With the rapid development of marine resource exploitation and the increasing demand for underwater robot inspection, achieving reliable target perception in turbid, low-illumination, and spectrally ...

Abstract: The performance of existing object detection algorithms significantly degrades when applied to low-resolution infrared (IR) images captured by unmanned aerial vehicles (UAVs), which suffers ...

The broad range of Scolytinae pests sizes and their subtle visual similarities, especially in smaller species, continue to challenge the accuracy of mainstream object detection models. To address ...

Traffic monitoring plays a vital role in smart city infrastructure, road safety, and urban planning. Traditional detection systems, including earlier deep learning models, often struggle with ...

1 Ambam Computer Science and Application Laboratory & Department of Computer Engineering, Higher Institute of Transport, Logistics and Commerce, University of Ebolowa, Ebolowa, Cameroon. 2 Institut ...

Abstract: The task of real-time object detection aims to identify targets from video streams or continuous image sequences with minimal latency. However, detecting small and easily occluded ...

Benchmarks tested on Intel i7-10700K CPU and NVIDIA RTX 3070 GPU ...