EDGE AI PLATFORM – iDhiTM

A Path breaking Low Power Al platform with 5G/WiFi6 connectivity and intelligent sensing capabilities, designed to build next gen cloud connected AI solutions at edge.

The iDhi platform is built around Innominds ISQ5165/ISQ8250 small-form-factor System on Modules (SOM) coupled with a customizable carrier board that integrates high-speed storage, LAN/WLAN/WWAN connectivity, and interfaces to cameras, displays, and third-party sensors. It leverages Qualcomm’s QRB5165 and QCS8250 SoCs, providing up to 15 TOPS of compute in Linux and Android environments for industrial enterprise and robotic applications.

Explore Devices

KiteBoardTM SoM Series

Our efficient & reliable building blocks for your IoT & Embedded solutions

ISQ 8250

  • Video Telematics
  • Healthcare
  • AI Connected Cameras
  • Smart Retail
  • Digital Signage
  • Worker Safety

ISQ 5165

  • Autonomous Delivery Vehicles
  • AMR and AGV for Industries
  • Commercial and Enterprise Drones

ISQ 2290

  • Industrial Handheld
  • Camera
  • Asset Tracking
  • Retail Point-of-Sale (POS)

EXPLORE SOMS

Highlights

Real – Time Insights

  • Provides real-time inferences for sense and control mission-critical scenarios
  • Uses highly accurate trained Computer Vision and Al models deployed at the edge
  • Leverages SoC’s heterogenous compute capability

Designed for Demanding Edge Scenario

  • Supports Android and Ubuntu Linux environments
  • Multiple high-performance interfaces for cameras, LiDARs and other intelligent sensors, controllers, and actuators.
  • Wired and wireless connectivity to on-premises and public clouds
  • Low power Fanless designs and compact portable devices

Multi-layer Security

  • Hardware level – Provides encryption through TrustZone (TZ)
  • Cloud level – Enables Role-based access control and device provisioning to enable only authorized devices to communicate with the cloud platform
  • Chipset level – Offers end-to-end encryption with an external cryptochip that is fully isolated from the SoC, and acts as a secure store for all security certificates

Highly Customizable Platform

  • Platform offers a high degree of modularity with standard high-performance interfaces like custom SMARC and M.2 connectors for hardware extensions like compatible storage, WWAN, AI accelerators, and various video inputs
  • Provides customizable splash screen and launcher to reflect the branding guidelines of the OEM

Key Features

Multiple Input/Output

Acquires multiple streams from cameras, LiDARs and intelligent sensors simultaneously, allowing rich multi-modal processing and inferencing for a real time control and display.

Global Connectivity

Supports global 4G and 5G technology with high quality end-to-end connectivity that enables low latency, high precision insights.

Optimized AI on the Edge

Leverages Qualcomm’s Neural Processing SDK and Qualcomm AI stack to deliver performance optimized on-device neural networks trained in Caffe/Caffe2, ONNX
or Tesor Flow.

Built-in Robotics

Supports Ubuntu and Robotics Operating System (ROS) 2 along with pre-integrated drivers for selected cameras and sensors – ISQ8250/ISQ5165 only.

Robust Video Processing

Offers rich multimedia a middleware that support a wide range of video/audio processing tasks and analytics engines like FastCV to implement and accelerate a wide range of multi-camera/display video algorithms in GPU.

Cloud Agnostic and ModelOps Capabilities

Supports public (AWS/Azure) cloud components or can connect to OEM specific private cloud. Leverages iFusion.ai™ ModelOps capabilities for end-to-end model orchestration.

Applications

Transforming Patient Outcomes with Powerful, Predictive and Precise Connected Healthcare

MedTech Solutions
Building advanced MedTech Devices
  • Diagnostic Equipment
  • Surgical Assistance Devices
  • Robotic Surgery Systems

Contactless vital sensing for telehealth from facial images

Customizable Platform for Tele-operation over Private 5G Network

Smart Tele-operation at Edge
  • Interfaces like multiple cameras, LiDAR, IMU and other sensors, motion controllers, display units at the vehicle and the operator side.
  • Teleoperation specific APIs, AI Analytics, Cloud and Security tightly integrated over a Private 5G network to realize the QoS and performance parameters required for real-time low speed teleoperation.

Accelerate your Industry 4.0 Digital Transformation with AI at the Edge

Industry 4.0
  • Realize the power of real-time operational data to optimize efficiency and digital transformation by enabling AI at the edge.
  • Connect, process, and evaluate your data in real-time with our customizable plug and play hardware and software solutions.

