An Integrated YOLOv5 and Hierarchical Human-Weight-First Path Planning Approach for Efficient UAV Searching Systems
Because the average number of missing people in our country is more than 20,000 per year, determining how to efficiently locate missing people is important. The traditional method of finding missing people involves deploying fixed cameras in some hotspots to capture images and using humans to identi...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Machines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1702/12/1/65 |
| _version_ | 1797343131073511424 |
|---|---|
| author | Ing-Chau Chang Chin-En Yen Hao-Fu Chang Yi-Wei Chen Ming-Tsung Hsu Wen-Fu Wang Da-Yi Yang Yu-Hsuan Hsieh |
| author_facet | Ing-Chau Chang Chin-En Yen Hao-Fu Chang Yi-Wei Chen Ming-Tsung Hsu Wen-Fu Wang Da-Yi Yang Yu-Hsuan Hsieh |
| author_sort | Ing-Chau Chang |
| collection | DOAJ |
| description | Because the average number of missing people in our country is more than 20,000 per year, determining how to efficiently locate missing people is important. The traditional method of finding missing people involves deploying fixed cameras in some hotspots to capture images and using humans to identify targets from these images. However, in this approach, high costs are incurred in deploying sufficient cameras in order to avoid blind spots, and a great deal of time and human effort is wasted in identifying possible targets. Further, most AI-based search systems focus on how to improve the human body recognition model, without considering how to speed up the search in order to shorten the search time and improve search efficiency, which is the aim of this study. Hence, by exploiting the high-mobility characteristics of unmanned aerial vehicles (UAVs), this study proposes an integrated YOLOv5 and hierarchical human-weight-first (HWF) path planning framework to serve as an efficient UAV searching system, which works by dividing the whole searching process into two levels. At level one, a searching UAV is dispatched to a higher altitude to capture images, covering the whole search area. Then, the well-known artificial intelligence model YOLOv5 is used to identify all persons in the captured images and compute corresponding weighted scores for each block in the search area, according to the values of the identified human bodies, clothing types, and clothing colors. At level two, the UAV lowers its altitude to sequentially capture images for each block, in descending order according to its weighted score at level one, and it uses the YOLOv5 recognition model repeatedly until the search target is found. Two improved search algorithms, HWFR-S and HWFR-D, which incorporate the concept of the convenient visit threshold and weight difference, respectively, are further proposed to resolve the issue of the lengthy and redundant flight paths of HWF. The simulation results suggest that the HWF, HWFR-S, and HWFR-D search algorithms proposed in this study not only effectively reduce the length of a UAV’s search path and the number of search blocks but also decrease the search time required for a UAV to locate the search target, with a much higher search accuracy than the two traditional search algorithms. Moreover, this integrated YOLOv5 and HWF framework is implemented and tested in a real scenario to demonstrate its capability in enhancing the efficiency of a search and rescue operation. |
| first_indexed | 2024-03-08T10:43:13Z |
| format | Article |
| id | doaj.art-61bbe9d56e724ae5842bb664fabfea74 |
| institution | Directory Open Access Journal |
| issn | 2075-1702 |
| language | English |
| last_indexed | 2024-03-08T10:43:13Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machines |
| spelling | doaj.art-61bbe9d56e724ae5842bb664fabfea742024-01-26T17:24:36ZengMDPI AGMachines2075-17022024-01-011216510.3390/machines12010065An Integrated YOLOv5 and Hierarchical Human-Weight-First Path Planning Approach for Efficient UAV Searching SystemsIng-Chau Chang0Chin-En Yen1Hao-Fu Chang2Yi-Wei Chen3Ming-Tsung Hsu4Wen-Fu Wang5Da-Yi Yang6Yu-Hsuan Hsieh7Department of Computer Science and Information Engineering, National Changhua University of Education, Changhua 50007, TaiwanDepartment of Early Childhood Development and Education, Chaoyang University of Technology, Taichung 41349, TaiwanDepartment of Computer Science and Information Engineering, National Changhua University of Education, Changhua 50007, TaiwanDepartment of Computer Science and Information Engineering, National Changhua University of Education, Changhua 50007, TaiwanDepartment of Computer Science and Information Engineering, National Changhua University of Education, Changhua 50007, TaiwanDepartment of Computer Science and Information Engineering, National Changhua University of Education, Changhua 50007, TaiwanDepartment of Computer Science and Information Engineering, National Changhua University of Education, Changhua 50007, TaiwanDepartment of Computer Science and Information Engineering, National Changhua University of Education, Changhua 50007, TaiwanBecause the average number of missing people in our country is more than 20,000 per year, determining how to efficiently locate missing people is important. The traditional method of finding missing people involves deploying fixed cameras in some hotspots to capture images and using humans to identify targets from these images. However, in this approach, high costs are incurred in deploying sufficient cameras in order to avoid blind spots, and