Thermal Human Detector uses proprietary synthetic tech for better performance in crowds, indoor/outdoor and low visibility. Effective in groups, busy areas and crowds.
Optimized for edge performance with a low power profile.
Ground-to-ground.
Dawn to dusk and artificial lighting.
Environmentally-agnostic performance.
Backbone: Resnet-101; Detector: RefineDet.
Detection.
512x512.
Thermal.
Reliably detect humans in low visibility conditions with thermal imaging.
Use the Thermal Human Detector as a part of a larger security framework. Enhance your existing security grid and ensure your system is ready for anything with a model trained to detect an extensive variety of situations.
Add to existing perimeter security measures with a model built to detect humans in the night and in low visibility conditions. The Thermal Human Detector has been tailored to reduce false positive in typical conditions through CVEDIA’s pioneering use of synthetic data.
Ensure your driver safety system is prepared with this algorithm, which is highly effective in crowds and busy areas so you can be sure that your ADAS / AD system is state-of-the-art and safe for both drivers and pedestrians, especially at nighttime and in low visibility.
Ensure peace of mind in public spaces and events with fewer resources using the Thermal Human Detector. Our models help you surpass the data collection and training phases of your project, so that you can get to market quicker.
We offer maintenance services for our AI models and provide the option to add fine grain classification or additional classes through our in-house team. Our models are built with proprietary synthetic data technology, allowing for quick integration of new classes.
Each CVEDIA model comes backed with an ongoing maintenance agreement. Our team is available for continuous improvements and to ensure upkeep.
Discuss fine grain classification with our team and get an answer today. We'll work with you to build a synthetic-based model to meet your specifications.
Our models are built using proprietary synthetic data technology, meaning adding additional classes to your model is possible in a matter of weeks.