Computer Vision Jobs

More details: What type of clothing items will be featured in the virtual trial room? It will cover the complete fashion industry like shirts, pants, skirts etc Do you have specific software requirements for the virtual trial room? No, I am open to suggestions What level of customization do you require for the virtual trial room? Advanced customization (3D modeling, animation)

Create a Key Point Detection Model

Implement Rain removal on a image using python

Video Surveillance System using Computer Vision I am looking for a freelancer who can help me develop a video surveillance system with computer vision capabilities. The main purpose of the system is for security monitoring. The system will use both IP and CCTV cameras to capture footage. I need Video Stream Pipeplining and Parellel Processing for handling 40 cameras in single system without latency . Ideal skills and experience for this job include: - Expertise in computer vision and video analytics - Experience working with IP and CCTV cameras - Video Streaming Pipeline - Data Pipeline and Handling RTSP streams If you have experience in these areas and are interested in working on this project, please submit your proposal with relevant examples of your work.

I have .pth file. You need to convert to .onnx and then to .trt file

Perform Object Detection Inference with Pretrained YOLOv8 Model - Purpose: Object Detection - Preferred Pretrained Model: YOLO - Expected Output Format: Class labels with confidence levels for each predicted level - Language: Python 3.10 The YOLOv8 object detection model is stored as an ONNX model in a GCP storage bucket. The model needs to be loaded, an image needs to be preprocessed, and the object detection inference needs to be performed with the expected output format. Ideal Skills and Experience: - Experience with object detection and computer vision - Familiarity with YOLOv8 framework and pretrained models - Proficiency in Python

I am looking for a freelancer who can help me with a deep learning based vehicle inspection project. Here are the details: Vehicle Type: - The inspection will be for cars. Inspection Focus: - The focus of the inspection will be on the exterior appearance of the cars. Primary Purpose: - The primary purpose of the inspection will be damage assessment. Ideal Skills and Experience: - Experience with deep learning algorithms and computer vision. - Knowledge of image recognition and object detection. - Experience with machine learning frameworks - Familiarity with automotive industry and vehicle inspection standards.

We have live feed from IP Cameras running on our servers - 1000s of IP Cameras running on single server with 64 IP Cameras (at max) - on single screen (via iframe) and each IP Camera feed running on unique URL. We want to detect human in the live feed. Live feed runs for 24hrs but our hours of importance is only an 8hr shift where we want the app/program to alert us whenever a human is detected in the region of interest. The region of interest will change for each camera and must be customizable via some gui (basic). Whenever a human is detected in region of interest, the program should highlight which camera the human is detected in. Kindly answer, whether you will run an AI program on each unique url (each having 1 camera feed) or on 1 collective page (each having 40/64 iframes of liv...

I am looking for a freelancer who can create an intelligent OCR system for Urdu language. Although I do not have a specific OCR software in mind, I do have a preference. Freelancers who apply for this project should submit detailed project proposals that include their past work and experience. The expected accuracy rate of the OCR system should be between 90-98%. The ideal candidate should have experience in developing OCR systems for complex languages and a strong background in artificial intelligence and machine learning.

We are seeking a skilled and innovative AI App Developer to join our team. As an AI App Developer, you will play a crucial role in developing an exciting AI-powered application that generates art based on room images' color and material schemes. Successful Candidate will guaranteed get a 5 stars rating! Responsibilities: • Collaborate with the development team to design and implement an AI-powered app for art generation. • Utilize ChatGPT and other AI models to assist in the creation of an interactive and intuitive user experience. • Work on the image processing component, extracting color and material information from room images. • Research and implement cutting-edge computer vision techniques for accurate color and material detection. • Integrate the AI mo...

Necesitamos crear un modelo que permitan detectar/ identificar elementos de un sitio web y que los clasifique en 3 categorías (Botones, Banners y formularios). De este modo a cada elemento detectado se debería asignarle 3 etiquetas: el texto del elemento, el tipo de elemento y la ubicación del elemento. Para ello debería ideal es habilitar un espacio web donde subir las imágenes y recibir un documento en formato JSON con el etiquetado resultante, la ubicación del elemento y el recorte de este. El output del modelo debe ser las imágenes con el elemento identificado en un repositorio y adicionalmente una base de datos donde se tengan los links de las imágenes y los parámetros que se identificaron en el modelo.