Machine Learning and Video Analytics

Deep Learning and Machine Learning which use computing resources intensively, are at the forefront of engineering research. We offer a self-developed coprocessor acceleration card in the PCIe (half size) form factor, with a toolkit for neural network video analytics acceleration. Support for acceleration (inference) of the following neural network pre-trained models are available:

- Face, gender and age recognition

- The trajectory of pedestrian movement

- Detecting camera damage

- Classification – person, bicycle, car

- Car number identification and recognition

- Classification of vehicles (truck, passenger, etc.)

- Car color recognition (6 colors)

- Emotion Recognition

Big Data Analytics

Big Data analytics is a process used to extract meaningful insights such as hidden patterns, unknown correlations, market trends, and customer preferences. Big Data analytics provides various advantages—it can be used for risk management, product development, faster and better decision making, preventing fraudulent activities, among other things.

Big Data analytics is supported by our FPGA based acceleration card and BSP.