The QCS6490 Vision-AI Development Kit features an energy-efficient, multi-camera, SMARC 2.1.1 compute module, based on the Qualcomm QCS6490 SOC device.
High performance cores on the QCS6490 SOC include an 8-core Kryo™ 670 CPU, Adreno 643 GPU, Hexagon DSP and 6th gen AI Engine (13 TOPS), Spectra 570L ISP (64MP/30fps capability) and Adreno 633 VPU (4K30/4K60 enc/dec rates), ensure that exceptional concurrent video I/O processing performance is delivered.
A useful subset of the SMARC’s interfaces are pinned-out on the carrier board, to support four cameras, two displays, five USB interfaces, CAN-FD, Gigabit Ethernet and optional high-speed Wi-Fi networking. The audio subsystem includes two PDM microphones, stereo audio Codec, digital audio interface and analog audio jack I/O.
Integrated TPM and Wi-Fi/BT modules are offered as a SMARC assembly option.
The carrier board has M.2 slots for NVME storage and advanced wireless options. Compact 100 mm x 79 mm carrier board dimensions and mounting hole alignment with similar AI developer boards, enable a drop-in capability with many enclosures.
The development kit ships with a Yocto-based Linux BSP, plus example AI and multi-camera open-source applications. Additional OS options are available, with Windows 11 IoT Enterprise due in 2H24. (Qualcomm also supports Android and Ubuntu Linux on the QCS6490, but for this platform it will depend on demand).