Specifications

Hardware Specifications

Software Specifications

SOM TOP VIEW

 
Components Descriptions
Processor (QCS8250 / QRB5165) Kryo 585-64bit with 4MB L3 Cache, (Kyro gold 2.419 GHz with 256KB L2)*3, (Kyro gold 2.842 GHz with 512KB L2)*1 and (Kyro silver 1.8 GHz with 128KB L2) *4
Memory and Storage System memory: 8GB LPDDR5 POP UFS memory: 128GB
OS 4G/5G through RM500Q-GL(Option)
Connectivity: WWAN Wi-Fi 6 – 802.11ax 2×2 MU-MIMO Wi-Fi/BT 5.1
Peripheral Interfaces Camera: USB, DVI, HDMI MIPI – CSI Display: DVI, HDMI, DisplayPort and MIPI – DSI High-Speed I/O: USB 3.x, PCIe
Connectivity LAN Gigabit Ethernet
Expandable Storage NVME/SATA SSD slot
Hi-Performance Expansion M.2 slot with USB3.x & 2-lane PCIe Gen 3
Antennas 2X2 MIMO for 4G/5G , 2X2 for Wi-Fi/BT
Power Input 12V DC
Video Encoding Up to 4K 120 fps 10-bit: H.265
GPU Adreno 650, Fmax 587MHz-2X2K 60fps UI, OpenGL ES 3.2, Vulkan1.1, DX12FL12.1, OpenCL 2.0 full profile
Digital-signal Processing/NPU Compute DSP with Hexagon Vector extensions (dual-HVX) and Hexagon CP2.0, Dedicated NPU230
Security SPU 240, Secure boot3.0 using Android Strongbox and iUICC, secure debug, secure key provisioning, TrustZone, Qualcomm® Trusted Execution Environment 5.0, hardware-supported Keystore Crypto engine v5 (CE5),  DRBG/PRNG (FIPS- compliant), inline crypto engine (FIPS- compliant) Secure file system, Fast trusted storage, DRM support in Hardware
Audio Built-in Audio Codec, Support for Multiple Digital MIC/MIC-Arrays, Stereo Speaker outputs, Qualcomm Fluence Pro audio signal processing (echo, noise, beamforming, beam tracking), Enhanced third party front-end audio processing
SoM Interface Custom SMARC
Dimension SoM – 100mmX50mm. Carrier – 23.8 cm X 20 cm
Peripheral Compatibility Camera: Stryker – (DVI interface), AIDA – 100 (HDMI interface), Customized IR camera (USB 3.1) Displays: Waveshare AMOLED FHD HDMI display with touch Storage: Western Digital NVMe SSD – SN500, SN550 WWAN: QUECTEL – RM500Q – GL (Worldwide 4G/5G support)


Components Descriptions
OS Andriod- 10, QCS8250LA1-0-AP-Standard-OEM/master/r00013. 1 or Ubuntu
Compute Power 15 TOPS cumulative (Octa-core APSS, DSP, NPU, GPU, DPU, VPU)
Imaging OpenCL 2.0 profile, OpenGL 3.2 profile, Vulkan 1.1, OpenCV accelerated by fastCV
Board Support Optimized bootloader and drivers for all listed peripherals
Package (BSP) Fluence/Acoustic voice suite (use case like Keyword spotting, Voice-based UI)
Analytics Object detection | Object tracking | Image segmentation
Public Cloud Connectivity Azure IoT Hub
Device Management Edge Agent AWS Green grass, Azure IoT Edge, and Customized OEM specific edge agents
ML ops AWS Sagemaker, Azure ML and iFusion™
OTA Updates Android OS updates, Security patches, Device specific application updates

SDKs

Components Descriptions
Hexagon DSP SDK Designed to optimize the features and performance of multimedia software
Helps allow audio, imaging, embedded vision, and heterogeneous computing acceleration on the Hexagon DSP embedded in Qualcomm Technologies processors to create compelling multimedia user experiences
Qualcomm® Neural Processing SDK Optimizes deep learning processing performance across available resources to achieve a superior edge computing experience
Qualcomm® Computer Vision SDK Offers a mobile-optimized computer vision (CV) library, enabling use cases like object detection, object tracking, & image segmentation
Qualcomm Spectra
480 Image Signal
Processor (ISP)		 Supports up to 12 cameras by D-PHY and 18 cameras by C-PHY (seven concurrent)
SNPE SDK Enables trained AI/ML models execution on the edge
ROS 2 Pre-integrated Robotics Operating System 2 on ISQ8250/ISQ5165 only with selected drivers for sensors and outputs

KiteBoard SOMs