Traffic Light Recognition using Deep Learning

Traffic Light Recognition using Deep Learning

Vamshi Gudavarthi

Vamshi Gudavarthi

Lakeside, California

Recognizing Traffic lights in the driving direction using Deep Learning. The dataset contains images taken by the drivers using Nexar app.

Artificial Intelligence

  • 0 Collaborators

  • 1 Followers

    Follow

Description

This project is pursued as a final project for the course Neural Networks and Pattern Recognition taken at University of California, San Diego. We tried to solve the problem posed in Nexar challenge shown in the following link, (https://challenge.getnexar.com/challenge-1). Although the challenge is over by then we are able to solve to the extent we were almost there matching the 2nd rank shown in their leaderboard. Also we localized the region of traffic lights using UCSD Traffic lights dataset where data for bounding boxes is also available. Apart from this I had many other machine learning and deep learning projects to my credit. Also I am currently enrolled for graduate study at UCSD specializing in Intelligent Systems, Robotics & Control. Following is one of the reference we used for our project (Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks by Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun)

Default user avatar 57012e2942

Anurag K. updated status

Default user avatar 57012e2942

Anurag Kushwaha

I'm currently working on a project called DoorBell. This is a IoT virtual door bell that sends respose as an email or sms if someone knocks the door. Also it can send the picture of the person standing behind the door.

Default user avatar 57012e2942

RITVIK D. updated status

Default user avatar 57012e2942

RITVIK DAVE

Hii, I am Ritvik Dave currently doing graduation in Electronics & Communication Engineering at Techno India NJR Institute of Technology. Right now I am working on a Smart City project called "Smart Well/Lake Monitoring System.

Medium screenshot 2017 01 07 21 10 50

jnc j. updated project Mini Operadora Bluetooth status

Medium screenshot 2017 01 07 21 10 50

jnc jnc

A Mini Operadora Bluetooth consta em substituir os ramais de empresas no que ocasiona em um baixo consumo de energia. Tendo com base sua distância de 10 metros, no que consegui expandi-la para o dobro ou mais a partir de um pequeno banco de dados que armazena e transfere a voz em tempo real.

Medium imageedit 7 5037756644

suryaveer s. created project Virtual Multi-controller

Medium a40dfaf8 5c0d 4047 a666 224ce18ee718

Virtual Multi-controller

Virtual Multi-controller is a virtual game controlling gesture. This can control each and every PC game virtually using a single device. We can calibrate this device according to user’s choices that he /she wants to play. Most of us want to play video games virtually because it looks so fascinating, but can’t play because these type of devices are so expensive and even cannot be afforded. But with the help of this controller we can play virtually. Construction Idea: We are going to use some basic sensors like orientation sensor, heart beat sensor etc. These sensors can give us position and behavior of player which we need during playing the game.

Medium default profile

donel a. updated status

Medium default profile

donel adams

Google or Bing name to view associate networks fostering business development by maximizing any platform potential for growth utilizing AI

Profile pic

Johnny C. added photos to project The Small Garden Birdwatch

Medium 3ddf1ec7 2fdf 4342 9a3e e2a95876d616

The Small Garden Birdwatch

Despite urbanisation, our back garden silently provides wildlife a chance to recuperate from our harsh urban landscape. Birds are able to fly into our garden - pecking away seeds from birdfeeders; pulling out and sucking worms from the soil; sneakily hunting bugs (that enjoy sticking onto plants and composts) for "yummy" snacks; having a wash by the pond; and even just sitting around sunbathing.

Some gardens attract certain types of birds, whilst some other, may attract other types. Wouldn't it be awesome to get a visual big picture of bird statistics that may help us improve our garden and the "bird wildlife community" as a whole? ("If we cannot measure, we cannot manage").

Inspiration: In the UK, there is this intuitive organised by RSPB (a charity) called The Big Garden Birdwatch (https://ww2.rspb.org.uk/get-involved/activities/birdwatch), aiming to do exactly that - "Count the wildlife that's counting on you. We'd love to know what you saw during Big Garden Birdwatch". The way it works: you spend a day with your loved ones, sitting by the garden, watching wildlife (primarily birds) coming in and out, and jot down what you see. You then submit the survey result via the web portal - contributing in building that big picture of "the bird wildlife community".

The Problem: not everybody has the time to participate, or the bird identification skills - and as a result, vital bird statistics collection opportunity may be lost, or birds being mis-identified.

So here's an idea - A network of local RealSense Cameras sitting on small form factor computers that poll and feed wildlife statistics of our back gardens onto a cloud server, where data maybe stored, analysed, visualised, and used for education.

Could we add AI recommendation (e.g. this is how to increase your chance of getting 50% more birds and reduction of garden pests... etc). Could we integrate some kind of auto bird recognition software? Include sound recording too? Time of day? Temperature and humidity? Sensors and Actuators? The possibility is infinite... maybe start simple and stupid, then go complicated and clever?

What will you make.

See More

No users to show at the moment.

Bigger bob duffy 3d head avatar
  • Projects 4
  • Followers 101

Bob Duffy

Folsom, CA, USA