einavg7 / study-project-image-recognition

Repository for IFGI study project winter semester 2020-21 Image Recognition for Citizen Science - Indoor Movement Tracking.

Study Project - Citizen Science for Image Recognition

Image Recognition for Citizen Science TRACKING INDOOR MOVEMENTS

Aim

To track the movement of individuals entering a building and count them according to their direction.

Case Study

Institute for Geoinformatics (IFGI)

Project Steps

Hardware

• Raspberry Pi 4 Model B 4GB RAM
• Raspberry Pi Power Supply
• Raspberry Pi Camera 2 Model
• Raspberry Pi Case
• SD Card Reader
• 32GB, SanDisk Extreme
• HDMI Adapter

Software

Described in source_codes&models folder

Possible Applications

Museums, Hospitals, Service Centers, Health Clinics, Government Offices, and other buildings.

---

References

• dlib C++ Library. Retrieved 3 February 2021, from http://dlib.net/
• Home - OpenCV. Retrieved 3 February 2021, from https://opencv.org/
• Jia, Y. (n.d.). Caffe: Convolutional architecture for fast feature embedding. https://doi.org/10.1145/2647868.2654889
• Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C., & Berg, A. (2016). SSD: Single Shot MultiBox Detector. ECCV.
• Rosebrock, A. (2017). Object detection with deep learning and OpenCV - PyImageSearch. Retrieved 18 December 2020, from https://www.pyimagesearch.com/2017/09/11/object-detection-with-deep-learning-and-opencv/
• Rosebrock, A. (2018). OpenCV People Counter - PyImageSearch. Retrieved 18 December 2020, from https://www.pyimagesearch.com/2018/08/13/opencv-people-counter/
• Rosebrock, A. (2018). Simple object tracking with OpenCV - PyImageSearch. Retrieved 18 December 2020, from https://www.pyimagesearch.com/2018/07/23/simple-object-tracking-with-opencv/