We’ve seen WiFi security cameras promising a year of battery life before with products like the Eufy EverCam, but the Ingenic T31 Smart video Innophase’s App Development Kit can enable the development of even more power-efficient WiFi AI security cameras with AI processing that can last for more than a year.
The development kit combines the Ingenic T31 MIPS and RISC-V camera SoC with the Innophase Talaria TWO INP101x (57µA @ DTIM10) ultra-low-power Wi-Fi and BLE wireless module, which has an estimated lifetime of 14, 4 months on 3000mAh battery running at 99.3% idle, 0.7% video capture rate.
Contents of the development kit:
- Board with Ingenic T31 MIPS processor at 1.5 GHz and low-power RISC-V core, H.265 encoder, 512 Mbit or 1 Gbit memory on chip equipped with
- Full HD 2M pixels camera at 30fps
- USB debug board
- Microphone and speaker
- InnoPhase Talaria TWO SDIO adapter board
- Equipped with INP1014 LGA module with WiFi 4 2.4 GHz, Bluetooth LE 5.0, PCB antenna
- Power Consumption: 57 uA at 3.3 V in Wi-Fi 802.11b power saving mode, 1 Mbps (DTIM10), 19 uA in hibernate mode
- JTAG programming and debug header
- INP3000 programming card with cables
- 12V power supply
The kit also includes Linux drivers for the Ingenic T31 and AI algorithms for human detection, facial detection/recognition, shout detection, vehicle detection, pet detection, as well as quick start and how-to guides. ‘use. The MIPS processor and Talaria TWO communicated via a “Dual-Stack” software implementation that shares processing responsibilities between the two chips to reduce system current consumption to the lowest level. The SDK also integrates device provisioning via BLE, AWS Cloud, and Azure Cloud connectivity, and support for over-the-air (OTA) firmware updates.
Technical details on estimated battery life:
- Video capture: 1080p at 25 fps, H.265
- 6 video capture events per day
- 10 second video capture duration
- Wi-Fi – DTIM10, 3min Keep-Alive
- Active/Idle Ratio – Wi-Fi Idle Connected: 99.93% per day; Active video capture: 0.07% per day
- Breakdown of battery consumption – Wi-Fi idle connected: 30% per day, video capture active: 70% per day
- Battery: 3000 mAh at 3.6 V
These conditions should allow the kit to last 1.16 years, or 14.4 months on a charge. WiFi standby power consumption is extremely low, so active video capture consumes the most, and this scenario is just 6 x 10 second captures per day or one minute video that probably won’t be realistic in most environments. But at least it should be possible to make AI cameras that last several months on a charge under most conditions.
Thanks to TLS for the advice.
Jean-Luc started CNX Software in 2010 on a part-time basis, before stepping down as Director of Software Engineering and starting writing daily news and reviews full-time later in 2011.