Aspinity, the leader in near-zero power AI solutions, announced the availability of a suite of new analogML™ algorithms for parked vehicle monitoring. Aspinity also launched a new dashcam-focused evaluation kit that enables the accurate detection and recording of security events for weeks or more without impacting the vehicle’s battery or requiring an external power source.
The number of sensors per car has grown rapidly as innovative automotive OEMs have implemented more real time monitoring applications for predictive and preventative maintenance, safety and security, infotainment, and more. While a vehicle’s power budget is stringent in any circumstance, always-on sensing is particularly challenging when the vehicle is parked since data collection and processing must happen without depleting the battery. The result to date is that always-on security solutions can either be highly accurate, or deliver an extended parking mode, but not at the same time. Aspinity’s innovative AML100 analog machine learning processor removes the power barrier so that vehicles can be continuously monitored for an extended period without having to worry about the vehicle’s battery.
Aspinity’s new automotive evaluation kit detects relevant events more accurately than today’s commonly used g-sensor based solution. At CES 2024 in Las Vegas, Aspinity demonstrated a side-by-side comparison of event detection accuracy using a dashcam with a standard g-sensor and a dashcam with a single microphone and an AML100. Aspinity’s solution uses an acoustic-only trigger with analogML algorithms that have been trained specifically to identify automotive security events, which vastly outperforms the g-sensor in detecting relevant vehicle events such as the jiggling of the door handle, a neighboring car door opening into the vehicle, and a runaway shopping cart hitting the side of the car.
The AML100 also specifically identifies particularly important security events, such as window glass breaking, so that the owner can be alerted immediately. Additionally, Aspinity’s machine learning algorithms ignore sounds from events unrelated to the vehicle that often trigger the g-sensor like a neighboring car alarm, a blaring horn, or a large truck driving by.
The dashcam evaluation kit uses Aspinity’s AML100-REF-1 wireless, battery-operated evaluation module that allows for rapid deployment and evaluation in the cabin of a vehicle. The solution consumes <50µA always-on and eliminates the video recording of false events that waste power and must be reviewed by the owner. Aspinity’s kit can be used as the front end of a third party dashcam or in-cabin OEM integrated solution that triggers a camera or sends alerts when a security event is detected.
Aspinity’s complete library of automotive surveillance algorithms leverages the sensor fusion capabilities of the AML100 by using combinations of analog input signals from acoustic, piezoelectric, radar, and other types of sensors. Sensors can be selected based on the specific monitoring application, sensitivity required, and whether the sensors will be located in the cabin of the vehicle or integrated within the vehicle’s panels.
SOURCE: Businesswire