Customized deep learning solution

Outsource your machine-learning work

Using our MIND platform, we develop a solution for your problem. Then, we train your staff to maintain the solution and refit the underlying models if needed.

Businesses in the industrial, medical, and consumer service sectors use our products and services to automate the processes that, until recently, only humans were able to do, for example:

01

02

03

04

05

06

07

Checking the quality of products by visual inspection

Providing quality assurance in the food industry

Counting and classifying cells or chromosomes in biomedicine

Analyzing performance in the gaming industry

Measuring geometrical characteristics (position, size, profile, distance, angle)

Tracking objects in agriculture

Performing time series analyses in healthcare and sport

Machine Intelligence Designer

Deep learning platform for engineers

With our MInD platform, you can build end-to-end AI solutions in your business. It gives you all the necessary tools for the five stages of developing deep learning solutions:

• Data management: PostgreSQL databases store the relations of your data and the assigned annotations.
• Annotation: You can annotate the data on comfortable Graphical User Interfaces.
• Model optimization: Pre- and post-processing operations can be optimized together with neural networks that best fits your problem.
• Deployment: You can deploy models either to the cloud or to on-premise computers or even to edge devices.
• Maintenance: Easy integration with MES systems and detailed reports on model performance.

Annotation

We can speed up your data annotation process.

No AI solution can work without high-quality data annotation, i.e., without adding labels, masks, and numeric metadata to the training data. Annotation is often the bottleneck in an automation project because it may require 80% to 90% of the total human effort devoted to the project.

We do it differently.

After a small portion of the data has been manually annotated, the MIND Annotator learns to semi-automatically annotate the data. Next, the platform recommends annotations that humans can revise, and in this way, the pre-annotating function can be iteratively improved. The result is an annotation process that is 10 to 100 times faster than a manual process.

Consultancy

Both at the Engineering and the Business level

Engineering

At the core of our business is our experience with the practical applications of deep learning. In our consultation projects, we work closely with you to solve engineering and business problems.

01 –

We plan the automation process with you.

02 –

We help design the data collection.

03 –

We can either annotate the data for you or train your staff to annotate the data.

04 –

We train your engineers to deliver AI solutions and to maintain them on their own.

05 –

We take the responsibility of specifying all of your hardware needs, and we connect you with our partners who will install and maintain the hardware.

Business

We can also assess your business from a broader perspective. We help business managers and executives consider how you can employ AI across your company to expand your business. We help you to:

01 –

Identify jobs that can be automated.

02 –

Reengineer business processes to cut costs or speed up your services.

Synthetic Data Generation

We can generate photo-realistic data in Virtual Reality

Good deep learning models need thousands of samples to train on. In many applications, it can be difficult to collect a balanced training set, because some classes are represented by only a few samples. For instance, in applications used for industrial quality control some failure modes occur in the range of one in a million, making it almost impossible to collect a thousand samples from that failure mode. In other cases, the cost of collecting data is prohibitive. One example is reinforcement learning models in robotics: collecting samples for bad outcomes (i.e. cases in which the robot might break itself or something else) can be very costly.

One effective way to compensate for the lack of real data is to synthesize data in virtual reality simulations. We use Unreal Engine to generate photorealistic samples in a wide variety of scenes as viewed from various angles under different lighting conditions. We can generate 2D or 3D images or videos with visible surface depth maps and with occlusions that are correctly accounted for. Since the per-pixel ground truth data is readily available in the simulation, there is no need to spend time and money on the annotation.
Here is how it works: You send us the CAD design of the objects along with the skins and backgrounds that would be expected in the real application, and we generate annotated data for you. In the video below, boxes with various colors were randomly generated to train an object detection model used for a depalletizing application.https://www.youtube.com/watch?v=BlU_zwXGG3k

MI-Crowd

Real time crowd counting on security cameras

MI-Crowd is an out-of-the box software product for real-time crowd counting. It is recommended for counting crowds up to 200 people, i.e. it is an ideal solution for public transport, conference halls or other public spaces.

Advantages

It has numerous advantages over classic people counting systems placed above the entrances:

01 –

It can count the crowd based on a single image, thus the estimation error can be diversified away by evaluating multiple images. E.g. taking multiple images between two bus stops can increase the 94% single-image accuracy up to 98%.

02 –

It counts only the heads, so other objects (e.g. luggage, umbrella) that can mislead the classic counters are ignored.

03 –

It is ready to be used on any camera using arbitrary image resolution.

Technical information

The inference speed of the model using 640×480 image resolution were tested on two hardver configurations:

01 –

GPU (GTX1050): 160 ms, i.e. about 6 images per second

02 –

CPU (i5): 960 ms, i.e. 1 image per second