Today we talk about teams that went through . There will be two of them in this habrapost. The first is the startup Labra, which is developing a solution for monitoring labor productivity. Second - with a face recognition system for turnstiles.
Photo: /unsplash.com
How Labra will increase productivity
Productivity growth in Western markets has slowed. By McKinsey, at the beginning of the 2,4s this figure was 2010%. But between 2014 and 0,5 it fell to 2%. Analysts note that the situation has not changed since then. But there is an opinion that artificial intelligence systems will help solve the problem. With the help of AI systems, productivity growth is expected to return to XNUMX% within ten years. Smart algorithms will help automate routine tasks and optimize work processes.
Research in these areas is already being carried out by specialists from , engineers and even representatives . Machine vision will play an important role in increasing productivity growth. The technology is used to independently assess the workplace and employee performance. Such solutions are already being implemented by Western companies - for example, ΠΈ .
Russian companies are also developing solutions for assessing labor productivity. For example, the startup Labra, which went through our . Engineers are making a video surveillance system with a neural network that recognizes the actions of enterprise employees and makes it clear exactly how they spend their working time.
How the system works. Labra can operate in any enterprise with machine or machine-manual labor whose staff exceeds 15 people. With the help of cameras, she forms the so-called - that is, it records everything that happens during the shift. In general terms, the algorithm looks like this:
- The system captures the image and marks the work operations;
- A machine learning algorithm analyzes the video;
- The algorithm then generates a photo of the working day;
- Next, the analytics are automatically calculated;
- Labra generates a final report with recommendations that will increase security in the enterprise and optimize its resources.
Who is on the team? The startup has a staff of eight people: the manager and founder, two developers, three labor standards specialists. There is also a customer service manager and an accountant. Some of them combine project work with university studies. Therefore, everyone monitors the completion of tasks and deadlines independently. However, the team holds meetups twice a week to discuss progress and plans for development.
Perspectives. At the beginning of September, the startup presented its project . There, engineers demonstrated the product's capabilities. Labra plans to further promote the solution and is working on the prospect of cooperation with enterprises in the country.
O.VISION will help you get rid of keys and passes
In 2017, MIT Technology Review facial recognition in the top 10 breakthrough technologies. This decision was partly due to the wide applicability of such systems. In particular, they can replace the usual keys and passes when entering a building - for example, a number of Russian banks have already implemented similar developments. New players are also appearing on the market, for example, a startup is developing a similar solution . The team is making a contactless access system for turnstiles that can be installed in 30 minutes.
How the system works. The development is a software and hardware complex installed at the checkpoint. It is based on five neural networks that process individual frames from the camera of the biometric system. The authors say processing a single image takes less than 200 milliseconds (about five frames per second). The team writes all recognition algorithms and interfaces independentlyβthe developers do not use proprietary solutions. Train neural networks using .
Data processing occurs locally. This approach increases the security of personal biometric data. The hardware includes the Jetson TX1 board from Nvidia, which is designed for standalone devices. The biometric system also contains an integrated circuit of its own design for controlling turnstiles and integrating with .
Photo: /unsplash.com
Startup employees. The head of the company says that the selection was carried out according to the principle: 60 candidates for one place. This format allowed us to recruit the most talented people. Currently, several programmers are working on the project, responsible for machine learning algorithms and code for embedded systems. There is also a backend developer, an information security specialist and a designer. Some of the employees are students who combine work with a master's degree.
Perspectives. Today's solutions installed at the largest coffee factory in Europe. The product is also being prepared for launch in one of the St. Petersburg fitness centers and the Polytechnic University. Perhaps in the future O.VISION will be installed at ITMO University. The head of the company says that they are already negotiating with Russian corporations: Gazprom Neft, Beeline, Rostelecom and Russian Railways. In the future, we will enter foreign markets.
About other accelerator projects:
Materials about the work of ITMO University:
Source: habr.com