Person Identification from Drones by Humans: Insights from Cognitive Psychology

Fysh, Matthew C.; Bindemann, Markus

doi:10.3390/drones2040032

Cited by 12 publications

(4 citation statements)

References 57 publications

(101 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…> 20 o sensor view angle from watch towers or UAV). However, due to the unique characteristics of aerial footage, human identification from aerial footage is very challenging, even for humans [10], [43]. This section reviews face and gait recognition, and person re-identification in the aerial surveillance setting.…”

Section: Aerial Human Identificationmentioning

confidence: 99%

The State of Aerial Surveillance: A Survey

Nguyen¹,

Fookes²,

Sridharan³

et al. 2022

Preprint

View full text Add to dashboard Cite

The rapid emergence of airborne platforms and imaging sensors are enabling new forms of aerial surveillance due to their unprecedented advantages in scale, mobility, deployment and covert observation capabilities. This paper provides a comprehensive overview of human-centric aerial surveillance tasks from a computer vision and pattern recognition perspective. It aims to provide readers with an in-depth systematic review and technical analysis of the current state of aerial surveillance tasks using drones, UAVs and other airborne platforms. The main object of interest is humans, where single or multiple subjects are to be detected, identified, tracked, re-identified and have their behavior analyzed. More specifically, for each of these four tasks, we first discuss unique challenges in performing these tasks in an aerial setting compared to a ground-based setting. We then review and analyze the aerial datasets publicly available for each task, and delve deep into the approaches in the aerial literature and investigate how they presently address the aerial challenges. We conclude the paper with discussion on the missing gaps and open research questions to inform future research avenues.

show abstract

Section: Aerial Human Identificationmentioning

confidence: 99%

The State of Aerial Surveillance: A Survey

Nguyen¹,

Fookes²,

Sridharan³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The availability of UAV datasets [16], [18], [19] has fostered aerial video research [20] pertaining to person reidentification [21], human detection [22], tracking [23], [24], pose estimation [25], few-shot learning [26], drone detection [27] and path planning [28]. Many architectures have been proposed to specifically tackle aerial video action recognition [29], [30], [31], [32], in addition to generic action recognition [2], [3].…”

Section: Related Work A) Aerial Video Recognitionmentioning

confidence: 99%

Differentiable Frequency-based Disentanglement for Aerial Video Action Recognition

Kothandaraman¹,

Ma²,

Manocha³

2022

Preprint

View full text Add to dashboard Cite

We present a learning algorithm for human activity recognition in videos. Our approach is designed for UAV videos, which are mainly acquired from obliquely placed dynamic cameras that contain a human actor along with background motion. Typically, the human actors occupy less than one-tenth of the spatial resolution. Our approach simultaneously harnesses the benefits of frequency domain representations, a classical analysis tool in signal processing, and data driven neural networks. We build a differentiable staticdynamic frequency mask prior to model the salient static and dynamic pixels in the video, crucial for the underlying task of action recognition. We use this differentiable mask prior to enable the neural network to intrinsically learn disentangled feature representations via an identity loss function. Our formulation empowers the network to inherently compute disentangled salient features within its layers. Further, we propose a cost-function encapsulating temporal relevance and spatial content to sample the most important frame within uniformly spaced video segments. We conduct extensive experiments on the UAV Human dataset and the NEC Drone dataset and demonstrate relative improvements of 5.72% − 13.00% over the state-of-the-art and 14.28% − 38.05% over the corresponding baseline model.

show abstract

“…The phenomenon of missing persons has remained constant over time, but today, thanks to this technology, it is possible to operate search and rescue activities with reduced intervention times and a wider field of action, saving human resources and lowering costs, but above all limiting the risks for operators. However, most of all, they have obtained a greater success rate not only in finding people but in finding them alive [6,[31][32][33].…”

Section: The Use Of Drones To Search For Missing Peoplementioning

confidence: 99%

Drones as an Integral Part of Remote Sensing Technologies to Help Missing People

Pensieri

Garau²,

Barone

2020

Drones

View full text Add to dashboard Cite

Due to the versatility of the drone, it can be applied in various areas and for different uses and as a practical support for human activities. In particular, this paper focuses on the situation in Italy and how the authorities use drones for the search and rescue of missing persons, especially now that a 10-year plague that has afflicted Italy with a large number of such incidents annually. Knowledge of the current legislation, the implementation of the drone with other instruments, specific pilot training, and experiential contributions are all essential elements that can provide exceptional assistance in search and rescue operations. However, to guarantee maximum effectiveness of the rescue device, they should seriously consider including teams with proven expertise in operating drones and count on their valuable contribution. Besides drones’ capacity to search large areas, thereby reducing the use of human resources and possibly limiting intervention times, to operate in difficult terrain and/or dangerous conditions for rescue teams, remote sensing tools (such as GPR or ground penetrating radar) as well as other disciplines (such as forensic archeology and, more generally, forensic geosciences) can be implemented to carry out search and rescue missions in case of missing persons.

show abstract

Person Identification from Drones by Humans: Insights from Cognitive Psychology

Cited by 12 publications

References 57 publications

The State of Aerial Surveillance: A Survey

The State of Aerial Surveillance: A Survey

Differentiable Frequency-based Disentanglement for Aerial Video Action Recognition

Drones as an Integral Part of Remote Sensing Technologies to Help Missing People

Contact Info

Product

Resources

About