welds, missing brackets, or other subtle manufacturing deviations without having to inspect the parts manually. Here is what matters most to me: 1. The tool must read standard JPEGs shot between 720p and 1080p—you can assume consistent lighting but plenty of reflections and shiny edges typical of stainless steel. 2. Output should be a single composite image (or screen) that shows both originals next to each other; regions that differ are accented visually so a technician can locate them in second...