DevMesh

TensorFlow_AndroidThings

DIKSHITA DESAI

DIKSHITA DESAI

Goa Velha, Goa

0 0
  • 0 Collaborators

Let us create a hardware system that classifies different objects. We will interface an NXP i.MX7D with touch screen and camera chip. The objects in front of the camera will be classified and in case of the image being that of a Dog or a Cat, we will further go ahead classifying their breed. ...learn more

Project status: Published/In Market

Mobile, Robotics, Artificial Intelligence

Intel Technologies
Intel Opt ML/DL Framework, Intel Python, Other, Intel FPGA

Code Samples [1]

Overview / Usage

In this project we walk through the interfacing of a microcontroller with a camera and touch screen, to classify objects.

We use TensorFlow and Android Things for the same.

Methodology / Approach

  1. Download and unzip the sample-tensorflow-imageclassifier project to the directory of your choice.
  2. Run the project using either of the following:
  • In Android Studio, select File > Open and select the directory where you unzipped the sample. Select Run > Run 'app'.
  • From the command line:
    cd sample-tensorflow-imageclassifier ./gradlew assembleDebug adb install -g -r app/build/outputs/apk/app-debug.apk adb shell am start com.example.androidthings.imageclassifier/.ImageClassifierActivity

  1. Point the camera at something that you want to analyze. The model is particularly good at recognizing breeds of dogs and cats.

  2. See the results on the multi-touch display. You can also connect a speaker or a headset to the board's audio jack. The sample uses text-to-speech to announce what it recognizes.

ALL THE DETAILED INFORMATION NEEDED FOR THE IMPLEMENTATION CAN BE FOUND ON GITHUB LINKED TO THIS ENTRY. KINDLY FOLLOW ME ON GITHUB TO APPRECIATE THE WORK.

Technologies Used

NXP i.MX7D

The i.MX 7Dual delivers high-performance processing for low-power requirements with a high degree of functional integration. The i.MX 7Dual features an advanced implementation of two ARM®Cortex®-A7 cores, which operate at speeds of up to 1.2 GHz, as well as the ARM® Cortex®-M4 core. The Pico variant is pin-compatible with the Intel® Edison for sensors and low-speed I/O, but also adds additional expansion possibilities for multimedia and connectivity, giving you cutting edge technology that can easily be expanded and implemented for IoT designs.

​

Android Things

TensorFlow

Camera

Touch Screen

Basic electronic components

Internet Connection

**Mobile Phone **

Repository

https://github.com/DikshitaDesai/HardwareClassifier

Comments (0)