AINS: Affordable Indoor Navigation Solution via Line Color Identification Using Mono-Camera for Autonomous Vehicles
Nizamuddin Maitlo, Nooruddin Noonari, Kaleem Arshid, Naveed Ahmed, Sathishkumar Duraisamy
TL;DR
The paper tackles indoor autonomous navigation in GPS-denied, budget-constrained settings by introducing AINS, a monocular-camera-based system that detects color-lined paths to guide motion. It combines HSV color-thresholding, contour-based edge detection, and image moments to locate a path centroid, from which a steering angle is computed and applied in real time. Experiments on a real-time Ubuntu platform show that vision-based path tracking can outperform sensor-based baselines in accuracy and speed while dramatically reducing hardware costs. The work highlights practical deployment viability for indoor environments and points to future enhancements via deep learning to further boost robustness and applicability.
Abstract
Recently, researchers have been exploring various ways to improve the effectiveness and efficiency of autonomous vehicles by researching new methods, especially for indoor scenarios. Autonomous Vehicles in indoor navigation systems possess many challenges especially the limited accuracy of GPS in indoor scenarios. Several, robust methods have been explored for autonomous vehicles in indoor scenarios to solve this problem, but the ineffectiveness of the proposed methods is the high deployment cost. To address the above-mentioned problems we have presented A low-cost indoor navigation method for autonomous vehicles called Affordable Indoor Navigation Solution (AINS) which is based on based on Monocular Camera. Our proposed solution is mainly based on a mono camera without relying on various huge or power-inefficient sensors to find the path, such as range finders and other navigation sensors. Our proposed method shows that we can deploy autonomous vehicles indoor navigation systems while taking into consideration the cost. We can observe that the results shown by our solution are better than existing solutions and we can reduce the estimated error and time consumption.