Improving the Model for Person Detection in Aerial Image Sequences Using the Displacement Vector: A Search and Rescue Scenario

Vasić, Mirela Kundid; Papić, Vladan

doi:10.3390/drones6010019

Cited by 9 publications

(6 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…High-definition cameras are also the most commonly used payload sensor, together with infrared cameras or LIDAR. The processing of images from the payload cameras can be used in missions such as building inspection (i.e., the identification of harmful asbestos slates [8] or the identification of damage to multiple steel surfaces from panorama images [9]), road traffic surveillance [10], and search and rescue [11]. Automatically labelling the images with significant information helps law enforcement agents to detect situations that need to be corrected or to find people that are lost.…”

Section: Previous Workmentioning

confidence: 99%

Enhancing Drones for Law Enforcement and Capacity Monitoring at Open Large Events

Royo

Asenjo

Trujillo

et al. 2022

Drones

View full text Add to dashboard Cite

Police tasks related with law enforcement and citizen protection have gained a very useful asset in drones. Crowded demonstrations, large sporting events, or summer festivals are typical situations when aerial surveillance is necessary. The eyes in the sky are moving from the use of manned helicopters to drones due to costs, environmental impact, and discretion, resulting in local, regional, and national police forces possessing specific units equipped with drones. In this paper, we describe an artificial intelligence solution developed for the Castelldefels local police (Barcelona, Spain) to enhance the capabilities of drones used for the surveillance of large events. In particular, we propose a novel methodology for the efficient integration of deep learning algorithms in drone avionics. This integration improves the capabilities of the drone for tasks related with capacity control. These tasks have been very relevant during the pandemic and beyond. Controlling the number of persons in an open area is crucial when the expected crowd might exceed the capacity of the area and put humans in danger. The new methodology proposes an efficient and accurate execution of deep learning algorithms, which are usually highly demanding for computation resources. Results show that the state-of-the-art artificial intelligence models are too slow when utilised in the drone standard equipment. These models lose accuracy when images are taken at altitudes above 30 metres. With our new methodology, these two drawbacks can be overcome and results with good accuracy (96% correct segmentation and between 20% and 35% mean average proportional error) can be obtained in less than 20 s.

show abstract

Section: Previous Workmentioning

confidence: 99%

Enhancing Drones for Law Enforcement and Capacity Monitoring at Open Large Events

Royo

Asenjo

Trujillo

et al. 2022

Drones

View full text Add to dashboard Cite

show abstract

“…Finally, the ratio of the sum area of all bounding boxes to the number of bounding boxes is defined in (7). It reflects the average size of the objects in the sub-region.…”

Section: Adaptive Sub-regions Selection Algorithm (Assa)mentioning

confidence: 99%

“…Nowadays, as a fast-growing number of Unmanned Aerial Vehicles (UAVs) start carrying high-definition cameras, object detection technology in aerial images has been widely used in various practical applications, including agricultural planting [1,2], pedestrian tracking [3], urban security [4,5], inspecting buildings [6], search and rescue [7], and rare plant monitoring [8]. These applications all require accurate object detection in visible or infrared images taken by onboard cameras.…”

Section: Introductionmentioning

confidence: 99%

ARSD: An Adaptive Region Selection Object Detection Framework for UAV Images

Wan

Zhong

Huang³

et al. 2022

Drones

View full text Add to dashboard Cite

Due to the rapid development of deep learning, the performance of object detection has greatly improved. However, object detection in high-resolution Unmanned Aerial Vehicles images remains a challenging problem for three main reasons: (1) the objects in aerial images have different scales and are usually small; (2) the images are high-resolution but state-of-the-art object detection networks are of a fixed size; (3) the objects are not evenly distributed in aerial images. To this end, we propose a two-stage Adaptive Region Selection Detection framework in this paper. An Overall Region Detection Network is first applied to coarsely localize the object. A fixed points density-based targets clustering algorithm and an adaptive selection algorithm are then designed to select object-dense sub-regions. The object-dense sub-regions are sent to a Key Regions Detection Network where results are fused with the results at the first stage. Extensive experiments and comprehensive evaluations on the VisDrone2021-DET benchmark datasets demonstrate the effectiveness and adaptiveness of the proposed framework. Experimental results show that the proposed framework outperforms, in terms of mean average precision (mAP), the existing baseline methods by 2.1% without additional time consumption.

show abstract

“…Some findings and results obtained during the development of such an expert system are already presented, but they relate to the transmission of images from UAVs to the ground station [16] and novel algorithms for person detection in aerial images [24,25].…”

Section: Introductionmentioning

confidence: 99%

Person Mobility Algorithm and Geographic Information System for Search and Rescue Missions Planning

Papić,

Gudelj,

Milan

et al. 2024

Remote Sensing

Self Cite

View full text Add to dashboard Cite

In search and rescue (SAR) operations, up-to-date information on the terrain is critical because every additional hour required to search for a person reduces the likelihood of success. Therefore, it is necessary to provide quick access and the best possible input data for planners and search teams and to develop tools that can help them plan and monitor actions in real-time. This paper describes a novel system based on the use of GIS for planning actions and visualizing the situation on the ground. Special focus is devoted to the algorithm for assessing the mobility of the missing person. Using this algorithm, the area of the proposed search area is modeled based on obtained information about the type of terrain on which the searches are planned. The obtained results are presented as a new Geographic Information System layer and have proven to be a quality that helps in defining the search space. Further research is discussed, especially regarding the assessment of the passability of certain types of terrain.

show abstract

Improving the Model for Person Detection in Aerial Image Sequences Using the Displacement Vector: A Search and Rescue Scenario

Cited by 9 publications

References 38 publications

Enhancing Drones for Law Enforcement and Capacity Monitoring at Open Large Events

Enhancing Drones for Law Enforcement and Capacity Monitoring at Open Large Events

ARSD: An Adaptive Region Selection Object Detection Framework for UAV Images

Person Mobility Algorithm and Geographic Information System for Search and Rescue Missions Planning

Contact Info

Product

Resources

About