globaledgesoft/Autoware.ai-on-RB5

Stars
2
Language
Dockerfile
License
GNU General Publi...
Created over 2 years ago
Updated over 2 years ago

globaledgesoft/Autoware.ai-on-RB5

globaledgesoft

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Autoware.ai is an Autonomous Vehicle development software stack. This project demonstrate that how to deploy Autoware.ai on Qualcomm Robotics RB5 Platform.

AIML-DashCam-App

The objective of this repository is to create an android application which would have the deep model trained and converted to the Qualcomm NPE format and thus deployed

deeplabv3-application-using-neural-processing-sdk

The application demonstrates the Image Semantic Segmentation considering the input image in portrait mode and changes the background to grayscale except for the persons.

Scene-Detection-on-RB5-Using-Pytorch-SNPE

Project is intended to build and deploy an scene detection application onto Qualcomm Robotics development Kit (RB5) that detects whether the bot is in an indoor or outdoor environment and takes necessary actions

Unsupported-Operation-Development-in-SNPE

This project is intended to build and deploy an SNPE model on Qualcomm Devices, which are having unsupported layers which are not part of the SNPE SDK or not supported by the SNPE Converter.

merchant-cart-aws-iot

Merchant Cart demo with AWS IoT integration of Music Festival for Inventory Management

RB5-Ball-Follower-Robot-using-Qualcomm-FastCV

This project is to build and deploy an Ball Follower Robot application on the Qualcomm RB5 Robotics platform that detects a football and track that detected football using Qualcomm's FastCV (Computer Vision SDK).

qca_hb_ecosap

eCos AP for the QCA9531 Honeybee Chipset

Lane-Detection-Using-YOLOP-on-RB5

The project is intended to demonstrate Lane tracking & detection on Qualcomm’s Robotics Platform RB5. YOLOP is the architecture used to implement this solution on top of the BDD100K Dataset. The inference is done using SNPE on RB5 with DSP Hardware accelerator, and it achieves the performance of 4.15 FPS.

on-device-facial-experssion-recognition

The application demonstrates the Facial Expression Recognition which works in real-time on Snapdragon mobile platforms.

Collision-Avoidance-RB5

This project is for avoiding a collision using lidar sensor & algorithm on RB5.

Center-Stage

Depth-Estimation-on-CM2290-with-SNPE-on-Android

This project is intended to build and deploy a depth estimation without depth sensor to generate depth map from RGB camera frames using monocular depth estimation model PackNet-SfM on CM2290 with SNPE on android Application with Integration on Thundercomm TurboX CM2290 LA (Linux Android) DK (Development Kit).

Low-Light-Image-Enhancement-Using-FastCV-on-C610

This project is intended to enhance the captured image from c610 camera under low light setting using Qualcomm’s FastCV API.

smartvine-greengrass

This application has several components such as temperature, moisture, light sensors connected to a Qualcomm 410c Dragonboard running AWS greengrass to show the efficiency of processing the data in the edge and saving cost on the Cloud

RB3-Auto-Drive

This project is intended to build and deploy an auto drive application onto Qualcomm Robotics development Kit (RB3) that detects obstacles and avoids it

AIML-Board-App

Contains the code with regards to the steps undertaken for training the model with caffe framework on custom data as well as the converted model (.dlc) file which has been deployed in the Qualcomm Android Application

person-detection-snpe-ros2-cpp-api-rb5

This project is for the Demonstration of Person Detection using ROS2 & SNPE using C++ API on Qualcomm’s Robotics RB5 Platform.

home-control-with-secure-communication

This application has several component like BLE Bulb, Smart Lock, Smoke detector, are securely connected to the Qualcomm QCA4020, and has capabilities of controlling those devices via android application with AES128 bit encryption. Secure connection and communication done via BLE.

home-control-app

Android App helps to interact with the QCA402X board to control the Smart Devices at home or connected to QCA board.

EfficientDet-based-object-detection-on-RB5

This project is intended to build and deploy EfficientDet model integrated Object Detection that can detect various objects and will be integrated with Qualcomm's RB5.

AutonomousRB5

This project is for the demonstration of Wake-word based Trigger to RB5, Stop Sign Detection, Reinforcement Learning based Lane Tracking & Following, and Obstacle Detection which automates the RB5 to run autonomously on maps.

rb5-person-segmentation

Person Segmentation which will perform the Segmentation operation using TFLite library

Person-Detection-With-YOLOV5-on-CM2290-with-SNPE

This project is intended to build and deploy a person detection on CM2290 with SNPE on android application using YOLOV5 model with Integration on Thundercomm TurboX CM2290 LA (Linux Android) DK (Development Kit).

Number-Plate-Detection-on-QCS610

This project is about the Number Plate Detection & Recognition on Qualcomm's QCS610 Platform.

home-control-app-with-secure-communication

Android App helps to interact with the QCA402X board securely to control the end Smart Devices at home to the board via secure BLE

LaneNet-on-RB5-with-SNPE-Python-Wrapper

This project is intended to build and deploy the lane detection application on the Qualcomm Robotics Platform RB5 which detects the road lane on real-time and helps to guide vehicle accordingly.

RB3-Navigation

This project implements Opensource ROS navigation stack porting on Qualcomm RB3. with use of depth camera sensor available on RB3 for navigation, obstacle detection and avoidance

facial-expression-recognition-using-keras

The application demonstrates the Facial Expression Recognition which works in real-time on Snapdragon mobile platforms

Ground-Plane-Estimation-on-RB5-using-SNPE-for-AV-Development

This project is intended to build and deploy an Autonomous Vehicle Development Use case for the ground plane estimation on RB5 from RGB camera frames using Deep Learning approach. The implemented use case uses the Qualcomm’s ISP camera on RB5.

Edge-AI-security-using-AWS-boto3

The goal of this project is to explore security techniques for passing images from edge devices to the cloud using AWS Boto3 object encryption techniques