Abstract
At present, the main methods of solving the monocular depth estimation for indoor drones are the simultaneous localization and mapping (SLAM) algorithm and the deep learning algorithm. SLAM requires the construction of a depth map of the unknown environment, which is slow to calculate and generally requires expensive sensors, whereas current deep learning algorithms are mostly based on binary classification or regression. The output of the binary classification model gives the decision algorithm relatively rough control over the unmanned aerial vehicle. The regression model solves the problem of the binary classification, but it carries out the same processing for long and short distances, resulting in a decline in short-range prediction performance. In order to solve the above problems, according to the characteristics of the strong order correlation of the distance value, we propose a non-uniform spacing-increasing discretization-based ordinal regression algorithm (NSIDORA) to solve the monocular depth estimation for indoor drone tasks. According to the security requirements of this task, the distance label of the data set is discretized into three major areas—the dangerous area, decision area, and safety area—and the decision area is discretized based on spacing-increasing discretization. Considering the inconsistency of ordinal regression, a new distance decoder is produced. Experimental evaluation shows that the root-mean-square error (RMSE) of NSIDORA in the decision area is 33.5% lower than that of non-uniform discretization (NUD)-based ordinal regression methods. Although it is higher overall than that of the state-of-the-art two-stream regression algorithm, the RMSE of the NSIDORA in the top 10 categories of the decision area is 21.8% lower than that of the two-stream regression algorithm. The inference speed of NSIDORA is 3.4 times faster than that of two-stream ordinal regression. Furthermore, the effectiveness of the decoder has been proved through ablation experiments.
Highlights
In the past decade, drones have greatly promoted the rapid development of aviation [1], and have been widely used in different fields such as search and rescue [2], infrastructure inspection [3], speed measurement of a moving vehicle [4], and so on
Experimental evaluation shows that the root-mean-square error (RMSE) of non-uniform spacing-increasing discretization-based ordinal regression algorithm (NSIDORA) in the decision area is 33.5% lower than that of non-uniform discretization (NUD)-based ordinal regression methods
In order to solve the problem of autonomous navigation by indoor drones, the traditional approach is to use the simultaneous localization and mapping (SLAM) algorithm [7,8,9] based on expensive sensors such as device obtaining ordinary RGB three-channel color + depth map (RGB-D) [7], LIDAR [10], etc
Summary
Drones have greatly promoted the rapid development of aviation [1], and have been widely used in different fields such as search and rescue [2], infrastructure inspection [3], speed measurement of a moving vehicle [4], and so on. The SFM-based obstacle avoidance method obtains a control signal to control a drone by means of the hover-map-plan-path-moving-hover method. Recent studies have mainly used the deep learning (DL) algorithm to extract features to enhance the autonomy of drones [5], because the features extracted by this algorithm show better performance than manual feature extraction [13], and this method makes the end-to-end learning method possible [13] In this direction, some researchers have used demonstration learning [16,17] or reinforcement learning [18,19] to process the original monocular image output control commands, and have achieved impressive results in autonomous navigation of the drone [16,17,18,19].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
