Human-like vision for machines
We are building the scorching-hot machine vision to let devices and digital media visually understand what humans like best and require most
Technology
Machine Vision SDK
  • Platform agnostic deep learning modules with own machine learning algorithms that scale down to low-cost single board computers
  • Real-time detection and recognition of objects and human actions on servers and devices
  • Framework-enabled combination of separately trained modules for complex decision making, e.g. real-time recognition of continuous actions and interpretation of situations
Training Tool
  • IoT machine vision
  • Transmission of vision skills to popular deep learning frameworks
  • Own tool for automated and faster training of calculation units (ML, neural networks, contour analysis) in modules
Solutions
Demo videos (3): real-time object recognition by Adventure Tourism and Security modules.
Modules are able to run on good budget graphics cards, can be tailored to customer-specified scenes and activities of interest
Fast algorithm
This Adventure Tourism module demonstrates the ability to detect and recognize:
  • barely visible and heavily obscured objects
  • the objects that visually merge together
Exact algorithm (2 videos)
This security module for surveillance cameras ensures high accuracy when it comes to detecting and recognizing perpetrators
Finding human contour
Source
Segmentation
Contour analysis with a capability to correct errors made by a neural network
Keep me posted about your progress
Scorch is one of the first companies focused on the visual recognition of complex actions and the development of human actions detection algorithms. Our modules run neural networks video processing in real time on both servers and devices. The modules are portable across different Operating Systems such as Linux, Android, iOS and GoPro Sdk.
Our big advantages are highly accurate real-time detection of human actions and our experienced computer vision team that is currently building the technology applying new AI concepts.
We believe that the computer vision for devices will change people’s lives dramatically, especially in that our machine vision will accelerate the advent of full-blown Augmented Reality smart glasses. We consider it a great honor to develop effective and innovative solutions in this area.