Human Target Search and Detection using Autonomous UAV and Deep learning

Das, Lyla B; Lijiya, A; Jagadanand, G; Aadith, A; Gautham, Sai M. R.; Mohan, Vandanan; Reuben, S; George, Geo

doi:10.1109/iaict50021.2020.9172031

Cited by 11 publications

(9 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several search and rescue methods have been proposed recently [14][15][16]. In [14], the sweep line search method conducts a thorough search from left to right, as illustrated in Figure 1.…”

Section: Related Work 21 Traditional Unmanned Aerial Vehicle Path Pla...mentioning

confidence: 99%

An Integrated YOLOv5 and Hierarchical Human-Weight-First Path Planning Approach for Efficient UAV Searching Systems

Chang,

Yen,

Chang

et al. 2024

Machines

View full text Add to dashboard Cite

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.

show abstract

Section: Related Work 21 Traditional Unmanned Aerial Vehicle Path Pla...mentioning

confidence: 99%

An Integrated YOLOv5 and Hierarchical Human-Weight-First Path Planning Approach for Efficient UAV Searching Systems

Chang,

Yen,

Chang

et al. 2024

Machines

View full text Add to dashboard Cite

show abstract

“…A deep learning strategy for human target search and detection using unmanned aerial vehicles (UAVs) is proposed in [52] A system designed by the authors makes it possible for an unmanned aerial vehicle (UAV) to search for and identify human targets in challenging environments. A large dataset of human targets is used to train the system's deep neural network, which is used to make decisions about what to do based on environmental observations.…”

Section: Search For An Objectmentioning

confidence: 99%

“…Objective Methodology [51] Autonomous UAV navigation and object localization RL-based decision making using a Deep Neural Network [52] Human target search and detection using UAVs DL-based decision-making using a Deep NN trained on a large dataset of human targets [53] Object tracking in drone images Rl-based decision-making using a Deep NN [54] Vision-based autonomous drone navigation in real-world scenarios RL-based decision making using visual observations of the environment [55] Human detection in real-time UAV applications Deep NN-based YOLO-v2 object detection algorithm [56] Use of drones for search and rescue in natural disasters…”

Section: Studymentioning

confidence: 99%

A Comprehensive Review of Classification and Application of Machine Learning in Drone Technology

Haque¹,

Chowdhury²,

Hassanalian³

2023

Preprint

View full text Add to dashboard Cite

The use of drones for various applications has become increasingly popular in recent years, and machine learning has played a significant role in this trend. In this paper, we provide a comprehensive survey of the classification and application of machine learning in drones. The paper begins with an overview of the different types of machine learning algorithms and their applications in drones, including supervised learning, unsupervised learning, and reinforcement learning. Next, we present a detailed analysis of various real-world applications of machine learning in drones, such as object recognition, route planning, obstacle avoidance, search area optimization, and autonomous search. The paper also discusses the challenges and limitations of using machine learning in drones, such as data privacy, data quality, and computational requirements. Finally, the paper concludes with a discussion of the future directions of machine learning in drones and its potential impact on various industries and fields. This paper provides a valuable resource for researchers, practitioners, and students interested in the intersection of machine learning and drones.

show abstract

“…In recognition of the target, the UAV will either be wont to hold its position thus to have a video feed of the target or come to its base station. The coordinates are calculable victimization GPS modules or relay the GPS location to the bottom station [88].…”

Section: Human Target Search and Detectionmentioning

confidence: 99%

A reawakening of Machine Learning Application in Unmanned Aerial Vehicle: Future Research Motivation

Shafik

Matinkhah

Shokoor

et al. 2022

EAI Endorsed Trans IoT

View full text Add to dashboard Cite

Machine learning (ML) entails artificial procedures that improve robotically through experience and using data. Supervised, unsupervised, semi-supervised, and Reinforcement Learning (RL) are the main types of ML. This study mainly focuses on RL and Deep learning, since necessitates mainly sequential and consecutive decision-making context. This is a comparison to supervised and non-supervised learning due to the interactive nature of the environment. Exploiting a forthcoming accumulative compensation and its stimulus of machines, complex policy decisions. The study further analyses and presents ML perspectives depicting state-of-the-art developments with advancement, relatively depicting the future trend of RL based on its applicability in technology. It's a challenge to an Internet of Things (IoT) and demonstrates what possibly can be adopted as a solution. This study presented a summarized perspective on identified arenas on the analysis of RL. The study scrutinized that a reasonable number of the techniques engrossed in alternating policy values instead of modifying other gears in an exact state of intellectual. The study presented a strong foundation for the current studies to be adopted by the researchers from different research backgrounds to develop models, and architectures that are relevant.

show abstract

Human Target Search and Detection using Autonomous UAV and Deep learning

Cited by 11 publications

References 5 publications

An Integrated YOLOv5 and Hierarchical Human-Weight-First Path Planning Approach for Efficient UAV Searching Systems

An Integrated YOLOv5 and Hierarchical Human-Weight-First Path Planning Approach for Efficient UAV Searching Systems

A Comprehensive Review of Classification and Application of Machine Learning in Drone Technology

A reawakening of Machine Learning Application in Unmanned Aerial Vehicle: Future Research Motivation

Contact Info

Product

Resources

About