Deep convolutional neural networks and Swin transformer-based frameworks for individual date palm tree detection and mapping from large-scale UAV images

MBA Gibril, HZM Shafri, A Shanableh… - Geocarto …, 2022 - Taylor & Francis
Timely and reliable mapping of individual date palm trees is essential for their monitoring,
health and risk assessment, pest control, and sustainable management of the date palm …

Potential cyber threats of adversarial attacks on autonomous driving models

E Boltachev - Journal of Computer Virology and Hacking Techniques, 2023 - Springer
Abstract Autonomous Vehicles (CAVs) are currently seen as a viable alternative to
traditional vehicles. However, CAVs will face serious cyber threats because many …

Optimized transfer learning based multi-modal medical image retrieval

MH Abid, R Ashraf, T Mahmood, CMN Faisal - Multimedia Tools and …, 2024 - Springer
Disease diagnosis using the medical image is a very technical and tedious process. Small
abnormalities in multiple medical images could be noticed by medical specialists but deep …

Adversarial attack on human pose estimation network

Z Zhang, S Huang, X Liu, Q Fan… - Journal of Electronic …, 2024 - spiedigitallibrary.org
Real-time human pose estimation (HPE) using convolutional neural networks (CNN) is
critical for enabling machines to better understand human beings based on images and …

Trusted Perception Method for Traffic Signs That Are Physically Attacked

S Huang, Q Tan, Z Zhang, Q Fan… - Transportation …, 2024 - journals.sagepub.com
Traffic sign recognition is a crucial method by which autonomous driving systems acquire
road information, and is predominantly based on deep neural networks (DNNs). However …

[HTML][HTML] Segment Shards: Cross-Prompt Adversarial Attacks against the Segment Anything Model

S Huang, Q Fan, Z Zhang, X Liu, G Song, J Qin - Applied Sciences, 2024 - mdpi.com
Foundation models play an increasingly pivotal role in the field of deep neural networks.
Given that deep neural networks are widely used in real-world systems and are generally …

A visual detection method for conveyor belt misalignment based on the improved YOLACT network

C Jin, J Yuan, J Shen, C Wheeler, Z Liu… - Particulate Science and …, 2024 - Taylor & Francis
Conveyor belt misalignment is an operational and maintenance issue for many belt
conveyor systems and can result in significant downtime and equipment failure. This article …

Hijacking Robot Teams Through Adversarial Communication

Z Wu, SC Ye, B Han, M Gombolay - 7th Annual Conference on …, 2023 - openreview.net
Communication is often necessary for robot teams to collaborate and complete a
decentralized task. Multi-agent reinforcement learning (MARL) systems allow agents to learn …

Autonomous Classification and Spatial Location of Objects from Stereoscopic Image Sequences for the Visually Impaired

TM Sivate, N Pillay, K Moorgas… - … Conference on Electrical …, 2022 - ieeexplore.ieee.org
One of the main problems faced by visually impaired individuals is the inability or difficulty to
identify objects. A visually impaired person usually wears glasses that help to enlarge or …

A Survey on Attacks and Defenses Targeting Region Proposals in Object Detectors

MB Larsen - 2022 - ntnuopen.ntnu.no
Object detectors have established their dominance in several safety-critical systems.
Meanwhile, there are an increasing number of research proving they are prone to carefully …