Drone Navigation Using Region and Edge Exploitation-Based Deep CNN
Drones are unmanned aerial vehicles (UAV) utilized for a broad range of functions, including delivery, aerial surveillance, traffic monitoring, architecture monitoring, and even War-field. Drones confront significant obstacles while navigating independently in complex and highly dynamic environments...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9878336/ |
| _version_ | 1811261367249797120 |
|---|---|
| author | Muhammad Arif Arshad Saddam Hussain Khan Suleman Qamar Muhammad Waleed Khan Iqbal Murtza Jeonghwan Gwak Asifullah Khan |
| author_facet | Muhammad Arif Arshad Saddam Hussain Khan Suleman Qamar Muhammad Waleed Khan Iqbal Murtza Jeonghwan Gwak Asifullah Khan |
| author_sort | Muhammad Arif Arshad |
| collection | DOAJ |
| description | Drones are unmanned aerial vehicles (UAV) utilized for a broad range of functions, including delivery, aerial surveillance, traffic monitoring, architecture monitoring, and even War-field. Drones confront significant obstacles while navigating independently in complex and highly dynamic environments. Moreover, the targeted objects within a dynamic environment have irregular morphology, occlusion, and minor contrast variation with the background. In this regard, a novel deep Convolutional Neural Network(CNN) based data-driven strategy is proposed for drone navigation in the complex and dynamic environment. The proposed Drone Split-Transform-and-Merge Region-and-Edge (Drone-STM-RENet) CNN is comprised of convolutional blocks where each block methodically implements region and edge operations to preserve a diverse set of targeted properties at multi-levels, especially in the congested environment. In each block, the systematic implementation of the average and max-pooling operations can deal with the region homogeneity and edge properties. Additionally, these convolutional blocks are merged at a multi-level to learn texture variation that efficiently discriminates the target from the background and helps obstacle avoidance. Finally, the Drone-STM-RENet generates steering angle and collision probability for each input image to control the drone moving while avoiding hindrances and allowing the UAV to spot risky situations and respond quickly, respectively. The proposed Drone-STM-RENet has been validated on two urban cars and bicycles datasets: udacity and collision-sequence, and achieved considerable performance in terms of explained variance (0.99), recall (95.47%), accuracy (96.26%), and F-score (91.95%). The promising performance of Drone-STM-RENet on urban road datasets suggests that the proposed model is generalizable and can be deployed for real-time autonomous drones navigation and real-world flights. |
| first_indexed | 2024-04-12T19:03:20Z |
| format | Article |
| id | doaj.art-6ddc3b942af74616ac785c5183943877 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T19:03:20Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-6ddc3b942af74616ac785c51839438772022-12-22T03:20:05ZengIEEEIEEE Access2169-35362022-01-0110954419545010.1109/ACCESS.2022.32048769878336Drone Navigation Using Region and Edge Exploitation-Based Deep CNNMuhammad Arif Arshad0Saddam Hussain Khan1Suleman Qamar2https://orcid.org/0000-0001-6528-1681Muhammad Waleed Khan3https://orcid.org/0000-0001-7532-0103Iqbal Murtza4Jeonghwan Gwak5https://orcid.org/0000-0002-6237-0141Asifullah Khan6https://orcid.org/0000-0003-2039-5305Department of Computer and Information Sciences, Pattern Recognition Lab, Pakistan Institute of Engineering & Applied Sciences, Nilore, Islamabad, PakistanDepartment of Computer and Information Sciences, Pattern Recognition Lab, Pakistan Institute of Engineering & Applied Sciences, Nilore, Islamabad, PakistanDepartment of Computer and Information Sciences, Pattern Recognition Lab, Pakistan Institute of Engineering & Applied Sciences, Nilore, Islamabad, PakistanDepartment of Computer and Information Sciences, Pattern Recognition Lab, Pakistan Institute of Engineering & Applied Sciences, Nilore, Islamabad, PakistanDepartment of Creative Technologies, Faculty of Computing and AI, Air University, Islamabad, PakistanDepartment of Software, Korea National University of Transportation, Chungju, South KoreaDepartment of Computer and Information Sciences, Pattern Recognition Lab, Pakistan Institute of Engineering & Applied Sciences, Nilore, Islamabad, PakistanDrones are unmanned aerial vehicles (UAV) utilized for a broad range of functions, including delivery, aerial surveillance, traffic monitoring, architecture monitoring, and even War-field. Drones confront significant obstacles while navigating independently in complex and highly dynamic environments. Moreover, the targeted objects within a dynamic environment have irregular morphology, occlusion, and minor contrast variation with the background. In this regard, a novel deep Convolutional Neural Network(CNN) based data-driven strategy is proposed for drone navigation in the complex and dynamic environment. The proposed Drone Split-Transform-and-Merge Region-and-Edge (Drone-STM-RENet) CNN is comprised of convolutional blocks where each block methodically implements region and edge operations to preserve a diverse set of targeted properties at multi-levels, especially in the congested environment. In each block, the systematic implementation of the average and max-pooling operations can deal with the region homogeneity and edge properties. Additionally, these convolutional blocks are merged at a multi-level to learn texture variation that efficiently discriminates the target from the background and helps obstacle avoidance. Finally, the Drone-STM-RENet generates steering angle and collision probability for each input image to control the drone moving while avoiding hindrances and allowing the UAV to spot risky situations and respond quickly, respectively. The proposed Drone-STM-RENet has been validated on two urban cars and bicycles datasets: udacity and collision-sequence, and achieved considerable performance in terms of explained variance (0.99), recall (95.47%), accuracy (96.26%), and F-score (91.95%). The promising performance of Drone-STM-RENet on urban road datasets suggests that the proposed model is generalizable and can be deployed for real-time autonomous drones navigation and real-world flights.https://ieeexplore.ieee.org/document/9878336/Residual networkdroneconvolutional neural networkperception and autonomydrone split transform merge |
| spellingShingle | Muhammad Arif Arshad Saddam Hussain Khan Suleman Qamar Muhammad Waleed Khan Iqbal Murtza Jeonghwan Gwak Asifullah Khan Drone Navigation Using Region and Edge Exploitation-Based Deep CNN IEEE Access Residual network drone convolutional neural network perception and autonomy drone split transform merge |
| title | Drone Navigation Using Region and Edge Exploitation-Based Deep CNN |
| title_full | Drone Navigation Using Region and Edge Exploitation-Based Deep CNN |
| title_fullStr | Drone Navigation Using Region and Edge Exploitation-Based Deep CNN |
| title_full_unstemmed | Drone Navigation Using Region and Edge Exploitation-Based Deep CNN |
| title_short | Drone Navigation Using Region and Edge Exploitation-Based Deep CNN |
| title_sort | drone navigation using region and edge exploitation based deep cnn |
| topic | Residual network drone convolutional neural network perception and autonomy drone split transform merge |
| url | https://ieeexplore.ieee.org/document/9878336/ |
| work_keys_str_mv | AT muhammadarifarshad dronenavigationusingregionandedgeexploitationbaseddeepcnn AT saddamhussainkhan dronenavigationusingregionandedgeexploitationbaseddeepcnn AT sulemanqamar dronenavigationusingregionandedgeexploitationbaseddeepcnn AT muhammadwaleedkhan dronenavigationusingregionandedgeexploitationbaseddeepcnn AT iqbalmurtza dronenavigationusingregionandedgeexploitationbaseddeepcnn AT jeonghwangwak dronenavigationusingregionandedgeexploitationbaseddeepcnn AT asifullahkhan dronenavigationusingregionandedgeexploitationbaseddeepcnn |