Global Proceedings Repository - American Research Foundation, ICCIIDT London - UK

Font Size: 
Computer Vision for Object Recognition and Tracking Based on Raspberry Pi
Ali A. Abed (SMIEEE), Sara A. Rahman

Last modified: 2017-01-02

Abstract


The tasks of object recognition and tracking are a key component of video surveillance and monitoring systems. This paper presents CamShift (Continuously Adaptive Mean Shift) algorithm and color detection in darkness for tracking a target with video sequences in real time. The system described in this paper contains a camera that is connected to a Raspberry Pi. The Raspberry Pi has an image processing algorithm which detects an object first and then tracks it. Color detection generally is a primary stage in most of the image processing applications, if the application is based on the color information. To monitor object in video, an embedded board is adopted to monitor the activity of the object of interest based on Raspberry Pi with LCD touch screen display TFT monitor. A software method for real time implementation of moving object tracking and recognition is done using Python programming language with OpenCV libraries. The two algorithms are tested and compared to prove the robustness of the proposed color detection algorithm operating in a low light environment. Good practical results for recognition and tracking are obtained.

Full Text: PDF