PENSAR CAMERA & SDK Develop and run your AI applications
Need to develop AI application and process real time data?
Create your own AI apps from concept to deployment within few days with the AI powered Pensar camera and SDK.
Pensar is the fastest, most power-efficient embedded AI computing device: NVIDIA Jetson TX2.
Pensar is a AI powered camera dedicated for professionals and integrates a Sony 30x zoom HD camera, an IR Flir Boson and a Nvidia Jetson TX2 GPU.
WHAT IS PENSAR SDK?
Pensar SDK is an end-to-end solution for AI application development which includes a Pensar Camera, an API, a dashboard and a SDK.
Develop on PC and deploy on Pensar camera
Application and GUI development based on Python on top of C++ hardware accelerated libraries.
Use the available pre-trained neural networks or import neural network in most common frameworks caffe, darknet and soon tensorrt)
Requirements for developers
‣ Programming languages: Python 3, C++ ‣ OS: Linux based operating system (Ubuntu, Mint…)
ADVANTAGES
Edge computing (no cloud dependency)
Real-time processing: no cloud latency
Reduce development costs
Simpler and faster developing time
Versatility – Cross sector applications
Modular SDK
Low power consumption
CROSS-INDUSTRY ARTIFICIAL INTELLIGENCE
AI APPLICATION EXAMPLES
Facial recognition
Multiple faces detection and recognition
Multiple faces annotations
Detected faces can be saved to a permanent database
An external faces database can be loaded for recognition
Faces to be detected can be sent to Pensar from an external device (i.e. mobile phone)
Object detection
80+ objects supported (person, animals, means of transportations, objects of common use, food, plants, etc.)
Several kinds of Neural Networks available, with different level of performances
Specific actions can be programmed when selected objects are detected (i.e. take a geotagged picture, etc.)
Car license plate recognition
Uses a combination of two neural networks, the first one to detect cars (other vehicles can be added in future) and the second one to detect and recognize car registration plates
Optical character recognition is used to extract license number plate. Performances of recognition depend on optimizations specific for each country
Optical Tracking
Any image area can be chosen and tracked on-demand by the user
Different tracking algorithms can be used in order to get best results on given scenario
Gimbal (if present) is controlled by Pensar to perform physical tracking
Supports both optical and thermal camera
AI Powered Object Tracking
AI is used to automatically detect objects to track (person, car, train, …)
User can choose which object to track amongst detected ones
Gimbal (if present) is controlled by Pensar to perform physical tracking
30x optical zoom is used to track objects on z axis. Object size is automatically kept constant on screen. Maximum tracking distance up to 200 meters (it depends on object type and size)
Limited support for thermal camera but specific neural network can be trained and added in the future
Thermal detection
Object detection based on thermal imaging
(see “Optical detection” above)
Thermal tracking
Tracking based on thermal imaging
(see “Object detection” above)
Do you need help? Do you have any questions?Ask a question and we'll respond promptly, publishing the most interesting questions and answers for others.