Recharge your business with the power of artificial intelligence and deep learning.
Our Work
Deep Learning Powered Intrusion Detection
We have designed an developed the AI/ML software stack for intrusion detection, for defense application. The hallmark of the solution is the application of computer vision and deep learning techniques to spatio-temporal signals of a completely different domain – fiber optics.
The system provides fibers, buried and or on fence, the ability to “hear” and detect intrusion. This allows for deployment for long distances along the border where camera installations could be problematic.
We have addressed challenges unique to the fiber optics domain – stringent requirements response time (< 10s) , accuracy (> 85) , false alarm rate , extremely high data velocity ( > 800 MBps ), noisy input, single box deployment
Â
- Application Area – fiber optics
- Industry Sector – defense, telecom
- AI Technology – deep learning, convolutional neural networks
- Customer – leading fiber optics manufacturer in India
Machine Learning for Telecom
We are applying machine learning techniques in a software product that aims to reduce the time and efforts of the NOC engineers in diagnosing faults in a telecom network. The software helps telecom operators to improve service assurance and helps the telecom service providers to reduce their operational costs.
- Application Area – telecom operation support system (OSS)
- Industry Sector – telecom
- AI Technology – gradient boosting
- Customer – leading telecom company in the world
Computer Vision for security of personnel
We are building a building a product for security of personnel in enterprises..
- Seamlessly localize and track people across multiple cameras.Â
- Re-identify people to distinguish between employees and strangers
- Detect entry of strangers into prohibited areas
- Detect security incidents like fights.
- Runs on embedded device which can be installed with no changes to existing CCTV infrastructure
- Data privacy as the system runs on-premise with no transfer of video feeds to the internet
- Application Area – security of employees in enterprises
- Industry Sector – all
- AI Technology – foundation models, contrastive representation learning, semi-supervised learning, Â
- Customer – a leading tyre manufacturing company
Computer Vision for worker safety
We are building AI powered application framework for worker safety
- Easily demarcate danger zones for monitoring.
- Alerts on entry into danger zones.
- Alerts on proximity to accident prone objects like forklifts, cranes.
- Detect safety norm violations like missing reflective vests or helmets.
- Live and history views for monitoring.
- Search and archival of safety related incidents.
- Application Area – safety of workers in factories, construction sites
- Industry Sector – all
- AI Technology – foundation models, monocular depth estimation, object detection and segmentation
- Customer – defense
Deep Learning for geospatial imagery
We work on building applications like ‘encroachment detection” from geo-spatial data using deep learning techniques.
We are also contributing to research work on systemic accident risk prediction for French cities. Unique aspect of this work is to encode multiple modalities in the geo-spatial domain into a computer vision based deep neural network. Â
Â
- Application Area – systemic accident risk prediction for town planners
- Industry Sector – manufacturing
- AI Technology – convolutional neural networks, GIS
- Customer – a multinational manufacturing giant
Customer Experiences
Shrirang Bapat
The product was delivered within a reasonable time. The Dataeaze team proved to be flexible when faced with challenges and project unknowns, coming up with solutions and new ideas. They reported on a weekly basis and used a transparent project management style.
Dr. Ambica Rajgopal
I had the pleasure of working with Dataeaze over the course of a year - their passion for AI, deep technical expertise and focus on execution helped us to build a complex deep learning solution from ideation to deployment in 8 months. They take full ownership of the pipeline and understand the complexities of production. Ajit is a mature leader of his team and this shows in their ability to retain world-class talent.
Dr. Badri Gomatam
Emergent technologies in fiber optics have brought in a new set of engineering problems that demand for artificial intelligence/machine learning approaches. Dataeaze helped us to tap the power of computer vision and deep learning techniques for the modeling of one such engineering problem. Following a rigorous data science and engineering discipline, they built a software stack for us. It was a complete ''software 2.0'' lifecycle execution, from ideas in the research lab to the code deployable in production. I wish them success and hope to work with them again in the future.