Innovation │ Technology │ Entrepreneurship
Hardware restrictions are one of the greatest influencing factors on the performance of artificial intelligence on the edge. To leverage the possibilities of AI for traffic detection, it is crucial to optimize the neural network architecture. At NovelSense we are using neural networks (NN) for the identification and classification of vehicles and other traffic participants. …
NovelSense is part of one of Europes biggest funding projects to improve air quality. The DEUS Smart Air project aims to develop a sensor grid which enables cities and municipalities to monitor air pollution and traffic flow to actively improve air quality. The sensor grid is made up of mobile and stationary sensors which cover …
Traditionally, the performance of AI models for “real-time” object detection is directly linked to the computing power and storage capacity of the hardware used to run the model. This factor heavily limits the application possibilities of Neural Networks on the edge of the IoT cloud. At the same time, embedding a Neural Network into an …
NovelSense is developing a battery powered and camera based traffic counter under the ABAKUS brand. The small build-size and low-power design increases the flexibility of the sensor and makes it ideal for temporary installations. Currently the ABAKUS is optimized for the recognition of bicycles. This makes it the perfect tool for cities or traffic planners …
Developing the future of mobility does require thinking about different modes of sustainable transportation. For urban mobility this implies bicycles. Bicycle usage in Germany has seen a significant increase during the 2000s and 2010s. This is partly also due to the development and widespread adaptation of pedelecs and electric bikes. Many cities are looking to …
Project “VideoSmart” is a mFUND project run by LAT Funkanlagen-Service GmbH in Berlin. It aims to utilize existing 360 degree security cameras in Berlins subways to optimize the passenger flow at the stations. Therefore the cameras are used to recognize the amount of passengers in each wagon. The information is transfered to LED signals on …
“ParkCheck” aims to develop an innovative traffic sensor. It should be used to count vehicles and applied to enable parking space detection in cities. The project was developed in cooperation with Nuremberg based startup Smart City System and funded by the Federal Ministry of Transport and Digital Infrastructure (BMVI) in Berlin. The new sensor is …