Sound event detector
SED (Sound Event Detector) is a solution that uses a proprietary algorithm driven by machine learning technology to detect, classify and subsequently alert on unwanted acoustic events. These events can be a gunshot, a scream, or high urban noise levels.
The SED has exceptional accuracy that provides the confidence to address threats quickly and avoid wasting resources on false alarms. In addition, this solution enables sound detection to operate on devices with low-power, low-cost processors.
Every second matters
Step 0: Adaptation
The SED analyzes the common background sounds from the environment in which it is located and adapts.
Step 1: Detection
The SED detects an unwanted sound event that is atypical in the environment.
Step 2: Extraction
The SED processes the input audio signal and extracts the audio features used to train the classifier.
Step 3: Classification
The SED triggers an alarm if the event is evaluated as undesirable.
Step 4: Result
The SED triggers an alarm if the event is evaluated as undesirable.
Step 5: Notification
The SED informs the user about the event, and help can be on the way immediately.
Immediate response saves lives.
The average processing time of a human reaction when evaluating a dangerous situation is around 7 minutes. The SED processing time is 2 seconds. This time can be crucial.
Software solution
SED’s SW solution is powered by state-of-the-art machine learning techniques with optimized deep neural network architectures running on low-power MCUs in real-time.
The software has been developed with an emphasis on speed and efficiency and allows third parties to easily adapt it to their embedded (low power) hardware platforms. The solution comes with a very intuitive user application, and both products can be customized to suit your needs.
It’s not a problem if you don’t want integration into your product; we also have our own devices ready for immediate order!
Hardware solution
Software solution
SED’s SW solution is powered by state-of-the-art machine learning techniques with optimized deep neural network architectures running on low-power MCUs in real-time.
The software has been developed with an emphasis on speed and efficiency and allows third parties to easily adapt it to their embedded (low power) hardware platforms. The solution comes with a very intuitive user application, and both products can be customized to suit your needs.
It’s not a problem if you don’t want integration into your product; we also have our own devices ready for immediate order!
Outdoor solution
- Operating temperature range: -40°C to +60°C
- Durable polycarbonate enclosure IP 67 certified
- An integrated GSM or UTP network ensures operability anywhere where the network is available and requires minimum data
- Highly customizable (white label)
- Possible to install in remote locations, with GSM and battery version (per request)
- The device comes with an outdoor installation kit
Indoor solution
- Install in minutes since the device is prepared for wall mounting
- Operating temperature range: -40°C to +60°C
- Durable polycarbonate enclosure IP 67 certified
- UTP network that requires minimum data
- Minimal maintenance
Just adds another sense to the cameras – an ear.
Hardware for remote locations
Battery powered version – works up to
30h from the battery, charges automatically
when power is restored.
Solar powered version – powered from
10w solar panel and battery
Low device consumption ~ 1w.