a great deal of time and human effort is wasted in identifying possible targets. Further, most AI-based search systems focus on how to improve the human body recognition model, without considering how to speed up the search in order to shorten the search time and improve search efficiency, which is the aim of this study. Hence, by exploiting the high-mobility characteristics of unmanned aerial vehicles (UAVs), this study proposes an integrated YOLOv5 and hierarchical human-weight-first (HWF) path planning framework to serve as an efficient UAV searching system, which works by dividing the whole searching process into two levels. At level one, a searching UAV is dispatched to a higher altitude to capture images, covering the whole search area. Then, the well-known artificial intelligence model YOLOv5 is used to identify all persons in the captured images and compute corresponding weighted scores for each block in the search area, according to the values of the identified human bodies, clothing types, and clothing colors. At level two, the UAV lowers its altitude to sequentially capture images for each block, in descending order according to its weighted score at level one, and it uses the YOLOv5 recognition model repeatedly until the search target is found. Two improved search algorithms, HWFR-S and HWFR-D, which incorporate the concept of the convenient visit threshold and weight difference, respectively, are further proposed to resolve the issue of the lengthy and redundant flight paths of HWF. The simulation results suggest that the HWF, HWFR-S, and HWFR-D search algorithms proposed in this study not only effectively reduce the length of a UAV’s search path and the number of search blocks but also decrease the search time required for a UAV to locate the search target, with a much higher search accuracy than the two traditional search algorithms. Moreover, this integrated YOLOv5 and HWF framework is implemented and tested in a real scenario to demonstrate its capability in enhancing the efficiency of a search and rescue operation.https://www.mdpi.com/2075-1702/12/1/65unmanned aerial vehiclehierarchical human-weight-first path planningartificial intelligence image recognitionYOLOv5searching corners without cameras |
| spellingShingle | Ing-Chau Chang Chin-En Yen Hao-Fu Chang Yi-Wei Chen Ming-Tsung Hsu Wen-Fu Wang Da-Yi Yang Yu-Hsuan Hsieh An Integrated YOLOv5 and Hierarchical Human-Weight-First Path Planning Approach for Efficient UAV Searching Systems Machines unmanned aerial vehicle hierarchical human-weight-first path planning artificial intelligence image recognition YOLOv5 searching corners without cameras |
| title | An Integrated YOLOv5 and Hierarchical Human-Weight-First Path Planning Approach for Efficient UAV Searching Systems |
| title_full | An Integrated YOLOv5 and Hierarchical Human-Weight-First Path Planning Approach for Efficient UAV Searching Systems |
| title_fullStr | An Integrated YOLOv5 and Hierarchical Human-Weight-First Path Planning Approach for Efficient UAV Searching Systems |
| title_full_unstemmed | An Integrated YOLOv5 and Hierarchical Human-Weight-First Path Planning Approach for Efficient UAV Searching Systems |
| title_short | An Integrated YOLOv5 and Hierarchical Human-Weight-First Path Planning Approach for Efficient UAV Searching Systems |
| title_sort | integrated yolov5 and hierarchical human weight first path planning approach for efficient uav searching systems |
| topic | unmanned aerial vehicle hierarchical human-weight-first path planning artificial intelligence image recognition YOLOv5 searching corners without cameras |
| url | https://www.mdpi.com/2075-1702/12/1/65 |
| work_keys_str_mv | AT ingchauchang anintegratedyolov5andhierarchicalhumanweightfirstpathplanningapproachforefficientuavsearchingsystems AT chinenyen anintegratedyolov5andhierarchicalhumanweightfirstpathplanningapproachforefficientuavsearchingsystems AT haofuchang anintegratedyolov5andhierarchicalhumanweightfirstpathplanningapproachforefficientuavsearchingsystems AT yiweichen anintegratedyolov5andhierarchicalhumanweightfirstpathplanningapproachforefficientuavsearchingsystems AT mingtsunghsu anintegratedyolov5andhierarchicalhumanweightfirstpathplanningapproachforefficientuavsearchingsystems AT wenfuwang anintegratedyolov5andhierarchicalhumanweightfirstpathplanningapproachforefficientuavsearchingsystems AT dayiyang anintegratedyolov5andhierarchicalhumanweightfirstpathplanningapproachforefficientuavsearchingsystems AT yuhsuanhsieh anintegratedyolov5andhierarchicalhumanweightfirstpathplanningapproachforefficientuavsearchingsystems AT ingchauchang integratedyolov5andhierarchicalhumanweightfirstpathplanningapproachforefficientuavsearchingsystems AT chinenyen integratedyolov5andhierarchicalhumanweightfirstpathplanningapproachforefficientuavsearchingsystems AT haofuchang integratedyolov5andhierarchicalhumanweightfirstpathplanningapproachforefficientuavsearchingsystems AT yiweichen integratedyolov5andhierarchicalhumanweightfirstpathplanningapproachforefficientuavsearchingsystems AT mingtsunghsu integratedyolov5andhierarchicalhumanweightfirstpathplanningapproachforefficientuavsearchingsystems AT wenfuwang integratedyolov5andhierarchicalhumanweightfirstpathplanningapproachforefficientuavsearchingsystems AT dayiyang integratedyolov5andhierarchicalhumanweightfirstpathplanningapproachforefficientuavsearchingsystems AT yuhsuanhsieh integratedyolov5andhierarchicalhumanweightfirstpathplanningapproachforefficientuavsearchingsystems |