Linkedin Twitter
Project name:

Video analysis and real-time media identification platform

Status: Idea
Creation date: 09-01-2023

Project objectives:

Short summary An IT Spanish SME has developed an advanced video & image analytics platform to infuse video analytics without human intervention. It is based on machine learning & artificial neural networks and can combine several recognitions capabilities: faces, emotions, scenes, people, objects, texts and activities. This tool can be implemented stand-alone or seamlessly integrated into new or existing tech. They are seeking IT integrators or final users for commercial agreements with technical assistance.

Full description Territorial control and security are an international concern. National governments and local authorities are reviewing their security and control systems for: * Borders, cities, roadas, places and centres of public use. * People´s identification, new instruments to support health and educational systems. Even the private sector is demanding new services related to: * Staff identification. * Surveillance and security of sensitive installations and infrastructures. * Monitoring and attendance at workplaces, surveillance of processes and products. * Advanced automation tools. * Customer profiling. * Marketing tools and big data. An IT Spanish SME has developed a video and image analytics platform to infuse video analytics into everything. This tool is an advanced solution for image processing algorithms with pattern recognition based on machine learning and artificial neural networks. It allows video and photo images to be analysed without human intervention. It combines recognition capabilities: Faces, emotions, scenes, people, objects, texts and activities. This accurate and scalable tool can use images from a wide range of sources: * Live video or recorded. * Video/photo from the internet. * Closed-circuit television (CCTV) * Vehicle mounted cameras. * RPAs (Remotely Piloted Aircraft System). * Satellite/aerial imagery. * Handheld cameras. * Smartphones. According to this, it can be used in a variety of applications and environments of security and marketing for everyday tasks that can be automated, authenticated and enhanced. (see attached image about markets) It generates real-time alerts to take appropiate action quickly. This unique recognition algorithms provide a range of aids to improve the accesibility and quality of service and offer a real advantage in terms of efficiency and cost reduction. Customers can use the platform through the web interface or the mobile app with a user-friendly interface that includes analytical pre-settings, actions (such as chatbot and SMS alerts) and periodic reports of the various analytics performed. This recognition technology can be implemented stand-alone or seamlessly integrated into new or existing solutions. The API easily integrates biometrics recognition objects and analytics with existing IT systems. It doesn´t depend on specific brands of cameras or surveillance systems. The Spanish SME developer of this technology is looking for IT integrators (to implement this technology in their areas) or final users. This cooperation would be carried out via commercial agreements with technical assistance.

Advantages and innovations a) State-of-the-Art Algorithms RTMIP (Real-Time Media Identification Platform) uses the bunch of neural networks, trained on more than 10 billions of unique images. Its high accuracy is confirmed by independent tests and contests. Moreover, they pay great attention to the performance of their algorithms without compromising the accuracy, sharpening the neural network for a specific task, which allows to be ahead of the competition. b) Highest Accuracy Unique face recognition neural network operates with an error rate as low as 1 in 1,000,000. With a test dataset of 10.000 unique people, its identification accuracy rate is up to 99.7% and its biometrics verification accuracy rate is up to 99.9%, which means the system can be used for every face recognition task. c) Highest Speed Networks runs up to 100 times faster than competitive neural networks without losing accuracy. They pay attention to constantly upgrade of networks to run even faster. d) Fastest Large Scale Search Face recognition algorithm handles millions of different faces. The RTMIP unique proprietary index engine is able search through billions of photos in less than a 0.1 sec. Face detection takes from 200 ns. Extraction of biometric personal characteristics takes about 500 nanos. e) On Your Hardware This software runs with all data stored on servers to give your business absolute peace of mind. With cross-platform REST API on board and stack of native APIs, the RTMIP server can be easily integrated in any web, standalone mobile, or desktop application in a prompt and unified manner.
Contact / source: NEXT EEN Widgets (