Animal/Object Identification Using Deep Learning on Raspberry Pi

  • Param Popat
  • Prasham Sheth
  • Swati Jain
Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 106)


In this paper, we have explained how to implement a Convolutional Neural Network(CNN) to detect and classify an animal/object from an image. By using the computational capabilities of a device known as Raspberry Pi, which has a relatively lower processing power and an infinitesimal small GPU, we classify the object provided to the CNN. An image is fed to Raspberry Pi, wherein we run a Python-based program with some dependencies, viz. TensorFlow, etc., to identify the animal/object from the image and classify it in appropriate category. We have tried to show that deep learning concepts like convolutional neural networks, and other such computation intensive programs can be implemented on an inexpensive and relatively less powerful device.


Animal identification Object identification Deep learning Raspberry Pi Convolutional neural networks 


  1. 1.
    Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions (2014) CoRR, abs/1409.4842. arXiv:1409.4842
  2. 2.
  3. 3.
    Norouzzadeh, M., Nguyen, A., Kosmala, M., Swanson, A., Palmer, M., Packer, C., Clune, J.: Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning (2017). CoRR, abs/1703.05830. arXiv:1703.05830
  4. 4.
    Verma, N., Sharma, T., Rajkumar, S., Salour A.: Object identification for inventory management using convolutional neural network. In: 2016 IEEE Applied Imagery Pattern Recognition Workshop (AIPR).
  5. 5.
    D urr, O., Pauchard, Y., Browarnik, D., Axthelm, R., Loeser, M.: Deep Learning on a Raspberry Pi for real time face recognition. In: EG 2015.

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Institute of TechnologyNirma UniversityAhmedabadIndia

Personalised recommendations