A Path Breaking Low Power Edge AI Platform With 5G/WiFi6 connectivity capabilities, designed to build next gen AI apps at edge We Customize, Design & Integrate End-to-End Solutions based on your requirement Prev Next A Path Breaking, Low Power Edge AI Platform With 5G/WiFi6 connectivity capabilities, designed to build next gen AI apps at edge     We Customize, Design & Integrate End-to-End Solutions based on your requirement
About iDhi™ The iDhi™ platform comprises ISQ8250/ISQ5165 small-form-factor System On Module (SOM) coupled with a customizable carrier board with high-speed storage, LAN/WLAN/WWAN connectivity, and interfaces to cameras, displays, and third party sensors. It leverages Qualcomm’s Snapdragon QCS8250/QRB5165 System-On-Chip’s powerful heterogeneous compute capability of 10 Trillion Operations Per Second (TOPS) to build disruptive Edge AI solutions.
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 Prev Next 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