NVIDIA® Jetson™ Developer Challenge

CURRENT STATUS

Winners announced

SEE RESULTS

Thanks to all Participants!

SEE RESULTS

NVIDIA® Jetson™ Developer Challenge

Back

Ai-Nimals

Project description

Ai-Nimals was created to find out which birds specious are visiting my winter bird feeder in the garden. It's is a connection between USB camera, Jetson TX2 board, solar charger and battery power supply. It is mobile and closed in case. It can be placed anywhere.

When bird visit feeding spot, camera catches it and TX2 software classifies the object. Software updates statistics and writes it to CSV file. When experiment is finished, file can be downloaded and processed in terms of statistics.

Software was fully written by my self after working hours in python. I used keras (with tensorflow) and opencv. For birds localization I make "one shot" detection using MobileNetSSD network with pretrained weights. For classification I base on VGG16 deep neural network architecture which was fully trained by myself using ctrl-break method and fine tuning ImageNet weights.

I wrote images scrapping script to get training images of birds specious which are visiting gardens in winter in Poland (22 specious). I downloaded ~40000 images. Preprocessed them by another script which was automatically cropping birds and sort them basing on their specious name. In the end I spend 40 working hours with ornithologist to manually check and label all images and prepare them for training process. Training process took about 10 days on my GTX1060 before I gained 93% accuracy in classification (on testing set).

Project is scalable. It can count not only birds but also other animals or even cars. It's just a matter of training data  for two neural networks.

Comments (8)

  1. m

    magdalena_kazmierczak


    Super idea and worth further developement!

  2. Joseph Horwath

    Cool idea and nice execution. The solar powered is a nice touch.

  3. HB

    Harsh Bajaj

    Nice hack to help us learn more about nature

  4. j

    johnyhajduk

    Nice work Pawel! Open-source project sounds great. The winner is coming!

  5. Pawel Rolbiecki

    19 Feb - 4 Mar is voting and reviewing period. And finals and public votes choice is announced on 5 Mar 2018.

  6. Pawel Rolbiecki

    Questions are in Polish but I'll answer in English. I am going to push source to Github to make it fully open for all. So you will be able to see the arch. Also scrappers, image pre processors and training scripts.

  7. MM

    Marcin Matera

    Świetny pomysł, gdzie i kiedy będzie można zobaczyć wyniki i szczegóły projektu?

  8. m

    mat_telega

    Pawel u r a genius! Respect!