Computer Vision | Deep Neural Network | Depth Sensors | Sensor Fusion | Point Cloud and Mesh
We deliver computer vision, deep neural network and depth sensors integration projects in the field of robotics, transportation, telecommunication, education, construction, and entertainment.
Our developers and researchers have PhD or Master in Computer Science and 10+ years of experience specialising Computer Vision, Deep Neural Networks, C/C++, OpenCV, Matlab, PCL, Cloud Computing, Linux and Windows platforms.
Some of the projects we have delivered:
Low Bandwidth Broadcasting Protocol for Video on Demand
In some cases data storage might be inefficient and video data might heavily load internal network. Extension of Video on Demand (VoD) module optimises data transfer between the CCTV video recording system and land side/station. The server part of the VoD was redesigned to extract a single camera data from all cameras data storage and transfer to the review station only a minimum required data amount reducing the train network load significantly.
Area access based on real-time facial recognition
The project included: Object classification: classification based on the size and the movement speed of objects. Restricted areas control: The algorithm can detect and report if people or objects enter, leave or stay in restricted areas. Tolerance to weather conditions: The algorithm ignores rain and snow, as well as trees and bushes, which are swayed by wind Multiple face detection: Features extraction and template matching with the internal database in real time. Face tracking: Performed in all successive frames from the video source within the camera field of view.
Multispectral identification of invisible gas fires
The use of multiple filters allows the camera to simultaneously identify, quantify, and display the type and amount of gas within a family by separating the radiation at the reference and active wavelengths from the broad thermal radiation emitted by the infrared source or background. A live-feed of images from Multispectral camera is fed into the Video processing unit which then segregates the results from the camera providing the viewer a clear identification of the source of threat.
Point Cloud based Autonomous Robot Remote Assistance system
The system consist of Volumetric Video system monitoring premises and enabling perceptual human-computer interface to control a mobile robot capable of autonomous navigation and mission based delivery. EF EVE web platform is facilitating the management and distribution of created volumetric content between doctors and operators of autonomous vehicle system and on-site VV capture.
Market leading 3D depth codec
The EF EVE™ team has developed market leading proprietary EF EVE™ Depth Codec that solves main industry problems: compression, recording and live-streaming of Volumetric Video. It has distinctively higher compression and faster algorithm than most of lossless and lossy compression solutions on the market. It has been applied in many industry cases where live 3D data streaming is needed.
Companies which are using our services and product
Start typing to see search results
Try "photogammery", "diorama", or "dinosaur", for some cool results.