General vehicle information recognition  based on deep learning algorithm

General vehicle information recognition based on deep learning algorithm

Based on Intel CPU + GPU , CNN vehicle information (brand + model + year) recognition

Artificial Intelligence

  • 0 Collaborators

  • 0 Followers

    Follow

Description

  1. based on deep learning;
  2. around 2000 vehicle models, including brand, model, year;
  3. 10 colors;
  4. 7 vehicle types;
  5. vehicle model detection accuracy more than 98%;

Gallery

Medium img 20171105 145128

Sahil S. created project MapTrace

Medium 09c43f9c b237 4fb0 b043 0bf334b0d5ba

MapTrace

THE ISSUE :

There are so many cases of now days where we come to know that there some people are selling or consuming drugs nearby , but some time police remember's that place and some times not and which is not very good thing , and even it will not make easy to give training to new police officers which is not good .

OUR MAGIC SOLUTION :

We have created a app which can analyze all these thing , this app take longitude and latitude value from current location and also ask for name of Drug which is being selling or consuming by suspect and mergers all these datas to heat map and save it to firebase and generates Heat Maps from that .. which is very help full for us..

Medium 22279457 2468435569963813 2256757450865497527 n

SHIVAM K. updated status

Medium 22279457 2468435569963813 2256757450865497527 n

SHIVAM KUMAR ROY

Hello,I am still working on Android development program and web development also. I just want to lean about amchine learnig and AI ,to explore its use in whatever the things are around us.

Medium soubhik 20das

Soubhik D. created project Presentify-let's know where we stand

Medium 0cfe0ada a187 4bb4 a79c 5e040ddf131c

Presentify-let's know where we stand

Suppose we're speaking in a hall before a hige audience but are unable to know whether or not the audience is interested so that we can mix up with lightning talks, motivational stories, quotes, etc. At that time, our talk starts becoming boring and we start getting the tag of 'unwanted speaker'. This will never happen if we have the data, specifically data of dynamic and running time users' rating of the speakers. There just needs to be a few Realsense Cameras placed optimally in the hall and a person/bot with AR and or VR headset tracks the user's rating collectively (heatmap). Realsense cameras and the headset are connected. This promises to make every talk in the world interesting after gathering enough data.

Medium img 20171105 145128

Sahil S. updated status

Medium img 20171105 145128

Sahil Singh

Iam currently working on a life saving IoT device which helps diabetic type-1 patients to automatically regulate their insulin levels. And also gives notification on high or low blood sugar..

Medium sofian hadiwijaya

Sofian H. updated status

Medium sofian hadiwijaya

Sofian Hadiwijaya

Now I just started new company call warung, warung is a small shop that sells cold bottled drinks, candy, cigarettes, snacks and other daily necessities, while the larger ones are small restaurant establishments. But instead of using POS to track the transaction we will build speech recognition and computer vision If you have any comment or suggestion for my project feel free to comment Thanks

Medium 3822884

Octaviano P. created project Garbage Detector

Medium a0e38ea6 680c 403b ab2d e7200f46447f

Garbage Detector

How we can differentiate garbage types whether "bottle", "pet bottle", "burnable" and so on? we sometimes hard to differentiate it. My experience when visited Japan, there are several waste bin types like i mentioned before. which one is correct when i have "banana peel" ? . In my country also has several types of waste bin types like "organic" and "not organic" , which one is correct when i have "bottle"? we don't know. So this project is created to differentiate garbage type based on images.

how it works? the user just upload image of garbage to system and the system will response the kind of garbages correctly! the garbage image will be forwarded to inference machine that i prepared before. the model in inference machine is Convolutional Neural Network. this system accuracy in predicting garbage type reach 90%.

Step-by-step of implementation:

  1. Download dataset from Image-net Stanford (imagenet.stanford.edu). This dataset contains 1000 class of images. we select only image that appropriate for our system like: Banana, Bottle, Pet Bottle, and so on. we additionally augment other image from other source to enrich dataset

  2. Train the model on dataset based on Convolutional Neural Network (see my previous project: https://devmesh.intel.com/projects/landuse-classification-convolutional-neural-network)

  3. After obtaining a model, we try to inference a new image to model. let say image captured by camera will be forwarded to this machine.

  4. create Front-end like Android or web apps that perform capturing images and forwarded to model. this sometimes use web service to connect front-end with model. in this case i use Flask micro-framework in Python environment as web apps and web service.

See More

Default user avatar 57012e2942

Diyrl

do you have a github link?

No users to show at the moment.

No users to show at the moment.