ARCN: A Real-time Attention-based Network for Crowd Counting from Drone Images

Nag, Subhrajit; Khandelwal, Yash; Mittal, Sparsh; Mohan, C. Krishna; Qin, A. K.

doi:10.1109/indicon52576.2021.9691659

Cited by 3 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Obtained results show that using this a high-quality network camera in conjunction with AI framework offered a notable advantage of minimal distortion and a high-resolution result. Attention-Based Real-time CrowdNet (ARCN) decoding model is presented in [13], which is a computationally efficient density estimation-based crowd counting model that perform crowdcounting from UAV images in real-time with high accuracy. The key idea of this model is to add a "Convolution Block Attention Module" (CBAM) blocks between the bottleneck layers of the MobileCount architecture to focus on crowds and ignore background information of the obtained images.…”

Section: Related Studymentioning

confidence: 99%

Developing CubeSat and AI Framework for Crowd Management Case of Short-Term Large-Scale Events

Almalki¹,

Mutawi²,

Turkistani³

et al. 2022

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

Many consequences can be resulted in mismanagement of crowd, which might get people injured or even lose their lives. Thus, crowd management helps in controlling overcrowded areas during events, and allowing authorities to monitor, manage and reduce incidents. Space science and technology have made huge leap in crowd management, let alone when this technology integrated with Artificial intelligent. Hence, space-based systems like CubeSats are seen as the best approach to help monitoring and providing various reasons. For instance, wide coverage footprint, collect specific area data simultaneously, assist in aerial photography, as well as providing wide range of wireless communications services that can integrate appropriately with AI and wearable devices. This work aims to design a CubeSat vehicle to manage crowds during short-term, large-scale events. The proposed system is, also, coupled with AI framework along with the camera and wearable devices to monitor the crowds' performance continuously by relying on two aspects: Firstly, aerial imaging (e.g., photos and videos). Secondly, using wearable devices that can be worn to monitor vital signs of crowds. Moreover, the proposed system can independently relieve congestion, as well as notify the ground controller of all problems to take further actions. The obtained results confirm that the proposed innovative solution is for crowd management with accuracy reached 95%, and MSE equal to 0.049.

show abstract

Section: Related Studymentioning

confidence: 99%