Overview

Qualcomm QCS6490 Object Detection

About Advantech Container Catalog

Advantech Container Catalog is a comprehensive collection of ready-to-use, containerized software packages designed to accelerate the development and deployment of Edge AI applications. By offering pre-integrated solutions optimized for embedded hardware, it simplifies the challenges often faced with software and hardware compatibility, especially in GPU/NPU-accelerated environments.

Key benefits of the Container Catalog include:

Feature / Benefit	Description
Accelerated Edge AI Development	Ready-to-use containerized solutions for fast prototyping and deployment
Hardware Compatibility Solved	Eliminates embedded hardware and AI software package incompatibility
GPU/NPU Access Ready	Supports passthrough for efficient hardware acceleration
Model Conversion & Optimization	Built-in AI model quantization and format conversion support
Optimized for CV & LLM Applications	Pre-optimized containers for computer vision and large language models
Scalable Device Management	Supports large-scale IoT deployments via EdgeSync, Kubernetes, etc.
Lower Entry Barrier for Developers	High-level language (Python, C#, etc.) support enables easier development
Developer Accessibility	Junior engineers can build embedded AI applications more easily
Increased Customer Stickiness	Simplified tools lead to higher adoption and retention
Open Ecosystem	3rd-party developers can integrate new apps to expand the platform

Container Overview

The Qualcomm QCS6490 Object Detection is an Object detection demo Container on Qualcomm QCS6490 DSP. This container demostrate Edge AI computing on Qualcomm platform, with built-in AI packages and DSP/GPU container passthrough enabled.

This container support Advantech hardware devices accelerated by Qualcomm Hexagon DSP such as AOM-2721. Built with an efficient on-chip DSP, the Qualcomm QCS6490 enables real-time object detection directly at the edge. Its powerful AI inference capabilities make it ideal for edge devices in industrial inspection, smart logistics, retail analytics, and public safety monitoring. Developers can deploy lightweight object detection models optimized for the QCS6490 NPU, achieving low-latency performance without relying on cloud resources. This accelerates AI application development and supports responsive, scalable solutions in edge environments where performance and efficiency are critical.

Key Features

AI Application Demo: Object Detection
Hardware Acceleration: Optimized access to DSP
Complete AI Framework Stack: Qualcomm IM SDK, SNPE
Edge AI Capabilities: Support for computer vision

Hardware Specifications

Component	Specification
Target Hardware	AOM-2721
DSP	Hexagon DSP
Memory	8 GB

Prerequisite Software on Host OS

Component	Version	Description
LE Yocto Linux	1.3	LE1.3 BSP

Software Components

Component	Version	Description
Qualcomm IM SDK	2.0.0.r2	QIM SDK is a unified environment for developing AI and multimedia use cases at the Edge on the Qualcomm® Linux platforms
YOLO	v5	YOLOX Computer Vision Model for Retinopathy detection
Object Detection	1.0.0	Object Detection Application

Quick Start Guide

Refer to Advantech Container Catalog Github: ACC-L3-01-Qualocmm-AI-enabled-Container and Qualcomm QCS6490 Container for more quick start guide details.

Run

./run_qc-ai-container.sh