Comparative Analysis of Depth Detection Algorithms using Stereo Vision

Koundinya, Poluri Nikhil and Rajalakshmi, P. and et al, . (2020) Comparative Analysis of Depth Detection Algorithms using Stereo Vision. In: IEEE World Forum on Internet of Things, WF-IoT 2020 - Symposium Proceedings, 2 June 2020 - 16 June 2020.

Full text not available from this repository. (Request a copy)


In recent years, the use of unmanned aerial vehicles in various domains has increased exponentially. Drones are being extensively used in the fields of Agriculture, Transportation, military, etc. Different sensors are being integrated into the drones depending upon the application. Lately, LIDAR sensors are being integrated on the drone for acquiring depth-related information. Though these sensors have advantages, they are very costly and do not perform very well under high sun angles. Stereo cameras can be mounted on drones to get depth perception of the obstacles as they are cheaper and efficient. In this paper, we have developed and compared two different algorithms ( Conventional and deep learning-based) for realtime depth detection of the obstacle using stereo vision with the intention to mount the stereo camera on drone in future. The comparison is based on accuracy, range of operation and load incurred by the algorithm on the system. The coefficient of determination (R 2) and correlation coefficient has also been calculated which shows that Algorithm1 exhibits correlation and R 2 value of 0:9985 and 0:9971 respectively. This is considerably higher than Algorithm2 whose values are around 0:8779 and 0:7707 respectively.

[error in script]
IITH Creators:
IITH CreatorsORCiD
Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Coefficient of determination; Comparative analysis; Correlation coefficient; Detection algorithm; LIDAR sensors; Real time; Stereo cameras; Sun angle
Subjects: Electrical Engineering
Divisions: Department of Electrical Engineering
Depositing User: . LibTrainee 2021
Date Deposited: 13 Jul 2021 05:44
Last Modified: 18 Feb 2022 06:29
Publisher URL:
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 8261 Statistics for this ePrint Item